基于Firebase平台开发（二） —— 基于ML Kit的iOS图片中文字的识别（二）

版本记录

版本号	时间
V1.0	2019.02.01 星期五

前言

Firebase是一家实时后端数据库创业公司，它能帮助开发者很快的写出Web端和移动端的应用。自2014年10月Google收购Firebase以来，用户可以在更方便地使用Firebase的同时，结合Google的云服务。Firebase能让你的App从零到一。也就是说它可以帮助手机以及网页应用的开发者轻松构建App。通过Firebase背后负载的框架就可以简单地开发一个App，无需服务器以及基础设施。接下来几篇我们就一起看一下基于Firebase平台的开发。感兴趣的看下面几篇文章。
1. 基于Firebase平台开发（一） —— 基于ML Kit的iOS图片中文字的识别（一）

源码

1. Swift

首先看下代码组织结构

看下sb中的内容

下面就是源码了

1. AppDelegate.swift

import UIKit
import Firebase

@UIApplicationMain
class AppDelegate: UIResponder, UIApplicationDelegate {
  var window: UIWindow?
  
  override init() {
    FirebaseApp.configure()
  }
}

2. ViewController.swift

import UIKit
import MobileCoreServices

class ViewController: UIViewController {
  @IBOutlet weak var imageView: UIImageView!
  @IBOutlet weak var textView: UITextView!
  @IBOutlet weak var cameraButton: UIButton!
  
  let processor = ScaledElementProcessor()
  var frameSublayer = CALayer()
  var scannedText: String = "Detected text can be edited here." {
    didSet {
      textView.text = scannedText
    }
  }
  
  override func viewDidLoad() {
    super.viewDidLoad()
    // Notifications to slide the keyboard up
    NotificationCenter.default.addObserver(self, selector: #selector(ViewController.keyboardWillShow), name: UIResponder.keyboardWillShowNotification, object: nil)
    NotificationCenter.default.addObserver(self, selector: #selector(ViewController.keyboardWillHide), name: UIResponder.keyboardWillHideNotification, object: nil)
    
    imageView.layer.addSublayer(frameSublayer)
    drawFeatures(in: imageView)
  }
    
  // MARK: Touch handling to dismiss keyboard
  override func touchesBegan(_ touches: Set<UITouch>, with event: UIEvent?) {
    if let evt = event, let tchs = evt.touches(for: view), tchs.count > 0 {
      textView.resignFirstResponder()
    }
  }
  
  // MARK: Actions
  @IBAction func cameraDidTouch(_ sender: UIButton) {
    if UIImagePickerController.isSourceTypeAvailable(.camera) {
      presentImagePickerController(withSourceType: .camera)
    } else {
      let alert = UIAlertController(title: "Camera Not Available", message: "A camera is not available. Please try picking an image from the image library instead.", preferredStyle: .alert)
      alert.addAction(UIAlertAction(title: "OK", style: .default, handler: nil))
      present(alert, animated: true, completion: nil)
    }
  }
  
  @IBAction func libraryDidTouch(_ sender: UIButton) {
    presentImagePickerController(withSourceType: .photoLibrary)
  }
  
  @IBAction func shareDidTouch(_ sender: UIBarButtonItem) {
    let vc = UIActivityViewController(activityItems: [scannedText, imageView.image!], applicationActivities: [])
    present(vc, animated: true, completion: nil)
  }
  
  // MARK: Keyboard slide up
  @objc func keyboardWillShow(notification: NSNotification) {
    if let keyboardSize = (notification.userInfo?[UIResponder.keyboardFrameBeginUserInfoKey] as? NSValue)?.cgRectValue {
      if view.frame.origin.y == 0 {
        view.frame.origin.y -= keyboardSize.height
      }
    }
  }
  
  @objc func keyboardWillHide(notification: NSNotification) {
    if let keyboardSize = (notification.userInfo?[UIResponder.keyboardFrameBeginUserInfoKey] as? NSValue)?.cgRectValue {
      if view.frame.origin.y != 0 {
        view.frame.origin.y += keyboardSize.height
      }
    }
  }
  
  private func removeFrames() {
    guard let sublayers = frameSublayer.sublayers else { return }
    for sublayer in sublayers {
      sublayer.removeFromSuperlayer()
    }
  }
  
  // 1
  private func drawFeatures(in imageView: UIImageView, completion: (() -> Void)? = nil) {
    removeFrames()
    processor.process(in: imageView) { text, elements in
      elements.forEach() { element in
        self.frameSublayer.addSublayer(element.shapeLayer)
      }
      self.scannedText = text
      completion?()
    }
  }
}

extension ViewController: UIImagePickerControllerDelegate, UINavigationControllerDelegate, UIPopoverPresentationControllerDelegate {
  // MARK: UIImagePickerController
  
  private func presentImagePickerController(withSourceType sourceType: UIImagePickerController.SourceType) {
    let controller = UIImagePickerController()
    controller.delegate = self
    controller.sourceType = sourceType
    controller.mediaTypes = [String(kUTTypeImage), String(kUTTypeMovie)]
    present(controller, animated: true, completion: nil)
  }
  
  // MARK: UIImagePickerController Delegate
  
  func imagePickerController(_ picker: UIImagePickerController, didFinishPickingMediaWithInfo info: [UIImagePickerController.InfoKey: Any]) {
    if let pickedImage =
      info[UIImagePickerController.InfoKey.originalImage] as? UIImage {
      
      imageView.contentMode = .scaleAspectFit
      let fixedImage = pickedImage.fixOrientation()
      imageView.image = fixedImage
      drawFeatures(in: imageView)
    }
    dismiss(animated: true, completion: nil)
  }
}

