利用机器学习套件的数字墨水识别功能,您可以识别在数以百计的数码表面手写的文字,以及对草图进行分类。
试试看
- 玩转示例应用,查看此 API 的用法示例。
准备工作
在 Podfile 中添加以下机器学习套件库:
pod 'GoogleMLKit/DigitalInkRecognition', '3.2.0'
安装或更新项目的 Pod 之后,请使用 Xcode 项目的
.xcworkspace
来打开项目。Xcode 版本 13.2.1 或更高版本支持机器学习套件。
您现在可以开始识别 Ink
对象中的文本。
构建 Ink
对象
构建 Ink
对象的主要方法是在触摸屏上绘制它。在 iOS 上,您可以使用 UIImageView 和触摸事件处理脚本来绘制屏幕上的描边,并存储描边的点以构建 Ink
对象。以下代码段对此常规模式进行了演示。请参阅快速入门应用,了解将触摸事件处理、屏幕绘制和描边数据管理分开的更完整示例。
Swift
@IBOutlet weak var mainImageView: UIImageView! var kMillisecondsPerTimeInterval = 1000.0 var lastPoint = CGPoint.zero private var strokes: [Stroke] = [] private var points: [StrokePoint] = [] func drawLine(from fromPoint: CGPoint, to toPoint: CGPoint) { UIGraphicsBeginImageContext(view.frame.size) guard let context = UIGraphicsGetCurrentContext() else { return } mainImageView.image?.draw(in: view.bounds) context.move(to: fromPoint) context.addLine(to: toPoint) context.setLineCap(.round) context.setBlendMode(.normal) context.setLineWidth(10.0) context.setStrokeColor(UIColor.white.cgColor) context.strokePath() mainImageView.image = UIGraphicsGetImageFromCurrentImageContext() mainImageView.alpha = 1.0 UIGraphicsEndImageContext() } override func touchesBegan(_ touches: Set, with event: UIEvent?) { guard let touch = touches.first else { return } lastPoint = touch.location(in: mainImageView) let t = touch.timestamp points = [StrokePoint.init(x: Float(lastPoint.x), y: Float(lastPoint.y), t: Int(t * kMillisecondsPerTimeInterval))] drawLine(from:lastPoint, to:lastPoint) } override func touchesMoved(_ touches: Set , with event: UIEvent?) { guard let touch = touches.first else { return } let currentPoint = touch.location(in: mainImageView) let t = touch.timestamp points.append(StrokePoint.init(x: Float(currentPoint.x), y: Float(currentPoint.y), t: Int(t * kMillisecondsPerTimeInterval))) drawLine(from: lastPoint, to: currentPoint) lastPoint = currentPoint } override func touchesEnded(_ touches: Set , with event: UIEvent?) { guard let touch = touches.first else { return } let currentPoint = touch.location(in: mainImageView) let t = touch.timestamp points.append(StrokePoint.init(x: Float(currentPoint.x), y: Float(currentPoint.y), t: Int(t * kMillisecondsPerTimeInterval))) drawLine(from: lastPoint, to: currentPoint) lastPoint = currentPoint strokes.append(Stroke.init(points: points)) self.points = [] doRecognition() }
Objective-C
// Interface @property (weak, nonatomic) IBOutlet UIImageView *mainImageView; @property(nonatomic) CGPoint lastPoint; @property(nonatomic) NSMutableArray*strokes; @property(nonatomic) NSMutableArray *points; // Implementations static const double kMillisecondsPerTimeInterval = 1000.0; - (void)drawLineFrom:(CGPoint)fromPoint to:(CGPoint)toPoint { UIGraphicsBeginImageContext(self.mainImageView.frame.size); [self.mainImageView.image drawInRect:CGRectMake(0, 0, self.mainImageView.frame.size.width, self.mainImageView.frame.size.height)]; CGContextMoveToPoint(UIGraphicsGetCurrentContext(), fromPoint.x, fromPoint.y); CGContextAddLineToPoint(UIGraphicsGetCurrentContext(), toPoint.x, toPoint.y); CGContextSetLineCap(UIGraphicsGetCurrentContext(), kCGLineCapRound); CGContextSetLineWidth(UIGraphicsGetCurrentContext(), 