Hello, With the update from iOS 26 to iOS 27 I have noticed significant regressions and degraded performance when using the Vision Framework for OCR via 'VNRecognizeTextRequest'. The degraded performance is only applicable to the .accurate model, the .fast model is identical between iOS 26 and iOS 27. I have an app that uses this framework extensively for extracting information from the video feed of professional cinema cameras. This runs using en-US, language correction off with a specific region of interest. On iOS 26 everything works reliably as it has for the past few years, with the exact same codebase on iOS 27 many strings that were previously detected are no longer detected, some strings return as if they've been read upside down (ISO1280 is returned as 08ZLOSI) and there are a lot of Cyrillic look alikes mixed into Latin text, there also appears to be a lot more junk characters tacked onto the end of numbers ('12ł' is returned when previously it was just '12'). You often see whole line duplicates too where the same text is recognised twice, once as a single line with all strings combined and once as individual strings. The iOS 27 Simulator doesn't show any of this. I only saw it on real iPads, if you only test in the Simulator you'll miss it. To put numbers on it, I built a test set of about 26,500 frame grabs and ran them through 'VNRecognizeTextRequest' on iPadOS 18, 26 and 27. With the version of my app that's on the App Store today, iOS 26 reads 99.7% of values correctly. On iOS 27 that drops to 65%. I've resolved this issue now and have been able to retain the level of performance that existed on iOS 26, this involves various preprocessing steps to the images as well as a significant amount of validation after the Vision Framework returns its results. These fixes took around 3.5 Days of work which is incredibly frustrating. I would much rather use my time building new features instead of fixing regressions introduced by poorly validated new models that have been shipped in iOS 27. What frustrates me most is this change wasn't announced anywhere and there's no way to opt out. The revision number didn't change so there's no way to keep using the model that worked. If this had shipped as VNRecognizeTextRequestRevision4 apps could have stayed on VNRecognizeTextRequestRevision3 until they'd had a chance to test. Or permanently stayed on 'VNRecognizeTextRequestRevision3' as obviously the new version performs significantly worse. Instead an app that worked fine on iOS 26 now gets wrong text back on iOS 27 with no error, no warning and nothing in the release notes. For a framework people rely on for real work that's a significant regression. It seems that other developers have also come across this issue: https://developer.apple.com/forums/thread/845452 For technical reference, if you diff System/Library/PrivateFrameworks/TextRecognition.framework between iOS 26.5 (23F77) and iOS 27.0 (24A434) you uncover a number of changes. New models on iOS 27 seem to use an '_e5' variant. The text detector in iOS 26 references training run 'yyzn76u6fs' with 88560 iterations, iOS 27 references training run 'hvcthxumvz' with only 10116 iterations. Perhaps an 8x reduction in iterations has something to do with the poor performance in iOS 27? Further, the orientation model changes from iOS 26 'cr_orientation_model_v1' with 1858472 iterations vs. iOS 27 'cr_orientation_model_v1_e5' with 671065 iterations. The Latin and Cyrillic Recogniser changed model entirely from 'cr_tr_model_latincyrillic_v3' on iOS 26 to 'cr_tr_model_latincyrillic_v3_e5' on iOS 27. It seems these 'e5' models are optimised for the neural engine. Is there any way to get the iOS 26 models/behaviour back or plans to back deploy the old model in iOS 27.1 or iOS 27.2? Can future model changes like this come with a new revision number? What testing process does the Vision Team use to validate models as clearly something was missed here? Thanks!

When building apps, how can I maximize my camera features while using an app to scan and analyze textiles? Is there an integration that has to be inputted that catalogs every fabric type or AI models are able to learn fabric type from every scan? also what is the process/code of including visionOS to scan fabric types to catalog on devices such as smartphones and computers?

I would like to understand the foundations of connecting my apps api structure to corporate reporting in regards to textile manufacturing. utilizing the core ML and vision through smartphone to link raw data capture and strategic execution.

Using VisionKit, there's two main ways to get text from images. ImageAnalyzer VNRecognizeRequest Based on some OCR tests, I'm seeing that the outputs from these two methods are different. Initially, I thought ImageAnalyzer was running VNRequestTextRecognitionLevel.fast because it's for Live Text, but the outputs from ImageAnalyzer are sometimes better than VNRequestTextRecognitionLevel.accurate. Is ImageAnalyzer running VNRequestTextRecognition in the background? Or if it isn't, what pipeline is it using to detect text?

