I am using VNRecognizeTextRequest to read Chinese characters. It works fine with text written horizontally, but if even two characters are written vertically, then nothing is recognized. Does anyone know how to get the vision framework to either handle vertical text or recognize characters individually when working with Chinese? I am setting VNRequestTextRecognitionLevel to accurate, since setting it to fast does not recognize any Chinese characters at all. I would love to be able to use fast recognition and handle the characters individually, but it just doesn't seem to work with Chinese. And, when using accurate, if I take a picture of any amount of text, but it's arranged vertically, then nothing is recognized. I can take a picture of 1 character and it works, but if I add just 1 more character below it, then nothing is recognized. It's bizarre. I've tried setting usesLanguageCorrection = false and tried using VNRecognizeTextRequestRevision3, ...Revision2 and ...Revision1. Strangely enough, revision 2 seems to recognize some text if it's vertical, but the bounding boxes are off. Or, sometimes the recognized text will be wrong. I tried playing with DataScannerViewController and it's able to recognize characters in vertical text, but I can't figure out how to replicate it with VNRecognizeTextRequest. The problem with using DataScannerViewController is that it treats the whole text block as one item, and it uses the live camera buffer. As soon as I capture a photo, I still have to use VNRecognizeTextRequest. Below is a code snippet of how I'm using VNRecognizeTextRequest. There's not really much to it and there aren't many other parameters I can try out (plus I've already played around with them). I've also attached a sample image with text laid out vertically. func detectText( in sourceImage: CGImage, oriented orientation: CGImagePropertyOrientation ) async throws -> [VNRecognizedTextObservation] { return try await withCheckedThrowingContinuation { continuation in let request = VNRecognizeTextRequest { request, error in // ... continuation.resume(returning: observations) } request.recognitionLevel = .accurate request.recognitionLanguages = ["zh-Hant", "zh-Hans"] // doesn't seem have any impact // request.usesLanguageCorrection = false do { let requestHandler = VNImageRequestHandler( cgImage: sourceImage, orientation: orientation ) try requestHandler.perform([request]) } catch { continuation.resume(throwing: error) } } }

Currently, I'm reducing the ios version being sold on the App Store with the same app id and identifier to visionos, and I'm trying to upload it using the same identifier, developer id, and icloud, but I can't upload it because of an error. I didn't know what the problem was, so I updated the update of the ios version early, but I uploaded the review without any problems. Uploading the visionos single version has a profile problem, so I would appreciate it if you could tell me the solution. In addition, a lot of the code used in the ios version is not compatible with visionos, so we have created a new project for visionos.

Context So basically I've trained my model for object detection with +4k images. Under preview I'm able to check the prediction for Image "A" which detects two labels with 100% and its Bounding Boxes look accurate. The problem itself However, inside the Swift Playground, when I try to perform object detection using the same model and same Image I don't get same results. What I expected Is that after performing the request and processing the array of VNRecognizedObjectObservation would show the very same results that appear in CreateML Preview. Notes: So the way I'm importing the model into playground is just by drag and drop. I've trained the images using JPEG format. The test Image is rotated so that it looks vertical using MacOS Finder rotation tool. I've tried, while creating VNImageRequestHandlerto pass a different orientation, with the same result. Swift Playground code This is the code I'm using. import UIKit import Vision do{ let model = try MYMODEL_FROMCREATEML(configuration: MLModelConfiguration()) let mlModel = model.model let coreMLModel = try VNCoreMLModel(for: mlModel) let request = VNCoreMLRequest(model: coreMLModel) { request, error in guard let results = request.results as? [VNRecognizedObjectObservation] else { return } results.forEach { result in print(result.labels) print(result.boundingBox) } } let image = UIImage(named: "TEST_IMAGE.HEIC")! let requestHandler = VNImageRequestHandler(cgImage: image.cgImage!) try requestHandler.perform([request]) } catch { print(error) } Additional Notes & Uncertainties Not sure if this is relevant, but just in case: I've trained the model using pictures I took from my iPhone using 48MP HEIC format. All photos were on vertical position. With a python script I overwrote the EXIF orientation to 1 (Normal). This was in order to be able to annotate the images using the CVAT tool and then convert to CreateML annotation format. Assumption #1 Since I've read that Object Detection in Create ML is based on YOLOv3 architecture which inside the first layer resizes the image dimension, meaning that I don't have to worry about using very large images to train my model. Is this correct? Assumption #2 Also makes me asume that the same thing happens when I try to make a prediction?