3. +UIImage.swift

import UIKit

extension UIImage {
  // Thx to: https://stackoverflow.com/questions/8915630/ios-uiimageview-how-to-handle-uiimage-image-orientation
  func fixOrientation() -> UIImage? {
    guard let cgImage = cgImage else {
      return nil
    }
    
    if imageOrientation == .up {
      return self
    }
    
    let width  = self.size.width
    let height = self.size.height
    
    var transform = CGAffineTransform.identity
    
    switch imageOrientation {
    case .down, .downMirrored:
      transform = transform.translatedBy(x: width, y: height)
      transform = transform.rotated(by: CGFloat.pi)
    case .left, .leftMirrored:
      transform = transform.translatedBy(x: width, y: 0)
      transform = transform.rotated(by: 0.5*CGFloat.pi)
    case .right, .rightMirrored:
      transform = transform.translatedBy(x: 0, y: height)
      transform = transform.rotated(by: -0.5*CGFloat.pi)
    case .up, .upMirrored:
      break
    }
    
    // Now we draw the underlying CGImage into a new context, applying the transform
    // calculated above.
    guard let colorSpace = cgImage.colorSpace else {
      return nil
    }
    
    guard let context = CGContext(
      data: nil,
      width: Int(width),
      height: Int(height),
      bitsPerComponent: cgImage.bitsPerComponent,
      bytesPerRow: 0,
      space: colorSpace,
      bitmapInfo: UInt32(cgImage.bitmapInfo.rawValue)
      ) else {
        return nil
    }
    
    context.concatenate(transform);
    
    switch imageOrientation {
    case .left, .leftMirrored, .right, .rightMirrored:
      // Grr...
      context.draw(cgImage, in: CGRect(x: 0, y: 0, width: height, height: width))
    default:
      context.draw(cgImage, in: CGRect(x: 0, y: 0, width: width, height: height))
    }
    
    // And now we just create a new UIImage from the drawing context
    guard let newCGImg = context.makeImage() else {
      return nil
    }
    
    let img = UIImage(cgImage: newCGImg)
    
    return img;
  }
}

4. ScaledElementProcessor.swift

import Firebase

struct ScaledElement {
  let frame: CGRect
  let shapeLayer: CALayer
}

class ScaledElementProcessor {
    let vision = Vision.vision()
    var textRecognizer: VisionTextRecognizer!
    
    init() {
        textRecognizer = vision.onDeviceTextRecognizer()
    }

  func process(in imageView: UIImageView, callback: @escaping (_ text: String, _ scaledElements: [ScaledElement]) -> Void) {
    guard let image = imageView.image else { return }
    let visionImage = VisionImage(image: image)
    
    textRecognizer.process(visionImage) { result, error in
      guard error == nil, let result = result, !result.text.isEmpty else {
        callback("", [])
        return
      }
      
      var scaledElements: [ScaledElement] = []
      for block in result.blocks {
        for line in block.lines {
          for element in line.elements {
            let frame = self.createScaledFrame(featureFrame: element.frame, imageSize: image.size, viewFrame: imageView.frame)
            
            let shapeLayer = self.createShapeLayer(frame: frame)
            let scaledElement = ScaledElement(frame: frame, shapeLayer: shapeLayer)
            scaledElements.append(scaledElement)
          }
        }
      }
      
      callback(result.text, scaledElements)
    }
  }

  private func createShapeLayer(frame: CGRect) -> CAShapeLayer {
    let bpath = UIBezierPath(rect: frame)
    let shapeLayer = CAShapeLayer()
    shapeLayer.path = bpath.cgPath
    shapeLayer.strokeColor = Constants.lineColor
    shapeLayer.fillColor = Constants.fillColor
    shapeLayer.lineWidth = Constants.lineWidth
    return shapeLayer
  }
  
  private func createScaledFrame(featureFrame: CGRect, imageSize: CGSize, viewFrame: CGRect) -> CGRect {
    let viewSize = viewFrame.size
    
    let resolutionView = viewSize.width / viewSize.height
    let resolutionImage = imageSize.width / imageSize.height
    
    var scale: CGFloat
    if resolutionView > resolutionImage {
      scale = viewSize.height / imageSize.height
    } else {
      scale = viewSize.width / imageSize.width
    }
    
    let featureWidthScaled = featureFrame.size.width * scale
    let featureHeightScaled = featureFrame.size.height * scale
    
    let imageWidthScaled = imageSize.width * scale
    let imageHeightScaled = imageSize.height * scale
    let imagePointXScaled = (viewSize.width - imageWidthScaled) / 2
    let imagePointYScaled = (viewSize.height - imageHeightScaled) / 2
    
    let featurePointXScaled = imagePointXScaled + featureFrame.origin.x * scale
    let featurePointYScaled = imagePointYScaled + featureFrame.origin.y * scale
    
    return CGRect(x: featurePointXScaled, y: featurePointYScaled, width: featureWidthScaled, height: featureHeightScaled)
  }

  // MARK: - private
  
  private enum Constants {
    static let lineWidth: CGFloat = 3.0
    static let lineColor = UIColor.yellow.cgColor
    static let fillColor = UIColor.clear.cgColor
  }
}

后记

本篇主要讲述了基于ML Kit的iOS图片中文字的识别，感兴趣的给个赞或者关注~~~