I'm trying to use VNRecognizeTextRequest and/or VNDetectTextRectanglesRequest to highlight Chinese text in an image. The results are mediocre/bad compared to what's recognized in e.g. the Photos app. The VN functions work okay for most left-to-right text that's in a "standard" font. The VN functions completely fail to recognize any top-to-bottom text at all, and also completely fail to recognize any text that's a little bit stylized. The ImageAnalysis functions have no problem recognizing and transcribing all the text in an image, they do a great job, but they don't return bounding boxes for the text, so as great as they are, they're kind of useless for my purposes. I guess my question is, why are the VN functions different from (and worse than) the ImageAnalysis functions, and is there any way to get the VN functions to do better?? Thanks in advance!

Hi everyone, I'm working on an iOS app that uses VisionKit and I'm exploring the .visualLookUp feature. Specifically, I want to extract the detailed information that Visual Look Up provides after identifying an object in an image (e.g., if the object is a flower, retrieve its name; if it’s a clothing tag, get the tag's content).

We are facing an issue with VNDocumentCameraViewController where the tick button in the top-right corner becomes completely unresponsive after a document is scanned. When the user taps the tick button immediately after capturing the document — before the "Ready for next Scan" text appears on screen — the button freezes and the documentCameraViewController(_:didFinishWith:) delegate is never called. Through debugging, we observed that if the tick is tapped before the scanned image thumbnail appears in the bottom-left corner, the delegate is never triggered. However, if the user waits for the thumbnail to appear and then taps the tick, it works as expected. This indicates that VNDocumentCameraViewController has an internal processing pipeline that must complete before the tick button becomes truly interactive, but there is no visual indication or API callback to inform the user or the developer when it is safe to tap. We would appreciate Apple looking into this and either disabling the button during processing, queuing the tap, or providing a delegate callback for when the controller is truly ready.

It is vital for Apple to refine its OCR models to correctly distinguish between Khmer and Thai scripts. Incorrectly labeling Khmer text as Thai is more than a technical bug; it is a culturally insensitive error that impacts national identity, especially given the current geopolitical climate between Cambodia and Thailand. Implementing a more robust language-detection threshold would prevent these harmful misidentifications. There is a significant logic flaw in the VNRecognizeTextRequest language detection when processing Khmer script. When the property automaticallyDetectsLanguage is set to true, the Vision framework frequently misidentifies Khmer characters as Thai. While both scripts share historical roots, they are distinct languages with different alphabets. Currently, the model’s confidence threshold for distinguishing between these two scripts is too low, leading to incorrect OCR output in both developer-facing APIs and Apple’s native ecosystem (Preview, Live Text, and Photos). import SwiftUI import Vision class TextExtractor { func extractText(from data: Data, completion: @escaping (String) -> Void) { let request = VNRecognizeTextRequest { (request, error) in guard let observations = request.results as? [VNRecognizedTextObservation] else { completion("No text found.") return } let recognizedStrings = observations.compactMap { observation in let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } completion(recognizedStrings.joined(separator: "\n")) } request.automaticallyDetectsLanguage = true // <-- This is the issue. request.recognitionLevel = .accurate let handler = VNImageRequestHandler(data: data, options: [:]) DispatchQueue.global(qos: .background).async { do { try handler.perform([request]) } catch { completion("Failed to perform OCR: \(error.localizedDescription)") } } } } Recognizing Khmer Confidence Score is low for Khmer text. (The output is in Thai language with low confidence score) Recognizing English Confidence Score is high expected. Recognizing Thai Confidence Score is high as expected Issues on Preview, Photos Khmer text Copied text Kouk Pring Chroum Temple [19121 รอาสายสุกตีนานยารรีสใหิสรราภูชิตีนนสุฐตีย์ [รุก เผือชิษาธอยกัตธ์ตายตราพาษชาณา ถวเชยาใบสราเบรถทีมูสินตราพาษชาณา ทีมูโษา เช็ก อาษเชิษฐอารายสุกบดตพรธุรฯ ตากร"สุก"ผาตากรธกรธุกเยากสเผาพศฐตาสาย รัอรณาษ"ตีพย" สเผาพกรกฐาภูชิสาเครๆผู:สุกรตีพาสเผาพสรอสายใผิตรรารตีพสๆ เดียอลายสุกตีน ธาราชรติ ธิพรหณาะพูชุบละเาหLunet De Lajonquiere ผารูกรสาราพารผรผาสิตภพ ตารสิทูก ธิพิ คุณที่นสายเระพบพเคเผาหนารเกะทรนภาษเราภุพเสารเราษทีเลิกสญาเราหรุฬารชสเกาก เรากุม สงสอบานตรเราะากกต่ายภากายระตารุกเตียน Recommended Solutions 1. Set a Threshold Filter out the detected result where the threshold is less than or equal to 0.5, so that it would not output low quality text which can lead to the issue. For example, let recognizedStrings = observations.compactMap { observation in if observation.confidence <= 0.5 { return nil } let str = observation.topCandidates(1).first?.string return "{text: \(str!), confidence: \(observation.confidence)}" } 2. Add Khmer Language Support This issue would never happen if the model has the capability to detect and recognize image with Khmer language. Doc2Text GitHub: https://github.com/seanghay/Doc2Text-Swift