Hello, I have been working to try to create a scanner to scan a PDF417 barcode from your photos library for a few days now and have come to a dead end. Every time that I run my function on the photo, my array of observations always returns as []. This example is me trying to use it with an automatic generated image because I think that if it works with this, it will work with a real screenshot. That being said, I have already tried with all sorts of images that aren't pre-generated, and they, still, have failed to work. Code below: Calling the function createVisionRequest(image: generatePDF417Barcode(from: "71238-12481248-128035-40239431")!) Creating the Barcode: static func generatePDF417Barcode(from key: String) -> UIImage? { let data = key.data(using: .utf8)! let filter = CIFilter.pdf417BarcodeGenerator() filter.message = data filter.rows = 7 let transform = CGAffineTransform(scaleX: 3, y: 4) if let outputImage = filter.outputImage?.transformed(by: transform) { let context = CIContext() if let cgImage = context.createCGImage(outputImage, from: outputImage.extent) { return UIImage(cgImage: cgImage) } } return nil } Main function for scanning the barcode: static func desynthesizeIDScreenShot(from image: UIImage, completion: @escaping (String?) -> Void) { guard let ciImage = CIImage(image: image) else { print("Empty image") return } let imageRequestHandler = VNImageRequestHandler(ciImage: ciImage, orientation: .up) let request = VNDetectBarcodesRequest { (request,error) in guard error == nil else { completion(nil) return } guard let observations = request.results as? [VNDetectedObjectObservation] else { completion(nil) return } request.revision = VNDetectBarcodesRequestRevision2 let result = (observations.first as? VNBarcodeObservation)?.payloadStringValue print("Observations", observations) if let result { completion(result) print() print(result) } else { print(error?.localizedDescription) //returns nil completion(nil) print() print(result) print() } } request.symbologies = [VNBarcodeSymbology.pdf417] try? imageRequestHandler.perform([request]) } Thanks!

i saw there is a way to track hands with vision, but is there also a way to record that movement and export it to fbx? Oh and is there a way to set only one hand to be recorded or both at the same time? Implementation will be in SwiftUI

After working immersively in vision, can the user adjust immersive mode and transparency in the wallpaper? Will developers be able to arbitrarily adjust transparency with code to see users overlap between reality and immersive mode at the same time?

i'm struggling to get my app through validation for visionOS. I'm not sure why I'm getting this as all of the appIcons are filled.

I have trained a model to classify some symbols using Create ML. In my app I am using VNImageRequestHandler and VNCoreMLRequest to classify image data. If I use a CVPixelBuffer obtained from an AVCaptureSession then the classifier runs as I would expect. If I point it at the symbols it will work fairly accurately, so I know the model is trained fairly correctly and works in my app. If I try to use a cgImage that is obtained by cropping a section out of a larger image (from the gallery), then the classifier does not work. It always seems to return the same result (although the confidence is not a 1.0 and varies for each image, it will be to within several decimal points of it, eg 9.9999). If I pause the app when I have the cropped image and use the debugger to obtain the cropped image (via the little eye icon and then open in preview), then drop the image into the Preview section of the MLModel file or in Create ML, the model correctly classifies the image. If I scale the cropped image to be the same size as I get from my camera, and convert the cgImage to a CVPixelBuffer with same size and colour space to be the same as the camera (1504, 1128, kCVPixelFormatType_420YpCbCr8BiPlanarVideoRange) then I get some difference in ouput, it's not accurate, but it returns different results if I specify the 'centerCrop' or 'scaleFit' options. So I know that 'something' is happening, but it's not the correct thing. I was under the impression that passing a cgImage to the VNImageRequestHandler would perform the necessary conversions, but experimentation shows this is not the case. However, when using the preview tool on the model or in Create ML this conversion is obviously being done behind the scenes because the cropped part is being detected. What am I doing wrong. tl;dr my model works, as backed up by using video input directly and also dropping cropped images into preview sections passing the cropped images directly to the VNImageRequestHandler does not work modifying the cropped images can produce different results, but I cannot see what I should be doing to get reliable results. I'd like my app to behave the same way the preview part behaves, I give it a cropped part of an image, it does some processing, it goes to the classifier, it returns a result same as in Create ML.

I used metal and CompositorLayer to render an immersive space skybox. In this space, the window created by the Swift UI I created only displays the gray frosted glass background effect (it seems to ignore the metal-rendered skybox and only samples and displays the black background). why is that? Is there any solution to display the normal frosted glass background? Thank you very much!

Hey guys! I'm building an app which detects cars via Vision and then retrieves the distance to said car by a synchronized depthDataMap. However, I'm having trouble finding the correct corresponding pixel in that depthDataMap. While the CGRect of the ObjectObservation ranges from 0 - 300 (x) and 0 - 600 (y), The width x height of the DepthDataMap is Only 320 x 180, so I can't get the right corresponding pixel. Any Idea on how to solve this? Kind regards

My project is use OC, is a iOS App, and now I need make it to visionOS (not unmodified designed for iPhone). So a question one, how can I differentiate visionOS by code, need use macro definitions, otherwise, it cannot be compiled. The question two, have some other tips？or other question need I know? Thanks.

