UIImages中的文本检测相关的类：
1) class VNDetectTextRectanglesRequest
NSLinguisticTagger解释的东西？Vision的帖子。这就是如何做到它的方式...
//
// ViewController.swift
//
import UIKit
import Vision
import CoreML
class ViewController: UIViewController {
//HOLDS OUR INPUT
var inputImage:CIImage?
//RESULT FROM OVERALL RECOGNITION
var recognizedWords:[String] = [String]()
//RESULT FROM RECOGNITION
var recognizedRegion:String = String()
//OCR-REQUEST
lazy var ocrRequest: VNCoreMLRequest = {
do {
//THIS MODEL IS TRAINED BY ME FOR FONT "Inconsolata" (Numbers 0...9 and UpperCase Characters A..Z)
let model = try VNCoreMLModel(for:OCR().model)
return VNCoreMLRequest(model: model, completionHandler: self.handleClassification)
} catch {
fatalError("cannot load model")
}
}()
//OCR-HANDLER
func handleClassification(request: VNRequest, error: Error?)
{
guard let observations = request.results as? [VNClassificationObservation]
else {fatalError("unexpected result") }
guard let best = observations.first
else { fatalError("cant get best result")}
self.recognizedRegion = self.recognizedRegion.appending(best.identifier)
}
//TEXT-DETECTION-REQUEST
lazy var textDetectionRequest: VNDetectTextRectanglesRequest = {
return VNDetectTextRectanglesRequest(completionHandler: self.handleDetection)
}()
//TEXT-DETECTION-HANDLER
func handleDetection(request:VNRequest, error: Error?)
{
guard let observations = request.results as? [VNTextObservation]
else {fatalError("unexpected result") }
// EMPTY THE RESULTS
self.recognizedWords = [String]()
//NEEDED BECAUSE OF DIFFERENT SCALES
let transform = CGAffineTransform.identity.scaledBy(x: (self.inputImage?.extent.size.width)!, y: (self.inputImage?.extent.size.height)!)
//A REGION IS LIKE A "WORD"
for region:VNTextObservation in observations
{
guard let boxesIn = region.characterBoxes else {
continue
}
//EMPTY THE RESULT FOR REGION
self.recognizedRegion = ""
//A "BOX" IS THE POSITION IN THE ORIGINAL IMAGE (SCALED FROM 0... 1.0)
for box in boxesIn
{
//SCALE THE BOUNDING BOX TO PIXELS
let realBoundingBox = box.boundingBox.applying(transform)
//TO BE SURE
guard (inputImage?.extent.contains(realBoundingBox))!
else { print("invalid detected rectangle"); return}
//SCALE THE POINTS TO PIXELS
let topleft = box.topLeft.applying(transform)
let topright = box.topRight.applying(transform)
let bottomleft = box.bottomLeft.applying(transform)
let bottomright = box.bottomRight.applying(transform)
//LET'S CROP AND RECTIFY
let charImage = inputImage?
.cropped(to: realBoundingBox)
.applyingFilter("CIPerspectiveCorrection", parameters: [
"inputTopLeft" : CIVector(cgPoint: topleft),
"inputTopRight" : CIVector(cgPoint: topright),
"inputBottomLeft" : CIVector(cgPoint: bottomleft),
"inputBottomRight" : CIVector(cgPoint: bottomright)
])
//PREPARE THE HANDLER
let handler = VNImageRequestHandler(ciImage: charImage!, options: [:])
//SOME OPTIONS (TO PLAY WITH..)
self.ocrRequest.imageCropAndScaleOption = VNImageCropAndScaleOption.scaleFill
//FEED THE CHAR-IMAGE TO OUR OCR-REQUEST - NO NEED TO SCALE IT - VISION WILL DO IT FOR US !!
do {
try handler.perform([self.ocrRequest])
} catch { print("Error")}
}
//APPEND RECOGNIZED CHARS FOR THAT REGION
self.recognizedWords.append(recognizedRegion)
}
//THATS WHAT WE WANT - PRINT WORDS TO CONSOLE
DispatchQueue.main.async {
self.PrintWords(words: self.recognizedWords)
}
}
func PrintWords(words:[String])
{
// VOILA'
print(recognizedWords)
}
func doOCR(ciImage:CIImage)
{
//PREPARE THE HANDLER
let handler = VNImageRequestHandler(ciImage: ciImage, options:[:])
//WE NEED A BOX FOR EACH DETECTED CHARACTER
self.textDetectionRequest.reportCharacterBoxes = true
self.textDetectionRequest.preferBackgroundProcessing = false
//FEED IT TO THE QUEUE FOR TEXT-DETECTION
DispatchQueue.global(qos: .userInteractive).async {
do {
try handler.perform([self.textDetectionRequest])
} catch {
print ("Error")
}
}
}
override func viewDidLoad() {
super.viewDidLoad()
// Do any additional setup after loading the view, typically from a nib.
//LETS LOAD AN IMAGE FROM RESOURCE
let loadedImage:UIImage = UIImage(named: "Sample1.png")! //TRY Sample2, Sample3 too
//WE NEED A CIIMAGE - NOT NEEDED TO SCALE
inputImage = CIImage(image:loadedImage)!
//LET'S DO IT
self.doOCR(ciImage: inputImage!)
}
override func didReceiveMemoryWarning() {
super.didReceiveMemoryWarning()
// Dispose of any resources that can be recreated.