I'm adopting Liquid Glass in iOS 26, when I try to test VNDocumentCameraViewController with document scanning after Liquid Glass enabled, there's a crash just after a photo is taken in VNDocumentCameraViewController, here's the screenshot when it crashed The exception output in XCode console is this: *** Terminating app due to uncaught exception 'NSInternalInconsistencyException', reason: 'Layout requested for visible navigation bar, <UINavigationBar: 0x1240bde00; frame = (0 117; 390 54); opaque = NO; tintColor = UIExtendedSRGBColorSpace 1 1 0 1; layer = <CALayer: 0x120c21e60>> standardAppearance=0x12407b900 scrollEdgeAppearance=0x12407bb80 compactAppearance=0x12407b880 no-scroll-edge-support, when the top item belongs to a different navigation bar. topItem = <UINavigationItem: 0x1240bd800> style=navigator leftBarButtonItems=0x123d4e5f0 rightBarButtonItems=0x123d4d5a0, navigation bar = <UINavigationBar: 0x107b9ad00; frame = (0 47; 390 54); opaque = NO; autoresize = W; tintColor = UIExtendedSRGBColorSpace 1 1 0 1; layer = <CALayer: 0x120c20150>> delegate=0x10a805200 standardAppearance=0x107b2c300 scrollEdgeAppearance=0x107b2c280 compactAppearance=0x107b2c100, possibly from a client attempt to nest wrapped navigation controllers.' *** First throw call stack: (0x18e1db994 0x18b0f5814 0x18c092aa0 0x193b18660 0x193a7d540 0x193a7e020 0x1953ec4a0 0x1943b7d78 0x18ed83420 0x18ed82f74 0x18eb83134 0x18eb44c10 0x18eb70bc4 0x18eb7e74c 0x193ac8cd0 0x193ac8c04 0x193ad6afc 0x193ad5f8c 0x27b456560 0x18e12c4cc 0x18e15c0b0 0x18e15bfd8 0x18e133c1c 0x18e132a6c 0x22ed54498 0x193af6ba4 0x193a9fa78 0x193bcb68c 0x102cc2718 0x102cc2688 0x102cc2794 0x18b14ae28) libc++abi: terminating due to uncaught exception of type NSException

We are facing a UI layout issue while using VisionKit (VNDocumentCameraViewController) for document scanning. After capturing a document, an unexpected extra blank space appears above the “Retake” and “Keep” action bar also in Bottom. This extra space is not part of our custom UI and seems to be introduced by VisionKit itself. This issue impacts the final scan preview layout and reduces usable screen space, especially noticeable on devices all the device iPhone or iPad

