annotate(body=None, x__xgafv=None)
Run image detection and annotation for a batch of images.
asyncBatchAnnotate(body=None, x__xgafv=None)
Run asynchronous image detection and annotation for a list of images.
annotate(body=None, x__xgafv=None)
Run image detection and annotation for a batch of images. Args: body: object, The request body. The object takes the form of: { # Multiple image annotation requests are batched into a single service call. "requests": [ # Required. Individual image annotation requests for this batch. { # Request for performing Google Cloud Vision API tasks over a user-provided # image, with user-requested features, and with context information. "imageContext": { # Image context and/or feature-specific parameters. # Additional context that may accompany the image. "latLongRect": { # Rectangle determined by min and max `LatLng` pairs. # Not used. "minLatLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # Min lat/long pair. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, "maxLatLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # Max lat/long pair. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, }, "languageHints": [ # List of languages to use for TEXT_DETECTION. In most cases, an empty value # yields the best results since it enables automatic language detection. For # languages based on the Latin alphabet, setting `language_hints` is not # needed. In rare cases, when the language of the text in the image is known, # setting a hint will help get better results (although it will be a # significant hindrance if the hint is wrong). Text detection returns an # error if one or more of the specified languages is not one of the # [supported languages](/vision/docs/languages). "A String", ], "productSearchParams": { # Parameters for a product search request. # Parameters for product search. "productCategories": [ # The list of product categories to search in. Currently, we only consider # the first category, and either "homegoods-v2", "apparel-v2", "toys-v2", # "packagedgoods-v1", or "general-v1" should be specified. The legacy # categories "homegoods", "apparel", and "toys" are still supported but will # be deprecated. For new products, please use "homegoods-v2", "apparel-v2", # or "toys-v2" for better product search accuracy. It is recommended to # migrate existing products to these categories as well. "A String", ], "filter": "A String", # The filtering expression. This can be used to restrict search results based # on Product labels. We currently support an AND of OR of key-value # expressions, where each expression within an OR must have the same key. An # '=' should be used to connect the key and value. # # For example, "(color = red OR color = blue) AND brand = Google" is # acceptable, but "(color = red OR brand = Google)" is not acceptable. # "color: red" is not acceptable because it uses a ':' instead of an '='. "productSet": "A String", # The resource name of a ProductSet to be searched for similar images. # # Format is: # `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`. "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon around the area of interest in the image. # If it is not specified, system discretion will be applied. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, }, "cropHintsParams": { # Parameters for crop hints annotation request. # Parameters for crop hints annotation request. "aspectRatios": [ # Aspect ratios in floats, representing the ratio of the width to the height # of the image. For example, if the desired aspect ratio is 4/3, the # corresponding float value should be 1.33333. If not specified, the # best possible crop is returned. The number of provided aspect ratios is # limited to a maximum of 16; any aspect ratios provided after the 16th are # ignored. 3.14, ], }, "webDetectionParams": { # Parameters for web detection request. # Parameters for web detection. "includeGeoResults": True or False, # Whether to include results derived from the geo information in the image. }, }, "image": { # Client image to perform Google Cloud Vision API tasks over. # The image to be processed. "content": "A String", # Image content, represented as a stream of bytes. # Note: As with all `bytes` fields, protobuffers use a pure binary # representation, whereas JSON representations use base64. "source": { # External image source (Google Cloud Storage or web URL image location). # Google Cloud Storage image location, or publicly-accessible image # URL. If both `content` and `source` are provided for an image, `content` # takes precedence and is used to perform the image annotation request. "gcsImageUri": "A String", # **Use `image_uri` instead.** # # The Google Cloud Storage URI of the form # `gs://bucket_name/object_name`. Object versioning is not supported. See # [Google Cloud Storage Request # URIs](https://cloud.google.com/storage/docs/reference-uris) for more info. "imageUri": "A String", # The URI of the source image. Can be either: # # 1. A Google Cloud Storage URI of the form # `gs://bucket_name/object_name`. Object versioning is not supported. See # [Google Cloud Storage Request # URIs](https://cloud.google.com/storage/docs/reference-uris) for more # info. # # 2. A publicly-accessible image HTTP/HTTPS URL. When fetching images from # HTTP/HTTPS URLs, Google cannot guarantee that the request will be # completed. Your request may fail if the specified host denies the # request (e.g. due to request throttling or DOS prevention), or if Google # throttles requests to the site for abuse prevention. You should not # depend on externally-hosted images for production applications. # # When both `gcs_image_uri` and `image_uri` are specified, `image_uri` takes # precedence. }, }, "features": [ # Requested features. { # The type of Google Cloud Vision API detection to perform, and the maximum # number of results to return for that type. Multiple `Feature` objects can # be specified in the `features` list. "model": "A String", # Model to use for the feature. # Supported values: "builtin/stable" (the default if unset) and # "builtin/latest". "type": "A String", # The feature type. "maxResults": 42, # Maximum number of results of this type. Does not apply to # `TEXT_DETECTION`, `DOCUMENT_TEXT_DETECTION`, or `CROP_HINTS`. }, ], }, ], "parent": "A String", # Optional. Target project and location to make a call. # # Format: `projects/{project-id}/locations/{location-id}`. # # If no parent is specified, a region will be chosen automatically. # # Supported location-ids: # `us`: USA country only, # `asia`: East asia areas, like Japan, Taiwan, # `eu`: The European Union. # # Example: `projects/project-A/locations/eu`. } x__xgafv: string, V1 error format. Allowed values 1 - v1 error format 2 - v2 error format Returns: An object of the form: { # Response to a batch image annotation request. "responses": [ # Individual