Stack Overflow
Stack Overflow

Questions tagged [apple-vision]

Apple Vision is a high-level computer vision framework to identify faces, detect and track features, and classify images, video, tabular data, audio and motion sensors data.

Apple Vision framework performs face and face landmark detection on input images and video, barcode recognition, image registration, text detection, and, of course, feature tracking. Vision API allows the use of custom CoreML models for tasks like classification or object detection.

205 questions
1
vote
2 answers

Swift 4: Vision Camera Preview Issues

For an object recognition app with CoreML and Vision I downloaded a sample app from Apple (https://developer.apple.com/documentation/vision/recognizing_objects_in_live_capture). Unfortunately this app only seems to work in portrait mode but I need…
kdawg13
  • 11
  • 3
1
vote
1 answer

Detect an Object from long distance using ARKit and CoreML

How can we detect an object from almost any distance using CoreML or ARKit. Currently I have tried ARKIT 3d object scanning and detection which works from the near distance to the object, But as we get far away from the object, it's unable to detect…
user2096064
  • 108
  • 1
  • 9
1
vote
0 answers

Use of imageCropAndScaleOption and regionOfInterest in VNCoreMLRequest

What happens if I use both imageCropAndScaleOption and regionOfInterest. What's the effect of the following codes request.imageCropAndScaleOption = .centerCrop request.regionOfInterest = CGRect(x: 0.0, y: 0.25, width: 1.0, height: 0.5) request is a…
Danny Wang
  • 429
  • 9
  • 24
1
vote
1 answer

Getting console spam in Xcode when using Vision framework and face moves off screen

I am running a face detector with the Vision framework, but have encountered one item that is making debugging a challenge. When I move a face off screen, I will often be spammed with the following error in the console: LandmarkDetector error…
CodeBender
  • 35,668
  • 12
  • 125
  • 132
1
vote
2 answers

Classifying images with Vision and CoreML in macOS

I have trained IBM Watson to recognize objects of interest. Since remote execution isn’t a requirement I want to export to .mlmodel with the tool provided and run in macOS. Unfortunately learning Swift and macOS development isn’t a requirement…
WuMing2
  • 73
  • 7
1
vote
2 answers

CVPixelBuffer – How to capture every THIRD frame out of 60 fps?

I need only 20 frames out of 60 frames per second for processing (CVPixelBuffer). How to capture every third ARFrame in ARKit session? I need approximately 20 fps for capture (I understand there may be a drop frame). Here's a code's snippet: func…
Andy Jazz
  • 49,178
  • 17
  • 136
  • 220
1
vote
1 answer

Multiple CALayer updates for single Vision/CoreML inference

I am trying to use Vision and CoreML to perform style transfer on tracked objects in as-close-to-real-time as possible. I am using AVKit to capture video, and AVCaptureVideoDataOutputSampleBufferDelegate to get each frame. At a high level, my…
tyrotyrotyro
  • 55
  • 1
  • 7
1
vote
2 answers

Apple Vision Framework Identify face

Is it possible in the Apple Vision Framework to compare faces and recognise if that person is in a picture compared to a reference image of that person? Something like Facebook Face recognition. Thomas
Thomas Delputte
  • 141
  • 1
  • 2
  • 6
1
vote
1 answer

How to measure the dimensions of a 3d object using ARKit or Apple Vision?

Using the iPhone camera (and presumably some combination of ARKit, Apple Vision, CoreML/mlmodels, etc), how would you measure the dimensions (width, height, depth) of an object? The object being something small that sits on a desk Using mlmodel, you…
xta
  • 729
  • 2
  • 8
  • 29
1
vote
0 answers

UIImage never frees memory (memory leak?)

So long as I retain a reference to the UIImage passed as an argument to either of these functions, the memory increase caused by each image-related operation remains. If I call these functions repeatedly (each time with a different instance of…
Gil Birman
  • 35,242
  • 14
  • 75
  • 119
1
vote
1 answer

Compare faces on device

My users need to be able to authenticate themselves using a picture. So that when they create a account on the phone a picture is selected and saved. When they log in a UIImagePickerController() with .sourceType = .camera should take a picture and…
Egghead
  • 6,837
  • 5
  • 20
  • 38
1
vote
1 answer

Objects Track using vision framework in iOS 11

I want to detect object and track that object using vision framework. I am successfully done with detect objects and little bit with tracking also but I don't get so much accuracy with tracking. I want much more accuracy while converting frames as…
Rajni Arora
  • 75
  • 9
1
vote
1 answer

The size of the output layer does not match the number of classes in the classifier?

When I execute my computer vision app, it gives me the following error: "The size of the output layer 'output1' in the neural network does not match the number of classes in the classifier." My CNN has been trained on the chars74K dataset, and has…
Thijs van der Heijden
  • 1,147
  • 1
  • 10
  • 25
1
vote
1 answer

ARKit and Vision – How to place a SCNPlane on a found QR-Code?

Through Vision Framework I'm able to detect a QR-code. The next thing I would like to do is to place a SCNPlane exactly on the QRCode using ARKit. I wrote the code below to find the position of the QRCode in the real world. But the SCNPlane keeps…
KNV
  • 631
  • 4
  • 19
1
vote
2 answers

Difference between using VNCoreMLModel and Inceptionv3.model()?

I have been trying to get started with CoreML (Apple's Machine Learning Library). I am following these tutorials to get started 1) https://www.appcoda.com/coreml-introduction/ 2)…
Teja C
  • 11
  • 1
  • 5
1 2 3
…
13 14