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

Why are there negative coordinate in the normalised object detection results? (CoreML,Vision,Swift, Ios)

I compiled the example. https://developer.apple.com/documentation/vision/recognizing_objects_in_live_capture It did not work correctly for me on an iPhone 7 Plus. The rectangles drawn did not cover the items detected. I created an app of my own to…
0
votes
1 answer

Does it matter which pixel format type we choose for AVCaptureSession to run CoreML model using Vision?

I am using Apple's sample app Breakfast finder which does detection and it use pixel format type in biplanar yuv format. I changed it to ARGB and its running on my own model trained on Turi create. Now i have no idea changing the pixel format type…
user2096064
  • 108
  • 1
  • 9
0
votes
0 answers

How to create a request like VNDetectFaceLandmarksRequest, but for detecting a whole human body, not just faces?

I would like to create a request like VNDetectFaceLandmarksRequest, but for detecting and giving the position of a whole human body. Is that possible with Vision framework? If so, what are the steps for accomplishing that?
crvo84
  • 303
  • 2
  • 11
0
votes
1 answer

Apple Vision create custom VNImageBasedRequest

I've been playing with Apple's CoreML and Vision APIs. My goal would be to make a simple proof of concept and be able to recognize nails on a hand picture. This is very specific. I have been trying to find documentation on how to create your own…
Scaraux
  • 3,841
  • 4
  • 40
  • 80
0
votes
0 answers

Replace real world text using ARKit and Vision(?)

I'm trying to build a translator app which would be able to replace foreign text in the real-time, but after exploring possible approaches got a bit cornered. Even though I was able to extract words images using Vision, I couldn't replace them in…
bitemybyte
  • 971
  • 1
  • 10
  • 24
0
votes
1 answer

Overlaying image onto CGRect swift

I'm using the following sample app that Apple provides to do some object detection. https://developer.apple.com/documentation/vision/tracking_multiple_objects_or_rectangles_in_video I'm trying to paste an image of a face on top of the green…
Shalin Shah
  • 8,145
  • 6
  • 31
  • 44
0
votes
1 answer

Warp quadrangle with for corner points to rectangular 2D image with given aspect ratio

I want to build a business card scanner with Vision API. So I'm performing a VNDetectRectanglesRequest with specific rectangle constraints for the business card format (which has a fixed ratio). As a result of this I'm getting a…
heyfrank
  • 5,291
  • 3
  • 32
  • 46
0
votes
1 answer

Rotating UIImage for Google ML Vision framework on Swift 4

When an image gets captured it defaults to left orientation. So when you feed it into the textDetector inside the Google Vision framework, it comes all jumbled, unless you take the photo oriented left (home button on the right). I want my app to…
Tyler Hackbart
  • 1,948
  • 1
  • 10
  • 5
0
votes
2 answers

Drawing rectangles using the CGPoint coordinate system - SWIFT

I am able to draw a rectangle using the code below (works). However, I am using the Vison framework to detect rectangles but it is giving me back CGPoint values that is less than 1.0. When I enter these coordinates to draw a rectangle I get…
johnDoe
  • 709
  • 11
  • 29
0
votes
1 answer

.a library cannot find vision framework

I have a react-native library in my project. The library is objective-c with added swift components requiring and importing vision. The project and target are set for all architectures (including arm64), also they build for all architectures and not…
thibaut noah
  • 1,474
  • 2
  • 11
  • 39
0
votes
1 answer

ARSession stuck indefinitely on ARTrackingStateLimited, with reason as ARTrackingStateReasonInitializing

I am using ARKit ARSession; the first time around I use an ARSession, everything works perfectly. It is fully responsive. Then I pause the ARSession; set it to to NULL so that it gets dealloced and create a second time around sometime later. The…
nishant
  • 736
  • 1
  • 12
  • 22
0
votes
1 answer

How do I generate a class_labels.txt in Keras for usage in a CoreML model?

I have been trying to create an IOS App using coreML, I have trained a convolutional neural network in Keras, when I use CoreMLTools to transform this model to a CoreML model it shows that the output is a multidimensional array, but I want it to be…
Thijs van der Heijden
  • 1,147
  • 1
  • 10
  • 25
0
votes
1 answer

App crashes when request.results of CoreML sqeezeNet model is casted as [VNRectangleObservation]

I am using CoreML SqueezeNet Model to detect paper or rectangles from an image. I have created model and request as per apple documentation. guard let model = try? VNCoreMLModel(for: squeezeNetModel.model)else {fatalError()} let request =…
cgeek
  • 558
  • 5
  • 18
0
votes
1 answer

How to improve VNDetectRectanglesRequest to VNDetectCarRequest?

I use VNImageRequestHandler and VNDetectRectanglesRequest to handle request to find rectangles in a image. But since Vision in iOS11 only provide barcode、rectangle、face finding,but I want to find cars in an image ,what should I change code to find…
hzhou
  • 9
  • 4
0
votes
1 answer

App Only Crashes for Iphone 6 and IPad in IOS 11 using Vision & Machine Learning API

I made a live translation app that identifies an object and translates it using the user's camera. It works just fine on my iPhone 6s and doesn't crash in any of the simulators, but when I run it on an iPhone 6, it crashes as soon I try to segue to…
Codemaster99
  • 87
  • 1
  • 1
  • 7
1 2 3
13
14