N|Solid N|Solid N|Solid

Vision was introduced in 2017 WWDC along with list of other machine learning frameworks apple released (Core ML,NLP).Vision can be used on both image as well as sequences of image (videos).We can also integrate vision with Core ML Models for example it can used to give Core ML required input parameters example for MINST image classification we can detect numbers as rect in image using vision and send it Core ML model for prediction. Check the WWDC Video

• Face Detection and Recognition
• Machine Learning Image Analysis
• Barcode Detection
• Image Alignment Analysis
• Text Detection
• Horizon Detection
• Object Detection and Tracking

In this project we are gonna look into simple image analysis techniques like marking Rectangle objects,faces ,text boxes,Char on texts

For performing any image analysis operation we need follow this three step process

• Create a Vision Image Request

• Create a Image Request Handler

• Assigning Image Requests To Request handler

N|Solid N|Solid

• Creating face detection request

 lazy var faceDetectionRequest : VNDetectFaceRectanglesRequest = {
 let faceRequest = VNDetectFaceRectanglesRequest(completionHandler:self.handleFaceDetection)
 return faceRequest
 }()

• Create a image request handler

 let handler = VNImageRequestHandler(ciImage: ciImage, orientation: Int32(uiImage.imageOrientation.rawValue))

• Assigning image requests to request handler

 try handler.perform([self.faceDetectionRequest])

• Handler code

 func handleFaceDetection (request: VNRequest, error: Error?) {
 guard let observations = request.results as? [VNFaceObservation]
 else { print("unexpected result type from VNFaceObservation")
 return }
 guard observations.first != nil else {
 return
 }
 // Show the pre-processed image
 DispatchQueue.main.async {
 self.analyzedImageView.subviews.forEach({ (s) in
 s.removeFromSuperview()
 })
 for face in observations
 {
 let view = self.CreateBoxView(withColor: UIColor.red)
 view.frame = self.transformRect(fromRect: face.boundingBox, toViewRect: self.analyzedImageView)
 self.analyzedImageView.image = self.originalImageView.image
 self.analyzedImageView.addSubview(view)
 self.loadingLbl.isHidden = true
 
 }
 }
 }

• Converting vision rect to uikit rect

  one main thing to keep in mind that vision rect values are different from others

  Vision: origin ---> bottom left

  Size ---> Max value of 1

  UIkit : origin ---> top left

  Size ---> UIVIEW bounds

   //Convert Vision Frame to UIKit Frame
   func transformRect(fromRect: CGRect , toViewRect :UIView) -> CGRect {
   
   var toRect = CGRect()
   toRect.size.width = fromRect.size.width * toViewRect.frame.size.width
   toRect.size.height = fromRect.size.height * toViewRect.frame.size.height
   toRect.origin.y = (toViewRect.frame.height) - (toViewRect.frame.height * fromRect.origin.y )
   toRect.origin.y = toRect.origin.y - toRect.size.height
   toRect.origin.x = fromRect.origin.x * toViewRect.frame.size.width
   
   return toRect
   }
   

• Box view

For drawing rectangle box around our detection

 func CreateBoxView(withColor : UIColor) -> UIView {
 let view = UIView()
 view.layer.borderColor = withColor.cgColor
 view.layer.borderWidth = 2
 view.backgroundColor = UIColor.clear
 return view
 }

N|Solid N|Solid

• Creating char detection request

   lazy var textRectangleRequest: VNDetectTextRectanglesRequest = {
   let textRequest = VNDetectTextRectanglesRequest(completionHandler: self.handleTextIdentifiaction)
   textRequest.reportCharacterBoxes = true
   return textRequest
   }()

• Create a image request handler

   let handler = VNImageRequestHandler(ciImage: ciImage, orientation: Int32(uiImage.imageOrientation.rawValue))

• Assigning image requests to request handler

   try handler.perform([self.textRectangleRequest])

• Handler code

   func handleTextIdentifiaction (request: VNRequest, error: Error?) {
   
   guard let observations = request.results as? [VNTextObservation]
   else { print("unexpected result type from VNTextObservation")
   return
   }
   guard observations.first != nil else {
   return
   }
   DispatchQueue.main.async {
   self.analyzedImageView.subviews.forEach({ (s) in
   s.removeFromSuperview()
   })
   for box in observations {
   guard let chars = box.characterBoxes else {
   print("no char values found")
   return
   }
   for char in chars
   {
   let view = self.CreateBoxView(withColor: UIColor.green)
   view.frame = self.transformRect(fromRect: char.boundingBox, toViewRect: self.analyzedImageView)
   self.analyzedImageView.image = self.originalImageView.image
   self.analyzedImageView.addSubview(view)
   self.loadingLbl.isHidden = true
   }
   }
   }
   
  } 

N|Solid

• Creating rectangle detection request

 lazy var rectangleBoxRequest: VNDetectRectanglesRequest = {
 return VNDetectRectanglesRequest(completionHandler:self.handleRectangles)
 }()

• Create a image request handler

   let handler = VNImageRequestHandler(ciImage: ciImage, orientation: Int32(uiImage.imageOrientation.rawValue))

• Assigning image requests to request handler

   try handler.perform([self.rectangleBoxRequest])

• Handler code

   func handleRectangles(request: VNRequest, error: Error?) {
   
   guard let observations = request.results as? [VNRectangleObservation]
   else { print("unexpected result type from VNDetectRectanglesRequest")
   return
   }
   guard observations.first != nil else {
   return
   }
   // Show the pre-processed image
   DispatchQueue.main.async {
   self.analyzedImageView.subviews.forEach({ (s) in
   s.removeFromSuperview()
   })
   for rect in observations
   {
   let view = self.CreateBoxView(withColor: UIColor.cyan)
   view.frame = self.transformRect(fromRect: rect.boundingBox, toViewRect: self.analyzedImageView)
   self.analyzedImageView.image = self.originalImageView.image
   self.analyzedImageView.addSubview(view)
   self.loadingLbl.isHidden = true
   }
   }
  }

 handler.perform([self.textRectangleRequest,self.faceDetectionRequest,self.rectangleBoxRequest])

Here am performing text,face and rectangle box analysis on a single input