responses to image annotation requests within the batch. { # Response to an image annotation request. "safeSearchAnnotation": { # Set of features pertaining to the image, computed by computer vision # If present, safe-search annotation has completed successfully. # methods over safe-search verticals (for example, adult, spoof, medical, # violence). "spoof": "A String", # Spoof likelihood. The likelihood that an modification # was made to the image's canonical version to make it appear # funny or offensive. "violence": "A String", # Likelihood that this image contains violent content. "medical": "A String", # Likelihood that this is a medical image. "adult": "A String", # Represents the adult content likelihood for the image. Adult content may # contain elements such as nudity, pornographic images or cartoons, or # sexual activities. "racy": "A String", # Likelihood that the request image contains racy content. Racy content may # include (but is not limited to) skimpy or sheer clothing, strategically # covered nudity, lewd or provocative poses, or close-ups of sensitive # body areas. }, "textAnnotations": [ # If present, text (OCR) detection has completed successfully. { # Set of detected entity features. "confidence": 3.14, # **Deprecated. Use `score` instead.** # The accuracy of the entity detection in an image. # For example, for an image in which the "Eiffel Tower" entity is detected, # this field represents the confidence that there is a tower in the query # image. Range [0, 1]. "description": "A String", # Entity textual description, expressed in its `locale` language. "locale": "A String", # The language code for the locale in which the entity textual # `description` is expressed. "topicality": 3.14, # The relevancy of the ICA (Image Content Annotation) label to the # image. For example, the relevancy of "tower" is likely higher to an image # containing the detected "Eiffel Tower" than to an image containing a # detected distant towering building, even though the confidence that # there is a tower in each image may be the same. Range [0, 1]. "locations": [ # The location information for the detected entity. Multiple # `LocationInfo` elements can be present because one location may # indicate the location of the scene in the image, and another location # may indicate the location of the place where the image was taken. # Location information is usually present for landmarks. { # Detected entity location information. "latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, }, ], "mid": "A String", # Opaque entity ID. Some IDs may be available in # [Google Knowledge Graph Search # API](https://developers.google.com/knowledge-graph/). "score": 3.14, # Overall score of the result. Range [0, 1]. "boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Not produced # for `LABEL_DETECTION` features. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "properties": [ # Some entities may have optional user-supplied `Property` (name/value) # fields, such a score or string that qualifies the entity. { # A `Property` consists of a user-supplied name/value pair. "uint64Value": "A String", # Value of numeric properties. "name": "A String", # Name of the property. "value": "A String", # Value of the property. }, ], }, ], "webDetection": { # Relevant information for the image from the Internet. # If present, web detection has completed successfully. "fullMatchingImages": [ # Fully matching images from the Internet. # Can include resized copies of the query image. { # Metadata for online images. "url": "A String", # The result image URL. "score": 3.14, # (Deprecated) Overall relevancy score for the image. }, ], "pagesWithMatchingImages": [ # Web pages containing the matching images from the Internet. { # Metadata for web pages. "pageTitle": "A String", # Title for the web page, may contain HTML markups. "url": "A String", # The result web page URL. "score": 3.14, # (Deprecated) Overall relevancy score for the web page. "partialMatchingImages": [ # Partial matching images on the page. # Those images are similar enough to share some key-point features. For # example an original image will likely have partial matching for its # crops. { # Metadata for online images. "url": "A String", # The result image URL. "score": 3.14, # (Deprecated) Overall relevancy score for the image. }, ], "fullMatchingImages": [ # Fully matching images on the page. # Can include resized copies of the query image. { # Metadata for online images. "url": "A String", # The result image URL. "score": 3.14, # (Deprecated) Overall relevancy score for the image. }, ], }, ], "visuallySimilarImages": [ # The visually similar image results. { # Metadata for online images. "url": "A String", # The result image URL. "score": 3.14, # (Deprecated) Overall relevancy score for the image. }, ], "partialMatchingImages": [ # Partial matching images from the Internet. # Those images are similar enough to share some key-point features. For # example an original image will likely have partial matching for its crops. { # Metadata for online images. "url": "A String", # The result image URL. "score": 3.14, # (Deprecated) Overall relevancy score for the image. }, ], "webEntities": [ # Deduced entities from similar images on the Internet. { # Entity deduced from similar images on the Internet. "entityId": "A String", # Opaque entity ID. "score": 3.14, # Overall relevancy score for the entity. # Not normalized and not comparable across different image queries. "description": "A String", # Canonical description of the entity, in English. }, ], "bestGuessLabels": [ # The service's best guess as to the topic of the request image. # Inferred from similar images on the open web. { # Label to provide extra metadata for the web detection. "languageCode": "A String", # The BCP-47 language code for `label`, such as "en-US" or "sr-Latn". # For more information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "label": "A String", # Label for extra metadata. }, ], }, "localizedObjectAnnotations": [ # If present, localized object detection has completed successfully. # This will be sorted descending by confidence score. { # Set of detected objects with bounding boxes. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "score": 3.14, # Score of the result. Range [0, 1]. "name": "A String", # Object name, expressed in its `language_code` language. "boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this object belongs. This must be populated. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "mid": "A String", # Object ID that should align with EntityAnnotation mid. }, ], "error": { # The `Status` type defines a logical error model that is suitable for # If set, represents the error message for the operation. # Note that filled-in image annotations are guaranteed to be # correct, even when `error` is set. # different programming environments, including REST APIs and RPC APIs. It is # used by [gRPC](https://github.com/grpc). Each `Status` message contains # three pieces of data: error code, error message, and error details. # # You can find out more about this error model and how to work with it in the # [API Design Guide](https://cloud.google.com/apis/design/errors). "message": "A String", # A developer-facing error message, which should be in English. Any # user-facing error message should be localized and sent in the # google.rpc.Status.details field, or localized by the client. "code": 42, # The status code, which should be an enum value of google.rpc.Code. "details": [ # A list of messages that carry the error details. There is a common set of # message types for APIs to use. { "a_key": "", # Properties of the object. Contains field @type with type URL. }, ], }, "labelAnnotations": [ # If present, label detection has completed successfully. { # Set of detected entity features. "confidence": 3.14, # **Deprecated. Use `score` instead.** # The accuracy of the entity detection in an image. # For example, for an image in which the "Eiffel Tower" entity is detected, # this field represents the confidence that there is a tower in the query # image. Range [0, 1]. "description": "A String", # Entity textual description, expressed in its `locale` language. "locale": "A String", # The language code for the locale in which the entity textual # `description` is expressed. "topicality": 3.14, # The relevancy of the ICA (Image Content Annotation) label to the # image. For example, the relevancy of "tower" is likely higher to an image # containing the detected "Eiffel Tower" than to an image containing a # detected distant towering building, even though the confidence that # there is a tower in each image may be the same. Range [0, 1]. "locations": [ # The location information for the detected entity. Multiple # `LocationInfo` elements can be present because one location may # indicate the location of the scene in the image, and another location # may indicate the location of the place where the image was taken. # Location information is usually present for landmarks. { # Detected entity location information. "latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, }, ], "mid": "A String", # Opaque entity ID. Some IDs may be available in # [Google Knowledge Graph Search # API](https://developers.google.com/knowledge-graph/). "score": 3.14, # Overall score of the result. Range [0, 1]. "boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Not produced # for `LABEL_DETECTION` features. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "properties": [ # Some entities may have optional user-supplied `Property` (name/value) # fields, such a score or string that qualifies the entity. { # A `Property` consists of a user-supplied name/value pair. "uint64Value": "A String", # Value of numeric properties. "name": "A String", # Name of the property. "value": "A String", # Value of the property. }, ], }, ], "imagePropertiesAnnotation": { # Stores image properties, such as dominant colors. # If present, image properties were extracted successfully. "dominantColors": { # Set of dominant colors and their corresponding scores. # If present, dominant colors completed successfully. "colors": [ # RGB color values with their score and pixel fraction. { # Color information consists of RGB channels, score, and the fraction of # the image that the color occupies in the image. "color": { # Represents a color in the RGBA color space. This representation is designed # RGB components of the color. # for simplicity of conversion to/from color representations in various # languages over compactness; for example, the fields of this representation # can be trivially provided to the constructor of "java.awt.Color" in Java; it # can also be trivially provided to UIColor's "+colorWithRed:green:blue:alpha" # method in iOS; and, with just a little work, it can be easily formatted into # a CSS "rgba()" string in JavaScript, as well. # # Note: this proto does not carry information about the absolute color space # that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, # DCI-P3, BT.2020, etc.). By default, applications SHOULD assume the sRGB color # space. # # Example (Java): # # import com.google.type.Color; # # // ... # public static java.awt.Color fromProto(Color protocolor) { # float alpha = protocolor.hasAlpha() # ? protocolor.getAlpha().getValue() # : 1.0; # # return new java.awt.Color( # protocolor.getRed(), # protocolor.getGreen(), # protocolor.getBlue(), # alpha); # } # # public static Color toProto(java.awt.Color color) { # float red = (float) color.getRed(); # float green = (float) color.getGreen(); # float blue = (float) color.getBlue(); # float denominator = 255.0; # Color.Builder resultBuilder = # Color # .newBuilder() # .setRed(red / denominator) # .setGreen(green / denominator) # .setBlue(blue / denominator); # int alpha = color.getAlpha(); # if (alpha != 255) { # result.setAlpha( # FloatValue # .newBuilder() # .setValue(((float) alpha) / denominator) # .build()); # } # return resultBuilder.build(); # } # // ... # # Example (iOS / Obj-C): # # // ... # static UIColor* fromProto(Color* protocolor) { # float red = [protocolor red]; # float green = [protocolor green]; # float blue = [protocolor blue]; # FloatValue* alpha_wrapper = [protocolor alpha]; # float alpha = 1.0; # if (alpha_wrapper != nil) { # alpha = [alpha_wrapper value]; # } # return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; # } # # static Color* toProto(UIColor* color) { # CGFloat red, green, blue, alpha; # if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { # return nil; # } # Color* result = [[Color alloc] init]; # [result setRed:red]; # [result setGreen:green]; # [result setBlue:blue]; # if (alpha <= 0.9999) { # [result setAlpha:floatWrapperWithValue(alpha)]; # } # [result autorelease]; # return result; # } # // ... # # Example (JavaScript): # # // ... # # var protoToCssColor = function(rgb_color) { # var redFrac = rgb_color.red || 0.0; # var greenFrac = rgb_color.green || 0.0; # var blueFrac = rgb_color.blue || 0.0; # var red = Math.floor(redFrac * 255); # var green = Math.floor(greenFrac * 255); # var blue = Math.floor(blueFrac * 255); # # if (!