Hi, I'm trying to use the new RecognizeDocumentsRequest from the Vision Framework to read a receipt. It looks very promising by being able to read paragraphs, lines and detect data. So far it unfortunately seems to read every line on the receipt as a paragraph and when there is more space on one line it creates two paragraphs. Is there perhaps an Apple Engineer who knows if this is expected behaviour or if I should file a Feedback for this? Code setup: let request = RecognizeDocumentsRequest() let observations = try await request.perform(on: image) guard let document = observations.first?.document else { return } for paragraph in document.paragraphs { print(paragraph.transcript) for data in paragraph.detectedData { switch data.match.details { case .phoneNumber(let data): print("Phone: \(data)") case .postalAddress(let data): print("Postal: \(data)") case .calendarEvent(let data): print("Calendar: \(data)") case .moneyAmount(let data): print("Money: \(data)") case .measurement(let data): print("Measurement: \(data)") default: continue } } } See attached image as an example of a receipt I'd like to parse. The top 3 lines are the name, street, and postal code + city. These are all separate paragraphs. Checking on detectedData does see the street (2nd line) as PostalAddress, but not the complete address. Might that be a location thing since it's a Dutch address. And lower on the receipt it sees the block with "Pomp 1 95 Ongelood" and the things below also as separate paragraphs. First picking up the left side and after that the right side. So it's something like this: * Pomp 1 Volume Prijs € TOTAAL * BTW Netto 21.00 % 95 Ongelood 41,90 l 1.949/ 1 81.66 € 14.17 67.49

We're observing several UI issues with VNDocumentCameraViewController on devices running iOS 26. These screens were functioning correctly in earlier iOS versions. Issue 1 - On the edge correction screen, the top bar now appears as a gray strip beneath the status bar, whereas in previous iOS versions, it was positioned at the bottom of the screen. Do we have any workarounds to address this issue? Issue2 - The edit buttons and their labels are not clearly visible, affecting usability. Im using XCode 16.4 to build to iOS26 and the usage is like below: `let scanner = VNDocumentCameraViewController() scanner.delegate = self self.present(scanner, animated: true)`

We're observing several localization issues with VNDocumentCameraViewController on devices running iOS 26. These localizations were correct in earlier iOS versions. Images indicate that some English labels appear when the device's language is changed to German. The issue can be reproduced by using the Note app.

Prerequisite: After the MDM APP issues the command, the camera on the phone is no longer visible (unusable). After upgrading to iOS 26.1, the isSourceTypeAvailable: UIImagePickerControlSourceTypeCamera method keeps returning true when the camera is unavailable. The isSourceTypeAvailable: UIImagePickerControlSourceTypeCamera method on iOS 26.0.1 is normal, returning false when the camera is unavailable and true when it is available.

The "Cancel" button for VNDocumentCameraViewController is not displayed on iPadOS 26. This issue appears to be specific to iPad, as the button appears correctly on iPhone.

The design of VNDocumentCameraViewController has been updated with iOS 26. Now the 'done' button that appears when at least one page has been scanned is by default in blue (liquid glass). Changing the navBar or the barButtonItems tintColor does not work. So, how does one change the color of this button to match the app's color? Thank you very much!

Description We observed multiple UI issues in VisionKit (VNDocumentCameraViewController) on iPad devices running iPadOS 26 (from Public Beta 4 onwards): Tab bar button titles are not properly visible due to color/contrast issues. An extra back button appears in the navigation bar when editing a captured image in landscape mode. These issues seem to be iPadOS 26 bugs, as Apple does not provide public APIs to customize or override VNDocumentCameraViewController. VisionKit relies on private ICDocCam* classes, which are not accessible for modification. Steps to Reproduce Open the app on an iPad running iPadOS 26 (Public Beta 4 or later). Switch the device to landscape mode. Launch document scanning using VNDocumentCameraViewController. Capture a document and tap Keep Scan. Go to the edit captured image screen. Observed Behavior: Tab bar button titles are not clearly visible (color/contrast issue). An extra back button is displayed in the navigation bar.

How to obtain the physical memory size of VisionPro and how much memory is currently available

Before you post —Camera doesn't work on the Simulator— that's no longer true. I've made a solution that makes the Simulator believe there's an actual hardware device connected, allowing users to stream the macOS camera to the iOS Simulator (see for more info RocketSim's documentation: https://docs.rocketsim.app/features/hzQMSrSga7BGWvxdNVdwYs/simulator-camera-support/58tQ5jvevLNSnyUEA7VgAv) Now, it works for VNDocumentCameraViewController, but when I try opening DataScannerViewController, I directly run into: Failed to start scanning: The operation couldn’t be completed. (VisionKit.DataScannerViewController.ScanningUnavailable error 0.) My question: How does this view controller determine whether scanning is available? Is there a certain capability the available AVCaptureDevice's need to support maybe? Any direction would be helpful for me to make this work for developers, making them build apps faster!

In Apple Vision Pro, I want to implement a HUD page similar to the one in Medivis' SuricalAR product (i.e. the UI is fixed on the screen field of view rather than in space). How should I do it?