10.0); CGContextSetRGBStrokeColor(UIGraphicsGetCurrentContext(), 1, 1, 1, 1); CGContextSetBlendMode(UIGraphicsGetCurrentContext(), kCGBlendModeNormal); CGContextStrokePath(UIGraphicsGetCurrentContext()); CGContextFlush(UIGraphicsGetCurrentContext()); self.mainImageView.image = UIGraphicsGetImageFromCurrentImageContext(); UIGraphicsEndImageContext(); } - (void)touchesBegan:(NSSet *)touches withEvent:(nullable UIEvent *)event { UITouch *touch = [touches anyObject]; self.lastPoint = [touch locationInView:self.mainImageView]; NSTimeInterval time = [touch timestamp]; self.points = [NSMutableArray array]; [self.points addObject:[[MLKStrokePoint alloc] initWithX:self.lastPoint.x y:self.lastPoint.y t:time * kMillisecondsPerTimeInterval]]; [self drawLineFrom:self.lastPoint to:self.lastPoint]; } - (void)touchesMoved:(NSSet *)touches withEvent:(nullable UIEvent *)event { UITouch *touch = [touches anyObject]; CGPoint currentPoint = [touch locationInView:self.mainImageView]; NSTimeInterval time = [touch timestamp]; [self.points addObject:[[MLKStrokePoint alloc] initWithX:currentPoint.x y:currentPoint.y t:time * kMillisecondsPerTimeInterval]]; [self drawLineFrom:self.lastPoint to:currentPoint]; self.lastPoint = currentPoint; } - (void)touchesEnded:(NSSet *)touches withEvent:(nullable UIEvent *)event { UITouch *touch = [touches anyObject]; CGPoint currentPoint = [touch locationInView:self.mainImageView]; NSTimeInterval time = [touch timestamp]; [self.points addObject:[[MLKStrokePoint alloc] initWithX:currentPoint.x y:currentPoint.y t:time * kMillisecondsPerTimeInterval]]; [self drawLineFrom:self.lastPoint to:currentPoint]; self.lastPoint = currentPoint; if (self.strokes == nil) { self.strokes = [NSMutableArray array]; } [self.strokes addObject:[[MLKStroke alloc] initWithPoints:self.points]]; self.points = nil; [self doRecognition]; }
请注意,该代码段包含一个将描边绘制到 UIImageView 中的示例函数,该函数应根据需要进行调整。我们建议您在绘制线段时使用圆环,这样就可以将零长度线段绘制为点(例如,将字母 {1} 视为点)。每次写入描边后都会调用 doRecognition()
函数,该函数定义如下。
获取 DigitalInkRecognizer
的实例
为了执行识别,我们需要将 Ink
对象传递给 DigitalInkRecognizer
实例。为了获取 DigitalInkRecognizer
实例,我们首先需要下载所需语言的识别器模型,然后将该模型加载到 RAM 中。为实现此目的,您可以使用以下代码段将其放置在 viewDidLoad()
方法中和使用硬编码语言名称。如需查看示例,了解如何向用户显示可用语言列表并下载所选语言,请参阅快速入门应用。
Swift
override func viewDidLoad() { super.viewDidLoad() let languageTag = "en-US" let identifier = DigitalInkRecognitionModelIdentifier(forLanguageTag: languageTag) if identifier == nil { // no model was found or the language tag couldn't be parsed, handle error. } let model = DigitalInkRecognitionModel.init(modelIdentifier: identifier!) let modelManager = ModelManager.modelManager() let conditions = ModelDownloadConditions.init(allowsCellularAccess: true, allowsBackgroundDownloading: true) modelManager.download(model, conditions: conditions) // Get a recognizer for the language let options: DigitalInkRecognizerOptions = DigitalInkRecognizerOptions.init(model: model) recognizer = DigitalInkRecognizer.digitalInkRecognizer(options: options) }