('alpha' in rgb_color)) { # return rgbToCssColor_(red, green, blue); # } # # var alphaFrac = rgb_color.alpha.value || 0.0; # var rgbParams = [red, green, blue].join(','); # return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); # }; # # var rgbToCssColor_ = function(red, green, blue) { # var rgbNumber = new Number((red << 16) | (green << 8) | blue); # var hexString = rgbNumber.toString(16); # var missingZeros = 6 - hexString.length; # var resultBuilder = ['#']; # for (var i = 0; i < missingZeros; i++) { # resultBuilder.push('0'); # } # resultBuilder.push(hexString); # return resultBuilder.join(''); # }; # # // ... "blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1]. "alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, # the final pixel color is defined by the equation: # # pixel color = alpha * (this color) + (1.0 - alpha) * (background color) # # This means that a value of 1.0 corresponds to a solid color, whereas # a value of 0.0 corresponds to a completely transparent color. This # uses a wrapper message rather than a simple float scalar so that it is # possible to distinguish between a default value and the value being unset. # If omitted, this color object is to be rendered as a solid color # (as if the alpha value had been explicitly given with a value of 1.0). "green": 3.14, # The amount of green in the color as a value in the interval [0, 1]. "red": 3.14, # The amount of red in the color as a value in the interval [0, 1]. }, "pixelFraction": 3.14, # The fraction of pixels the color occupies in the image. # Value in range [0, 1]. "score": 3.14, # Image-specific score for this color. Value in range [0, 1]. }, ], }, }, "faceAnnotations": [ # If present, face detection has completed successfully. { # A face annotation object contains the results of face detection. "panAngle": 3.14, # Yaw angle, which indicates the leftward/rightward angle that the face is # pointing relative to the vertical plane perpendicular to the image. Range # [-180,180]. "sorrowLikelihood": "A String", # Sorrow likelihood. "landmarkingConfidence": 3.14, # Face landmarking confidence. Range [0, 1]. "underExposedLikelihood": "A String", # Under-exposed likelihood. "detectionConfidence": 3.14, # Detection confidence. Range [0, 1]. "joyLikelihood": "A String", # Joy likelihood. "landmarks": [ # Detected face landmarks. { # A face-specific landmark (for example, a face feature). "position": { # A 3D position in the image, used primarily for Face detection landmarks. # Face landmark position. # A valid Position must have both x and y coordinates. # The position coordinates are in the same scale as the original image. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. "z": 3.14, # Z coordinate (or depth). }, "type": "A String", # Face landmark type. }, ], "surpriseLikelihood": "A String", # Surprise likelihood. "blurredLikelihood": "A String", # Blurred likelihood. "tiltAngle": 3.14, # Pitch angle, which indicates the upwards/downwards angle that the face is # pointing relative to the image's horizontal plane. Range [-180,180]. "angerLikelihood": "A String", # Anger likelihood. "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon around the face. The coordinates of the bounding box # are in the original image's scale. # The bounding box is computed to "frame" the face in accordance with human # expectations. It is based on the landmarker results. # Note that one or more x and/or y coordinates may not be generated in the # `BoundingPoly` (the polygon will be unbounded) if only a partial face # appears in the image to be annotated. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "rollAngle": 3.14, # Roll angle, which indicates the amount of clockwise/anti-clockwise rotation # of the face relative to the image vertical about the axis perpendicular to # the face. Range [-180,180]. "headwearLikelihood": "A String", # Headwear likelihood. "fdBoundingPoly": { # A bounding polygon for the detected image annotation. # The `fd_bounding_poly` bounding polygon is tighter than the # `boundingPoly`, and encloses only the skin part of the face. Typically, it # is used to eliminate the face from any image analysis that detects the # "amount of skin" visible in an image. It is not based on the # landmarker results, only on the initial face detection, hence # the <code>fd</code> (face detection) prefix. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, }, ], "productSearchResults": { # Results for a product search request. # If present, product search has completed successfully. "productGroupedResults": [ # List of results grouped by products detected in the query image. Each entry # corresponds to one bounding polygon in the query image, and contains the # matching products specific to that region. There may be duplicate product # matches in the union of all the per-product results. { # Information about the products similar to a single product in a query # image. "objectAnnotations": [ # List of generic predictions for the object in the bounding box. { # Prediction for what the object in the bounding box is. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "score": 3.14, # Score of the result. Range [0, 1]. "mid": "A String", # Object ID that should align with EntityAnnotation mid. "name": "A String", # Object name, expressed in its `language_code` language. }, ], "results": [ # List of results, one for each product match. { # Information about a product. "image": "A String", # The resource name of the image from the product that is the closest match # to the query. "score": 3.14, # A confidence level on the match, ranging from 0 (no confidence) to # 1 (full confidence). "product": { # A Product contains ReferenceImages. # The Product. "productLabels": [ # Key-value pairs that can be attached to a product. At query time, # constraints can be specified based on the product_labels. # # Note that integer values can be provided as strings, e.g. "1199". Only # strings with integer values can match a range-based restriction which is # to be supported soon. # # Multiple values can be assigned to the same key. One product may have up to # 500 product_labels. # # Notice that the total number of distinct product_labels over all products # in one ProductSet cannot exceed 1M, otherwise the product search pipeline # will refuse to work for that ProductSet. { # A product label represented as a key-value pair. "value": "A String", # The value of the label attached to the product. Cannot be empty and # cannot exceed 128 bytes. "key": "A String", # The key of the label attached to the product. Cannot be empty and cannot # exceed 128 bytes. }, ], "displayName": "A String", # The user-provided name for this Product. Must not be empty. Must be at most # 4096 characters long. "description": "A String", # User-provided metadata to be stored with this product. Must be at most 4096 # characters long. "productCategory": "A String", # Immutable. The category for the product identified by the reference image. This should # be either "homegoods-v2", "apparel-v2", or "toys-v2". The legacy categories # "homegoods", "apparel", and "toys" are still supported, but these should # not be used for new products. "name": "A String", # The resource name of the product. # # Format is: # `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`. # # This field is ignored when creating a product. }, }, ], "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon around the product detected in the query image. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, }, ], "results": [ # List of results, one for each product match. { # Information about a product. "image": "A String", # The resource name of the image from the product that is the closest match # to the query. "score": 3.14, # A confidence level on the match, ranging from 0 (no confidence) to # 1 (full confidence). "product": { # A Product contains ReferenceImages. # The Product. "productLabels": [ # Key-value pairs that can be attached to a product. At query time, # constraints can be specified based on the product_labels. # # Note that integer values can be provided as strings, e.g. "1199". Only # strings with integer values can match a range-based restriction which is # to be supported soon. # # Multiple values can be assigned to the same key. One product may have up to # 500 product_labels. # # Notice that the total number of distinct product_labels over all products # in one ProductSet cannot exceed 1M, otherwise the product search pipeline # will refuse to work for that ProductSet. { # A product label represented as a key-value pair. "value": "A String", # The value of the label attached to the product. Cannot be empty and # cannot exceed 128 bytes. "key": "A String", # The key of the label attached to the product. Cannot be empty and cannot # exceed 128 bytes. }, ], "displayName": "A String", # The user-provided name for this Product. Must not be empty. Must be at most # 4096 characters long. "description": "A String", # User-provided metadata to be stored with this product. Must be at most 4096 # characters long. "productCategory": "A String", # Immutable. The category for the product identified by the reference image. This should # be either "homegoods-v2", "apparel-v2", or "toys-v2". The legacy categories # "homegoods", "apparel", and "toys" are still supported, but these should # not be used for new products. "name": "A String", # The resource name of the product. # # Format is: # `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`. # # This field is ignored when creating a product. }, }, ], "indexTime": "A String", # Timestamp of the index which provided these results. Products added to the # product set and products removed from the product set after this time are # not reflected in the current results. }, "logoAnnotations": [ # If present, logo detection has completed successfully. { # Set of detected entity features. "confidence": 3.14, # **Deprecated. Use `score` instead.** # The accuracy of the entity detection in an image. # For example, for an image in which the "Eiffel Tower" entity is detected, # this field represents the confidence that there is a tower in the query # image. Range [0, 1]. "description": "A String", # Entity textual description, expressed in its `locale` language. "locale": "A String", # The language code for the locale in which the entity textual # `description` is expressed. "topicality": 3.14, # The relevancy of the ICA (Image Content Annotation) label to the # image. For example, the relevancy of "tower" is likely higher to an image # containing the detected "Eiffel Tower" than to an image containing a # detected distant towering building, even though the confidence that # there is a tower in each image may be the same. Range [0, 1]. "locations": [ # The location information for the detected entity. Multiple # `LocationInfo` elements can be present because one location may # indicate the location of the scene in the image, and another location # may indicate the location of the place where the image was taken. # Location information is usually present for landmarks. { # Detected entity location information. "latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, }, ], "mid": "A String", # Opaque entity ID. Some IDs may be available in # [Google Knowledge Graph Search # API](https://developers.google.com/knowledge-graph/). "score": 3.14, # Overall score of the result. Range [0, 1]. "boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Not produced # for `LABEL_DETECTION` features. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "properties": [ # Some entities may have optional user-supplied `Property` (name/value) # fields, such a score or string that qualifies the entity. { # A `Property` consists of a user-supplied name/value pair. "uint64Value": "A String", # Value of numeric properties. "name": "A String", # Name of the property. "value": "A String", # Value of the property. }, ], }, ], "landmarkAnnotations": [ # If present, landmark detection has completed successfully. { # Set of detected entity features. "confidence": 3.14, # **Deprecated. Use `score` instead.** # The accuracy of the entity detection in an image. # For example, for an image in which the "Eiffel Tower" entity is detected, # this field represents the confidence that there is a tower in the query # image. Range [0, 1]. "description": "A String", # Entity textual description, expressed in its `locale` language. "locale": "A String", # The language code for the locale in which the entity textual # `description` is expressed. "topicality": 3.14, # The relevancy of the ICA (Image Content Annotation) label to the # image. For example, the relevancy of "tower" is likely higher to an image # containing the detected "Eiffel Tower" than to an image containing a # detected distant towering building, even though the confidence that # there is a tower in each image may be the same. Range [0, 1]. "locations": [ # The location information for the detected entity. Multiple # `LocationInfo` elements can be present because one location may # indicate the location of the scene in the image, and another location # may indicate the location of the place where the image was taken. # Location information is usually present for landmarks. { # Detected entity location information. "latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, }, ], "mid": "A String", # Opaque entity ID. Some IDs may be available in # [Google Knowledge Graph Search # API](https://developers.google.com/knowledge-graph/). "score": 3.14, # Overall score of the result. Range [0, 1]. "boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Not produced # for `LABEL_DETECTION` features. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "properties": [ # Some entities may have optional user-supplied `Property` (name/value) # fields, such a score or string that qualifies the entity. { # A `Property` consists of a user-supplied name/value pair. "uint64Value": "A String", # Value of numeric properties. "name": "A String", # Name of the property. "value": "A String", # Value of the property. }, ], }, ], "context": { # If an image was produced from a file (e.g. a PDF), this message gives # If present, contextual information is needed to understand where this image # comes from. # information about the source of that image. "pageNumber": 42, # If the file was a PDF or TIFF, this field gives the page number within # the file used to produce the image. "uri": "A String", # The URI of the file used to produce the image. }, "fullTextAnnotation": { # TextAnnotation contains a structured representation of OCR extracted text. # If present, text (OCR) detection or document (OCR) text detection has # completed successfully. # This annotation provides the structural hierarchy for the OCR detected # text. # The hierarchy of an OCR extracted text structure is like this: # TextAnnotation -> Page -> Block -> Paragraph -> Word -> Symbol # Each structural component, starting from Page, may further have their own # properties. Properties describe detected languages, breaks etc.. Please refer # to the TextAnnotation.TextProperty message definition below for more # detail. "text": "A String", # UTF-8 text detected on the pages. "pages": [ # List of pages detected by OCR. { # Detected page from OCR. "width": 42, # Page width. For PDFs the unit is points. For images (including # TIFFs) the unit is pixels. "confidence": 3.14, # Confidence of the OCR results on the page. Range [0, 1]. "property": { # Additional information detected on the structural component. # Additional information detected on the page. "detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment. "isPrefix": True or False, # True if break prepends the element. "type": "A String", # Detected break type. }, "detectedLanguages": [ # A list of detected languages together with confidence. { # Detected language for a structural component. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "confidence": 3.14, # Confidence of detected language. Range [0, 1]. }, ], }, "blocks": [ # List of blocks of text, images etc on this page. { # Logical element on the page. "boundingBox": { # A bounding polygon for the detected image annotation. # The bounding box for the block. # The vertices are in the order of top-left, top-right, bottom-right, # bottom-left. When a rotation of the bounding box is detected the rotation # is represented as around the top-left corner as defined when the text is # read in the 'natural' orientation. # For example: # # * when the text is horizontal it might look like: # # 0----1 # | | # 3----2 # # * when it's rotated 180 degrees around the top-left corner it becomes: # # 2----3 # | | # 1----0 # # and the vertex order will still be (0, 1, 2, 3). "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "confidence": 3.14, # Confidence of the OCR results on the block. Range [0, 1]. "property": { # Additional information detected on the structural component. # Additional information detected for the block. "detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment. "isPrefix": True or False, # True if break prepends the element. "type": "A String", # Detected break type. }, "detectedLanguages": [ # A list of detected languages together with confidence. { # Detected language for a structural component. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "confidence": 3.14, # Confidence of detected language. Range [0, 1]. }, ], }, "blockType": "A String", # Detected block type (text, image etc) for this block. "paragraphs": [ # List of paragraphs in this block (if this blocks is of type text). { # Structural unit of text representing a number of words in certain order. "boundingBox": { # A bounding polygon for the detected image annotation. # The bounding box for the paragraph. # The vertices are in the order of top-left, top-right, bottom-right, # bottom-left. When a rotation of the bounding box is detected the rotation # is represented as around the top-left corner as defined when the text is # read in the 'natural' orientation. # For example: # * when the text is horizontal it might look like: # 0----1 # | | # 3----2 # * when it's rotated 180 degrees around the top-left corner it becomes: # 2----3 # | | # 1----0 # and the vertex order will still be (0, 1, 2, 3). "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "confidence": 3.14, # Confidence of the OCR results for the paragraph. Range [0, 1]. "property": { # Additional information detected on the structural component. # Additional information detected for the paragraph. "detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment. "isPrefix": True or False, # True if break prepends the element. "type": "A String", # Detected break type. }, "detectedLanguages": [ # A list of detected languages together with confidence. { # Detected language for a structural component. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "confidence": 3.14, # Confidence of detected language. Range [0, 1]. }, ], }, "words": [ # List of all words in this paragraph. { # A word representation. "boundingBox": { # A bounding polygon for the detected image annotation. # The bounding box for the word. # The vertices are in the order of top-left, top-right, bottom-right, # bottom-left. When a rotation of the bounding box is detected the rotation # is represented as around the top-left corner as defined when the text is # read in the 'natural' orientation. # For example: # * when the text is horizontal it might look like: # 0----1 # | | # 3----2 # * when it's rotated 180 degrees around the top-left corner it becomes: # 2----3 # | | # 1----0 # and the vertex order will still be (0, 1, 2, 3). "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "symbols": [ # List of symbols in the word. # The order of the symbols follows the natural reading order. { # A single symbol representation. "boundingBox": { # A bounding polygon for the detected image annotation. # The bounding box for the symbol. # The vertices are in the order of top-left, top-right, bottom-right, # bottom-left. When a rotation of the bounding box is detected the rotation # is represented as around the top-left corner as defined when the text is # read in the 'natural' orientation. # For example: # * when the text is horizontal it might look like: # 0----1 # | | # 3----2 # * when it's rotated 180 degrees around the top-left corner it becomes: # 2----3 # | | # 1----0 # and the vertex order will still be (0, 1, 2, 3). "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "text": "A String", # The actual UTF-8 representation of the symbol. "confidence": 3.14, # Confidence of the OCR results for the symbol. Range [0, 1]. "property": { # Additional information detected on the structural component. # Additional information detected for the symbol. "detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment. "isPrefix": True or False, # True if break prepends the element. "type": "A String", # Detected break type. }, "detectedLanguages": [ # A list of detected languages together with confidence. { # Detected language for a structural component. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "confidence": 3.14, # Confidence of detected language. Range [0, 1]. }, ], }, }, ], "confidence": 3.14, # Confidence of the OCR results for the word. Range [0, 1]. "property": { # Additional information detected on the structural component. # Additional information detected for the word. "detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment. "isPrefix": True or False, # True if break prepends the element. "type": "A String", # Detected break type. }, "detectedLanguages": [ # A list of detected languages together with confidence. { # Detected language for a structural component. "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more # information, see # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. "confidence": 3.14, # Confidence of detected language. Range [0, 1]. }, ], }, }, ], }, ], }, ], "height": 42, # Page height. For PDFs the unit is points. For images (including # TIFFs) the unit is pixels. }, ], }, "cropHintsAnnotation": { # Set of crop hints that are used to generate new crops when serving images. # If present, crop hints have completed successfully. "cropHints": [ # Crop hint results. { # Single crop hint that is used to generate a new crop when serving an image. "confidence": 3.14, # Confidence of this being a salient region. Range [0, 1]. "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the crop region. The coordinates of the bounding # box are in the original image's scale. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, "importanceFraction": 3.14, # Fraction of importance of this salient region with respect to the original # image. }, ], }, }, ], }
asyncBatchAnnotate(body=None, x__xgafv=None)
Run asynchronous image detection and annotation for a list of images. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `OperationMetadata` (metadata). `Operation.response` contains `AsyncBatchAnnotateImagesResponse` (results). This service will write image annotation outputs to json files in customer GCS bucket, each json file containing BatchAnnotateImagesResponse proto. Args: body: object, The request body. The object takes the form of: { # Request for async image annotation for a list of images. "outputConfig": { # The desired output location and metadata. # Required. The desired output location and metadata (e.g. format). "batchSize": 42, # The max number of response protos to put into each output JSON file on # Google Cloud Storage. # The valid range is [1, 100]. If not specified, the default value is 20. # # For example, for one pdf file with 100 pages, 100 response protos will # be generated. If `batch_size` = 20, then 5 json files each # containing 20 response protos will be written under the prefix # `gcs_destination`.`uri`. # # Currently, batch_size only applies to GcsDestination, with potential future # support for other output configurations. "gcsDestination": { # The Google Cloud Storage location where the output will be written to. # The Google Cloud Storage location to write the output(s) to. "uri": "A String", # Google Cloud Storage URI prefix where the results will be stored. Results # will be in JSON format and preceded by its corresponding input URI prefix. # This field can either represent a gcs file prefix or gcs directory. In # either case, the uri should be unique because in order to get all of the # output files, you will need to do a wildcard gcs search on the uri prefix # you provide. # # Examples: # # * File Prefix: gs://bucket-name/here/filenameprefix The output files # will be created in gs://bucket-name/here/ and the names of the # output files will begin with "filenameprefix". # # * Directory Prefix: gs://bucket-name/some/location/ The output files # will be created in gs://bucket-name/some/location/ and the names of the # output files could be anything because there was no filename prefix # specified. # # If multiple outputs, each response is still AnnotateFileResponse, each of # which contains some subset of the full list of AnnotateImageResponse. # Multiple outputs can happen if, for example, the output JSON is too large # and overflows into multiple sharded files. }, }, "requests": [ # Required. Individual image annotation requests for this batch. { # Request for performing Google Cloud Vision API tasks over a user-provided # image, with user-requested features, and with context information. "imageContext": { # Image context and/or feature-specific parameters. # Additional context that may accompany the image. "latLongRect": { # Rectangle determined by min and max `LatLng` pairs. # Not used. "minLatLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # Min lat/long pair. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, "maxLatLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # Max lat/long pair. # of doubles representing degrees latitude and degrees longitude. Unless # specified otherwise, this must conform to the # <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84 # standard</a>. Values must be within normalized ranges. "latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0]. "longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0]. }, }, "languageHints": [ # List of languages to use for TEXT_DETECTION. In most cases, an empty value # yields the best results since it enables automatic language detection. For # languages based on the Latin alphabet, setting `language_hints` is not # needed. In rare cases, when the language of the text in the image is known, # setting a hint will help get better results (although it will be a # significant hindrance if the hint is wrong). Text detection returns an # error if one or more of the specified languages is not one of the # [supported languages](/vision/docs/languages). "A String", ], "productSearchParams": { # Parameters for a product search request. # Parameters for product search. "productCategories": [ # The list of product categories to search in. Currently, we only consider # the first category, and either "homegoods-v2", "apparel-v2", "toys-v2", # "packagedgoods-v1", or "general-v1" should be specified. The legacy # categories "homegoods", "apparel", and "toys" are still supported but will # be deprecated. For new products, please use "homegoods-v2", "apparel-v2", # or "toys-v2" for better product search accuracy. It is recommended to # migrate existing products to these categories as well. "A String", ], "filter": "A String", # The filtering expression. This can be used to restrict search results based # on Product labels. We currently support an AND of OR of key-value # expressions, where each expression within an OR must have the same key. An # '=' should be used to connect the key and value. # # For example, "(color = red OR color = blue) AND brand = Google" is # acceptable, but "(color = red OR brand = Google)" is not acceptable. # "color: red" is not acceptable because it uses a ':' instead of an '='. "productSet": "A