}
}
你可以在这里找到完整的项目，其中包括已训练好的模型！
苹果公司最终更新了Vision来进行OCR。打开playground并将一些测试图片放入Resources文件夹中。在我的例子中，我称它们为“demoDocument.jpg”和“demoLicensePlate.jpg”。
新的类名为VNRecognizeTextRequest。将其放入playground并试一下：
import Vision
enum DemoImage: String {
case document = "demoDocument"
case licensePlate = "demoLicensePlate"
}
class OCRReader {
func performOCR(on url: URL?, recognitionLevel: VNRequestTextRecognitionLevel) {
guard let url = url else { return }
let requestHandler = VNImageRequestHandler(url: url, options: [:])
let request = VNRecognizeTextRequest { (request, error) in
if let error = error {
print(error)
return
}
guard let observations = request.results as? [VNRecognizedTextObservation] else { return }
for currentObservation in observations {
let topCandidate = currentObservation.topCandidates(1)
if let recognizedText = topCandidate.first {
print(recognizedText.string)
}
}
}
request.recognitionLevel = recognitionLevel
try? requestHandler.perform([request])
}
}
func url(for image: DemoImage) -> URL? {
return Bundle.main.url(forResource: image.rawValue, withExtension: "jpg")
}
let ocrReader = OCRReader()
ocrReader.performOCR(on: url(for: .document), recognitionLevel: .fast)
这里有一个来自WWDC19的深入讨论
SwiftOCR
我刚刚成功地使用SwiftOCR处理了小型文本集。
https://github.com/garnele007/SwiftOCR
使用了Swift-AI的NeuralNet-MNIST模型进行文本识别。
待做事项：VNTextObservation > SwiftOCR
一旦我把它链接到另一个方面，我会发布一个示例，演示它如何使用VNTextObservation。
OpenCV + Tesseract OCR
我试图使用OpenCV + Tesseract，但是出现了编译错误，后来发现了SwiftOCR。
另请参阅：Google Vision iOS
请注意，Google Vision Text Recognition-Android SDK具有文本检测功能，但也有iOS Cocoapod版本。因此，请保持关注，因为它最终应该会添加文本识别功能到iOS中。
https://developers.google.com/vision/text-overview
//更正：我刚刚尝试过它，但只有Android版本的SDK支持文本检测。
https://developers.google.com/vision/text-overview
如果您订阅了发布版本，点击“SUBSCRIBE TO RELEASES”，您可以看到什么时候将文本检测添加到Cocoapod的iOS部分。
补充一下我的进展，如果有更好的解决方案，请告诉我：
我已经成功地在屏幕上绘制出区域框和字符框。苹果的视觉 API 实际上非常高效。您需要将视频的每一帧转换为图像，并将其提供给识别器。这比直接从相机馈送像素缓冲区要准确得多。
if #available(iOS 11.0, *) {
guard let pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else {return}
var requestOptions:[VNImageOption : Any] = [:]
if let camData = CMGetAttachment(sampleBuffer, kCMSampleBufferAttachmentKey_CameraIntrinsicMatrix, nil) {
requestOptions = [.cameraIntrinsics:camData]
}
let imageRequestHandler = VNImageRequestHandler(cvPixelBuffer: pixelBuffer,
orientation: 6,
options: requestOptions)
let request = VNDetectTextRectanglesRequest(completionHandler: { (request, _) in
guard let observations = request.results else {print("no result"); return}
let result = observations.map({$0 as? VNTextObservation})
DispatchQueue.main.async {
self.previewLayer.sublayers?.removeSubrange(1...)
for region in result {
guard let rg = region else {continue}
self.drawRegionBox(box: rg)
if let boxes = region?.characterBoxes {
for characterBox in boxes {
self.drawTextBox(box: characterBox)
}
}
}
}
})
request.reportCharacterBoxes = true
try? imageRequestHandler.perform([request])
}
}
现在我正在尝试识别文本。苹果没有提供任何内置的OCR模型。我想使用CoreML来实现这一点，所以我正在尝试将Tesseract训练数据模型转换为CoreML。
您可以在此处找到Tesseract模型：https://github.com/tesseract-ocr/tessdata，我认为下一步是编写一个支持这些类型输入并输出.coreML文件的coremltools转换器。
或者，您可以直接链接到TesseractiOS，并尝试使用从Vision API获取的区域框和字符框进行输入。
- (void)detectWithImageURL:(NSURL *)URL
{
VNImageRequestHandler *handler = [[VNImageRequestHandler alloc] initWithURL:URL options:@{}];
VNDetectTextRectanglesRequest *request = [[VNDetectTextRectanglesRequest alloc] initWithCompletionHandler:^(VNRequest * _Nonnull request, NSError * _Nullable error) {
if (error) {
NSLog(@"%@", error);
}
else {
for (VNTextObservation *textObservation in request.results) {
// NSLog(@"%@", textObservation);
// NSLog(@"%@", textObservation.characterBoxes);
NSLog(@"%@", NSStringFromCGRect(textObservation.boundingBox));
for (VNRectangleObservation *rectangleObservation in textObservation.characterBoxes) {
NSLog(@" |-%@", NSStringFromCGRect(rectangleObservation.boundingBox));
}
}
}
}];
request.reportCharacterBoxes = YES;
NSError *error;
[handler performRequests:@[request] error:&error];
if (error) {
NSLog(@"%@", error);
}
}
对于那些仍在寻找解决方案的人，我写了一个快速的库来完成这个任务。它同时使用了Vision API和Tesseract，并可以用一个方法实现问题所描述的任务。
func sliceaAndOCR(image: UIImage, charWhitelist: String, charBlackList: String = "", completion: @escaping ((_: String, _: UIImage) -> Void))
这个方法会在你的图片中查找文本，返回被发现的字符串和一个原始图片的切片，显示出文本被发现的位置。