Objective-C
- (void)viewDidLoad { [super viewDidLoad]; NSString *languagetag = @"en-US"; MLKDigitalInkRecognitionModelIdentifier *identifier = [MLKDigitalInkRecognitionModelIdentifier modelIdentifierForLanguageTag:languagetag]; if (identifier == nil) { // no model was found or the language tag couldn't be parsed, handle error. } MLKDigitalInkRecognitionModel *model = [[MLKDigitalInkRecognitionModel alloc] initWithModelIdentifier:identifier]; MLKModelManager *modelManager = [MLKModelManager modelManager]; [modelManager downloadModel:model conditions:[[MLKModelDownloadConditions alloc] initWithAllowsCellularAccess:YES allowsBackgroundDownloading:YES]]; MLKDigitalInkRecognizerOptions *options = [[MLKDigitalInkRecognizerOptions alloc] initWithModel:model]; self.recognizer = [MLKDigitalInkRecognizer digitalInkRecognizerWithOptions:options]; }
快速入门应用包含额外的代码,展示了如何同时处理多项下载,以及如何通过处理完成通知来确定下载是否成功。
识别 Ink
对象
接下来是 doRecognition()
函数,为简单起见,从 touchesEnded()
调用该函数。在其他应用中,可能希望在超时后或用户按下按钮触发识别时调用识别。
Swift
func doRecognition() { let ink = Ink.init(strokes: strokes) recognizer.recognize( ink: ink, completion: { [unowned self] (result: DigitalInkRecognitionResult?, error: Error?) in var alertTitle = "" var alertText = "" if let result = result, let candidate = result.candidates.first { alertTitle = "I recognized this:" alertText = candidate.text } else { alertTitle = "I hit an error:" alertText = error!.localizedDescription } let alert = UIAlertController(title: alertTitle, message: alertText, preferredStyle: UIAlertController.Style.alert) alert.addAction(UIAlertAction(title: "OK", style: UIAlertAction.Style.default, handler: nil)) self.present(alert, animated: true, completion: nil) } ) }
Objective-C
- (void)doRecognition { MLKInk *ink = [[MLKInk alloc] initWithStrokes:self.strokes]; __weak typeof(self) weakSelf = self; [self.recognizer recognizeInk:ink completion:^(MLKDigitalInkRecognitionResult *_Nullable result, NSError *_Nullable error) { typeof(weakSelf) strongSelf = weakSelf; if (strongSelf == nil) { return; } NSString *alertTitle = nil; NSString *alertText = nil; if (result.candidates.count > 0) { alertTitle = @"I recognized this:"; alertText = result.candidates[0].text; } else { alertTitle = @"I hit an error:"; alertText = [error localizedDescription]; } UIAlertController *alert = [UIAlertController alertControllerWithTitle:alertTitle message:alertText preferredStyle:UIAlertControllerStyleAlert]; [alert addAction:[UIAlertAction actionWithTitle:@"OK" style:UIAlertActionStyleDefault handler:nil]]; [strongSelf presentViewController:alert animated:YES completion:nil]; }]; }
管理模型下载
我们已经介绍了如何下载识别模型。以下代码段说明了如何检查模型是否已下载,以及在不再需要模型时如何删除存储空间。
检查模型是否已下载
Swift
let model : DigitalInkRecognitionModel = ... let modelManager = ModelManager.modelManager() modelManager.isModelDownloaded(model)
Objective-C
MLKDigitalInkRecognitionModel *model = ...; MLKModelManager *modelManager = [MLKModelManager modelManager]; [modelManager isModelDownloaded:model];
删除已下载的模型
Swift
