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
6
votes
0 answers

IOS: Brighten up stream for ARKit and Vision

I’m currently working on a feature of my app, which recognizes faces in a camera stream. I’m reading landmark features like the mouth etc. Everything works fine when light conditions are sufficient. But in the dark both ARKit and Vision have…
Bruno Eigenmann
  • 346
  • 3
  • 16
6
votes
1 answer

ARKit & Vision frameworks – Detecting wall edges

I wonder is it theoretically possible to detect wall edges/lines (like in the picture)? All I could achieve is detecting the vertices of rectangles that are visible to Camera Preview. But we can't consider real walls as rectangles. So, is there…
arturdev
  • 10,884
  • 2
  • 39
  • 67
6
votes
3 answers

Is it possible to train a CoreML model on device as the app runs?

Is it possible to ship an iOS app with a CoreML model and then have the app continue improving (training) the model on device based on user behaviour for example? So, then the model would keep growing and improving right on the device with no need…
zumzum
  • 17,984
  • 26
  • 111
  • 172
6
votes
1 answer

How can I take a photo of a detected rectangle in Apple Vision framework

How can I take a photo (get an CIImage) from the successful VNRectangleObservation object? I have a video capture session running and in func captureOutput(_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer, from connection:…
denis631
  • 1,765
  • 3
  • 17
  • 38
6
votes
3 answers

Get the cvPixelBuffer used in a VNImageRequestHandler on the VNDetectTextRectanglesRequest completion handler

I am creating my request with the following code: let textRequest = VNDetectTextRectanglesRequest(completionHandler: self.detectTextHandler) textRequest.reportCharacterBoxes = true self.requests = [textRequest] And inside my…
Pochi
  • 13,391
  • 3
  • 64
  • 104
5
votes
1 answer

Apple Vision – Barcode Detection doesn't work for barcodes with different colours

So, I have to scan different barcodes with various colours. For example, a yellow barcode on black background or yellow barcode on white background. I don't have any issues with them being recognized by traditional linear and CCD barcode scanners. I…
curiously77
  • 225
  • 1
  • 4
  • 24
5
votes
0 answers

How to wrap 3d object around detected object in live tracking

i have created ML Model for foot as VNRecognizedObjectObservation now i am successfully able to detect foot in live tracking the problem is i am not able to wrap or place 3d object on foot as i need 3 coordinates to place AR content. i used below…
Saif
  • 61
  • 5
5
votes
0 answers

Detect Foot and Place 3D model Boots in ARKit

I want to detect foot using Scenekit(ARKit) and place 3D shoes same like body detect and place shirts onto it. Is there any help ? how can i do that ? ARkit ? Vision ? or CoreML What will be the sequence of the work ?
Akhzar Nazir
  • 724
  • 9
  • 13
5
votes
1 answer

ARKit Barcode tracking and Vision framework

I have been trying to draw bounding box for QR code detected during ARSession. The result is: boundingbox 1 boundingbox 2 The barcode is being tracked, but the geometry of bounding box is wrong. How to get correct coordinates of bounding box? The…
Дмитрий Акимов
  • 663
  • 1
  • 8
  • 15
5
votes
0 answers

Memory Leak of CVPixelBuffer In Dispatch Queue Using Vision

I'm using a renderer class within a capture pipeline to add a CI filter to video. Inside the copyRenderedPixelBuffer of the renderer I'd also like to copy the pixel buffer and send it to Vision to detect facial landmarks. I've made a singleton for…
Alistair Cooper
  • 251
  • 1
  • 3
  • 11
5
votes
1 answer

Reading a barcode image without using cocoapods or other external API's

I'm trying to use the new Apple Vision API to detect a barcode from an image and return its details. I've successfully detected a QR code and returned a message using the CIDetector. However I can't make this work for 1 dimensional barcodes. Heres…
Wazza
  • 1,725
  • 2
  • 17
  • 49
5
votes
1 answer

Barcode string value when using the Vision Framework of iOS11

The following piece of Swift code is using the new iOS11 Vision framework to analyze an image and find QR codes within it. let barcodeRequest = VNDetectBarcodesRequest(completionHandler {(request, error) in for result in request.results! { …
yossile
  • 768
  • 1
  • 6
  • 18
4
votes
1 answer

Anyone know how to use Apple's vision framework for real-time text recognition?

I can't seem to find a way to not use the document scanner, and supplement it with AVFoundation instead. I'm trying to create a feature where the user can click a button, scan text, and then save that to some textview w/o having the user click the…
notary
  • 43
  • 1
  • 5
4
votes
2 answers

Swiftui getting an image's displaying dimensions

I'm trying to get the dimensions of a displayed image to draw bounding boxes over the text I have recognized using apple's Vision framework. So I run the VNRecognizeTextRequest uppon the press of a button with this funcion func…
Carlos Maria Caraccia
  • 470
  • 4
  • 22
4
votes
0 answers

"request VNRecognizeTextRequest was cancelled" iOS Vision framework

I am designing an iOS OCR app using the Vision framework. The app relies on a video feed, which is what the user sees, but it takes photos in the background on a timer to improve the text recognition performance (I use the photos to take advantage…
Roo Weed
  • 41
  • 2
1
2
3
…
13 14