String", # The resource name of a ProductSet to be searched for similar images. # # Format is: # `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`. "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon around the area of interest in the image. # If it is not specified, system discretion will be applied. "normalizedVertices": [ # The bounding polygon normalized vertices. { # A vertex represents a 2D point in the image. # NOTE: the normalized vertex coordinates are relative to the original image # and range from 0 to 1. "y": 3.14, # Y coordinate. "x": 3.14, # X coordinate. }, ], "vertices": [ # The bounding polygon vertices. { # A vertex represents a 2D point in the image. # NOTE: the vertex coordinates are in the same scale as the original image. "y": 42, # Y coordinate. "x": 42, # X coordinate. }, ], }, }, "cropHintsParams": { # Parameters for crop hints annotation request. # Parameters for crop hints annotation request. "aspectRatios": [ # Aspect ratios in floats, representing the ratio of the width to the height # of the image. For example, if the desired aspect ratio is 4/3, the # corresponding float value should be 1.33333. If not specified, the # best possible crop is returned. The number of provided aspect ratios is # limited to a maximum of 16; any aspect ratios provided after the 16th are # ignored. 3.14, ], }, "webDetectionParams": { # Parameters for web detection request. # Parameters for web detection. "includeGeoResults": True or False, # Whether to include results derived from the geo information in the image. }, }, "image": { # Client image to perform Google Cloud Vision API tasks over. # The image to be processed. "content": "A String", # Image content, represented as a stream of bytes. # Note: As with all `bytes` fields, protobuffers use a pure binary # representation, whereas JSON representations use base64. "source": { # External image source (Google Cloud Storage or web URL image location). # Google Cloud Storage image location, or publicly-accessible image # URL. If both `content` and `source` are provided for an image, `content` # takes precedence and is used to perform the image annotation request. "gcsImageUri": "A String", # **Use `image_uri` instead.** # # The Google Cloud Storage URI of the form # `gs://bucket_name/object_name`. Object versioning is not supported. See # [Google Cloud Storage Request # URIs](https://cloud.google.com/storage/docs/reference-uris) for more info. "imageUri": "A String", # The URI of the source image. Can be either: # # 1. A Google Cloud Storage URI of the form # `gs://bucket_name/object_name`. Object versioning is not supported. See # [Google Cloud Storage Request # URIs](https://cloud.google.com/storage/docs/reference-uris) for more # info. # # 2. A publicly-accessible image HTTP/HTTPS URL. When fetching images from # HTTP/HTTPS URLs, Google cannot guarantee that the request will be # completed. Your request may fail if the specified host denies the # request (e.g. due to request throttling or DOS prevention), or if Google # throttles requests to the site for abuse prevention. You should not # depend on externally-hosted images for production applications. # # When both `gcs_image_uri` and `image_uri` are specified, `image_uri` takes # precedence. }, }, "features": [ # Requested features. { # The type of Google Cloud Vision API detection to perform, and the maximum # number of results to return for that type. Multiple `Feature` objects can # be specified in the `features` list. "model": "A String", # Model to use for the feature. # Supported values: "builtin/stable" (the default if unset) and # "builtin/latest". "type": "A String", # The feature type. "maxResults": 42, # Maximum number of results of this type. Does not apply to # `TEXT_DETECTION`, `DOCUMENT_TEXT_DETECTION`, or `CROP_HINTS`. }, ], }, ], "parent": "A String", # Optional. Target project and location to make a call. # # Format: `projects/{project-id}/locations/{location-id}`. # # If no parent is specified, a region will be chosen automatically. # # Supported location-ids: # `us`: USA country only, # `asia`: East asia areas, like Japan, Taiwan, # `eu`: The European Union. # # Example: `projects/project-A/locations/eu`. } x__xgafv: string, V1 error format. Allowed values 1 - v1 error format 2 - v2 error format Returns: An object of the form: { # This resource represents a long-running operation that is the result of a # network API call. "metadata": { # Service-specific metadata associated with the operation. It typically # contains progress information and common metadata such as create time. # Some services might not provide such metadata. Any method that returns a # long-running operation should document the metadata type, if any. "a_key": "", # Properties of the object. Contains field @type with type URL. }, "error": { # The `Status` type defines a logical error model that is suitable for # The error result of the operation in case of failure or cancellation. # different programming environments, including REST APIs and RPC APIs. It is # used by [gRPC](https://github.com/grpc). Each `Status` message contains # three pieces of data: error code, error message, and error details. # # You can find out more about this error model and how to work with it in the # [API Design Guide](https://cloud.google.com/apis/design/errors). "message": "A String", # A developer-facing error message, which should be in English. Any # user-facing error message should be localized and sent in the # google.rpc.Status.details field, or localized by the client. "code": 42, # The status code, which should be an enum value of google.rpc.Code. "details": [ # A list of messages that carry the error details. There is a common set of # message types for APIs to use. { "a_key": "", # Properties of the object. Contains field @type with type URL. }, ], }, "done": True or False, # If the value is `false`, it means the operation is still in progress. # If `true`, the operation is completed, and either `error` or `response` is # available. "response": { # The normal response of the operation in case of success. If the original # method returns no data on success, such as `Delete`, the response is # `google.protobuf.Empty`. If the original method is standard # `Get`/`Create`/`Update`, the response should be the resource. For other # methods, the response should have the type `XxxResponse`, where `Xxx` # is the original method name. For example, if the original method name # is `TakeSnapshot()`, the inferred response type is # `TakeSnapshotResponse`. "a_key": "", # Properties of the object. Contains field @type with type URL. }, "name": "A String", # The server-assigned name, which is only unique within the same service that # originally returns it. If you use the default HTTP mapping, the # `name` should be a resource name ending with `operations/{unique_id}`. }