let model : DigitalInkRecognitionModel = ... let modelManager = ModelManager.modelManager() if modelManager.isModelDownloaded(model) { modelManager.deleteDownloadedModel( model!, completion: { error in if error != nil { // Handle error return } NSLog(@"Model deleted."); }) }
Objective-C
MLKDigitalInkRecognitionModel *model = ...; MLKModelManager *modelManager = [MLKModelManager modelManager]; if ([self.modelManager isModelDownloaded:model]) { [self.modelManager deleteDownloadedModel:model completion:^(NSError *_Nullable error) { if (error) { // Handle error. return; } NSLog(@"Model deleted."); }]; }
提高文字识别准确性的提示
文字识别的准确性可能因语言而异。准确性还取决于写作风格。虽然数字墨水识别训练经过训练,可以处理多种书写样式,但结果可能因用户而异。
下面是提高文本识别器准确性的一些方法。请注意,这些技巧不适用于表情符号、自动绘制和形状的绘图分类器。
书写区域
许多应用都有明确定义的用户输入区域。符号的含义在一定程度上取决于其大小(相对于包含该符号的写入区域的大小)。例如,大写字母或字母“o”或“c”之间的区别,以及英文逗号和正斜杠。
告知识别器手写区域的宽度和高度有助于提高准确性。不过,识别器会假定写入区域仅包含一行文本。如果物理写入区域足够大,允许用户写入两行或更多行,您可以传入 WriterArea 区域,此时该高度是您对单行文本的最佳估计值,从而可能会获得更好的结果。您传递给识别器的 WRITEArea 对象不必与屏幕上的物理写入区域完全一致。在某些语言中,以这种方式更改 WRITEArea 高度更适合使用某些语言。
指定写入区域时,请指定其宽度和高度(与描边坐标相同)。x,y 坐标参数没有单位要求 - API 会对所有单位进行归一化,因此唯一重要的是描边的相对大小和位置。您可以随意传入适合自己系统的任何缩放比例。
背景信息
上下文是您尝试识别的 Ink
中描边之前紧接着的文本。您可以通过识别前置上下文帮助识别器。
例如,手写字母“n”和“u”经常会被误解。如果用户已输入部分字词“arg”,则系统可能会继续使用可被识别为“ument”或“nment”的描边。指定前置上下文“arg”可解决模棱两可的问题,因为“argument”一词更有可能比“argnment”得到解决。
前置上下文还有助于识别器识别字词间的间隔,即字词之间的空格。您可以输入空格字符,但不能绘制空格,所以识别器如何确定一个字词的结束时间和下一个字词的开始时间?如果用户已经编写了“hello”并继续写了“world”,而没有前置上下文,识别器会返回字符串“world”。但是,如果您指定前置上下文“hello”,则模型将返回字符串“world”,并带有前导空格,因为“hello world”比“helloword”更有意义。
您应提供最长的预上下文字符串,最多 20 个字符(包括空格)。如果字符串较长,则识别器只能使用最后 20 个字符。
以下代码示例展示了如何定义写入区域并使用 RecognitionContext
对象指定前置上下文。
Swift
let ink: Ink = ...; let recognizer: DigitalInkRecognizer = ...; let preContext: String = ...; let writingArea = WritingArea.init(width: ..., height: ...); let context: DigitalInkRecognitionContext.init( preContext: preContext, writingArea: writingArea); recognizer.recognizeHandwriting( from: ink, context: context, completion: { (result: DigitalInkRecognitionResult?, error: Error?) in if let result = result, let candidate = result.candidates.first { NSLog("Recognized \(candidate.text)") } else { NSLog("Recognition error \(error)") } })
Objective-C
MLKInk *ink = ...; MLKDigitalInkRecognizer *recognizer = ...; NSString *preContext = ...; MLKWritingArea *writingArea = [MLKWritingArea initWithWidth:... height:...]; MLKDigitalInkRecognitionContext *context = [MLKDigitalInkRecognitionContext initWithPreContext:preContext writingArea:writingArea]; [recognizer recognizeHandwritingFromInk:ink context:context completion:^(MLKDigitalInkRecognitionResult *_Nullable result, NSError *_Nullable error) { NSLog(@"Recognition result %@", result.candidates[0].text); }];
描边排序
识别准确性与笔画的顺序密切相关。识别器预期中风的笔画按照自然顺序书写;例如,从左到右表示笔画。任何偏离此模式的情况(例如从最后一个单词开始编写英文句子)都会降低准确度。
另一个示例是移除 Ink
中间的一个单词并将其替换为另一个单词。修订版本可能位于句子的中间,但修订版本的描边位于笔画序列的末尾。
在这种情况下,我们建议您将新写入的字词单独发送到 API,并使用您自己的逻辑将结果与之前的识别值合并。
处理不明确形状
在某些情况下,提供给识别器的形状的含义不明确。例如,边缘非常圆角的矩形可以看作矩形或椭圆形。
这些不明的情况可通过识别识别值(如果有)进行处理。只有形状分类器提供得分。如果模型非常有信心,则排在最前面的结果的得分会远高于次优结果。如果不确定,前两个结果的分数将会接近。另请注意,形状分类器会将整个 Ink
解读为单个形状。例如,如果 Ink
包含一个矩形和一个相邻的椭圆形,则识别器可能会返回一个(或完全不同的一个),因为单个识别候选无法代表两个形状。