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
0
votes
1 answer

Can't run the ActionAndVision sample on iPhone 11 pro

Trying to run the demo project for wwc20-10099 ActionAndVision in a iPhone 11 Pro/iPhone Pro using the supplied sample.mov, or real board. The entire time the app has the "Locating board" overlay instead of finding the board before the bean bags…
user9837656
  • 31
  • 3
0
votes
1 answer

Convert VNCoreMLFeatureValueObservations to VNDetectedObjectObservation

I have exported YOLOV5 model, but the output configuration is in VNCoreMLFeatureValueObservations instead of VNDetectedObjectObservation. Output configuration: [ 4FC4A8B2-A967-4CC7-8A86-E16863258F1B…
ajay_nasa
  • 2,278
  • 2
  • 28
  • 45
0
votes
1 answer

Cropping/Compositing An Image With Vision/CoreImage

I am working with the Vision framework in iOS 13 and am trying to achieve the following tasks; Take an image (in this case, a CIImage) and locate all faces in the image using Vision. Crop each face into its own CIImage (I'll call this a "face…
ZbadhabitZ
  • 2,753
  • 1
  • 25
  • 45
0
votes
2 answers

Vision and CoreML – CGImagePropertyOrientation expects wrong type

Currently I am work with ARKit/CoreML/Vision to identify images/objects. For this purpose I took a look at Apple's sample project Recognizing and Labeling Arbitrary Objects I have copied the following lines from the ViewController.Swift Script into…
Itzuko
  • 54
  • 8
0
votes
2 answers

How to pass an extra parameter to Vision framework?

I have a Swift / CoreML code that works fine. I want to simplify my code by using the Vision framework. In this code, there is a UIImage -> CGImage -> CVPixelBuffer conversion that I would like to get rid of. I know that using Vision one can pass…
Vincent Garcia
  • 635
  • 10
  • 19
0
votes
0 answers

slow frame rate when rendering cifiltered ciimage and MTKView while using face detection (Vision and CIDetection)

I have an app which does real time filtering on camera feed, i'm getting each frame from camera and then do some filtering using CIFilter and then pass the final frame(CIImage) to MTKView to be shown on my swiftUI view, it works fine, but when i…
Mostafa
  • 48
  • 1
  • 8
0
votes
1 answer

AVCaptureVideoPreviewLayer does not detect objects in two ranges of the screen

I downloaded Apple's project about recognizing Objects in Live Capture. When I tried the app I saw that if I put the object to recognize on the top or on the bottom of the camera view, the app doesn't recognize the object: In this first image the…
Edoardo
  • 657
  • 7
  • 24
0
votes
1 answer

Swift access progressvalue in VNRecognizeTextRequest with completion handler

I'd like to capture the progress value in a VNRecognizeTextRequest session. So I inclueded it in a closure. The problem is it is passed when the closure is completed. I can capture the value and print it but not pass it to the main thread to update…
Carlos Maria Caraccia
  • 470
  • 4
  • 22
0
votes
0 answers

Returning the first result

I'm new to swift and trying my best to learn as much as possible and searching through many forums. However, the answer to this question doesn't appear to be anywhere. So I'm hoping someone will be able to help me with this. I'm wanting to return…
L. Hinton
  • 69
  • 1
  • 7
0
votes
1 answer

What are the input image size requirements for CoreML Vision face detection

I'm working with Vision framework to detect faces in images. I couldn't find in the Apple's documentation what are the input image requirements. Usually when working with a machine learning model, and particularly with .mlmodel in CoreML, it…
Sanich
  • 1,739
  • 6
  • 25
  • 43
0
votes
1 answer

Apple Vision Error – Use of unresolved identifier 'ObjectDetector'

Xcode 10.3 started generating errors in all my projects containing VNCoreMLModel() class in lines like this: let visionModel = try? VNCoreMLModel(for: ObjectDetector().model) Here's how this error looks like: "Use of unresolved identifier…
Andy Jazz
  • 49,178
  • 17
  • 136
  • 220
0
votes
1 answer

Google mobile vision iOS swift

https://developers.google.com/vision/ios/text-overview the link refers to Objective C implementation. Can anyone help me out for Swift Version? I have tried using the above code, but the delegates are somehow not working in my case.
prasad nikumbh
  • 165
  • 11
0
votes
0 answers

iOS - CGImage cropping rotated rectangle

I am using Vision framework to detect rectangles on images. When Vision detected any rectangle it returns four points of rectangle corners. I would like to crop this rectangle from cgImage but the main problem is how to do it when rectangle is…
Sebastianor
  • 196
  • 10
0
votes
0 answers

Tracking Objects from a VNCoreMLFeatureValueObservation

I am using Vision and a CoreML Model whose role is prediction rather than classification or image-to-image processing. I input the pixelBuffer and get back a [VNCoreMLFeatureValueObservation]1. func createCoreMLRequest() -> VNCoreMLRequest? { …
Allen Savio
  • 151
  • 2
  • 16
0
votes
0 answers

Reading qrcode (non-unique) once per session with Arkit+Vision

Given two QRcode (not unique) fixed in space. As with Arkit and Vision, count each code once per session, even if we take away the camera. I managed to write reading QRcodes into a session (hitTest) and using Vision to recognize and add a 3D object,…
Shaguard
  • 1
  • 1
1 2 3
…
13 14