I want to make icloud backup using SwiftData in VisionOS and I need to use SwiftData first but I get the following error even though I do the following steps I followed the steps below I created a Model import Foundation import SwiftData @Model class NoteModel { @Attribute(.unique) var id: UUID var date:Date var title:String var text:String init(id: UUID = UUID(), date: Date, title: String, text: String) { self.id = id self.date = date self.title = title self.text = text } } I added modelContainer WindowGroup(content: { NoteView() }) .modelContainer(for: [NoteModel.self]) And I'm making inserts to test import SwiftUI import SwiftData struct NoteView: View { @Environment(\.modelContext) private var context var body: some View { Button(action: { // new Note let note = NoteModel(date: Date(), title: "New Note", text: "") context.insert(note) }, label: { Image(systemName: "note.text.badge.plus") .font(.system(size: 24)) .frame(width: 30, height: 30) .padding(12) .background( RoundedRectangle(cornerRadius: 50) .foregroundStyle(.black.opacity(0.2)) ) }) .buttonStyle(.plain) .hoverEffectDisabled(true) } } #Preview { NoteView().modelContainer(for: [NoteModel.self]) }

Currently, I try to test the ImageTrackingProvider with the Apple Vision Pro. I started with some basic code: import RealityKit import ARKit @MainActor class ARKitViewModel: ObservableObject{ private let session = ARKitSession() private let imageTracking = ImageTrackingProvider(referenceImages: ReferenceImage.loadReferenceImages(inGroupNamed: "AR")) func runSession() async { do{ try await session.run([imageTracking]) } catch{ print(error) } } func processUpdates() async { for await _ in imageTracking.anchorUpdates{ print("test") } } } I only have one picture in the AR folder. I added the size an I have no error messages in the AR folder. As I am trying to run the application with the vision Pro, I receive following error: ar_image_tracking_provider_t <0x28398f1e0>: Failed to load reference image <ARReferenceImage: 0x28368f120 name="IMG_1640" physicalSize=(1.350, 2.149)> with error: Failed to add reference image. It finds the image, but there seems to be a problem with the loading. I tried the jpeg and the png format. I do not understand why it fails to load the ReferenceImage. I use Xcode Version 15.3 beta 3

I think there is a problem with the keyboard of vision pro. I don't think it's difficult to enter another language. If you're not going to make it, shouldn't Apple provide an extended custom keyboard? Sometimes it's frustrating to see things that are intentionally restricted. If you have any information about vision pro's keyboard or want to discuss it, let's talk about your thoughts together! I don't have any information yet

Hello . I'm currently selling an app. I tried to run the ios version on visionos to provide the same service as the existing app, but a huge amount of incompatible code was generated. Can I create a visionos app with the same name, add visionos from the App Store connect site, and upload a completely separate app project file? The iOS app and the visionos app will use the same icloud, in-app payment, and so on. However, we plan to separate the project itself to reduce the size of the user's app itself and optimize it.

Like the basic environment of visionpro, I want to create a surrounding space when I run my app. Like other apps, I want to customize the space like when I run a movie theater or Apple TV, so I want to give users a better experience. Does anyone know the technology or developer documentation?

Hi, I'm working on developing an app. I need my app to work in a crowd with multiple people (who have multiple hands). From what I understand, the Vision Framework currently uses a heuristic of "largest hand" to assign as the detected hand. This won't work for my application since the largest hand won't always be the one that is of interest. In fact, the hand of interest will be the one that is pointing. I know how to train a model using CreateML to identify a hand that is pointing, but where I'm running into issues is that there is no straightforward way to directly override the Vision framework's built-in heuristic of selecting the largest hand when you're solely relying on Swift and Create ML. I would like my framework to be: Request hand landmarks Process image CreateML reports which hand is pointing We use the pointing hand to collect position data on the points of the index finger But within vision's framework, if you set the number of hands to collect data for to 1, it will just choose the largest hand and report position data for that hand only. Of course, the easy work around here is to set it to X number of hands, but within the scope of an IOS device, this is computationally intensive (since my app could be handling up to 10 hands at a time). Has anyone come up with a simpler solution to this problem or aware of something within visionOS to do it?

Hi Developers, I want to create a Vision app on Swift Playgrounds on iPad. However, Vision does not properly function on Swift Playgrounds on iPad or Xcode Playgrounds. The Vision code only works on a normal Xcode Project. SO can I submit my Swift Student Challenge 2024 Application as a normal Xcode Project rather than Xcode Playgrounds or Swift Playgrounds File. Thanks :)

Hi, I tried to change the default size for a volumetric window but It looks like this window has a maximum width value. Is it true? WindowGroup(id: "id") { ItemToShow() }.windowStyle(.volumetric) .defaultSize(width: 100, height: 0.8, depth: 0.3, in: .meters) Here I set the width to 100 meters but It still looks like about 2 meters

Hello everyone, I want to develop an app for vision pro that aims to help people with vertigo and dizziness problems. The problem is that I can not afford vision pro. If I use standart vr set with an iPhone inside would it cause issues on real vision pro?