Hey Devs,
I'm trying to create my own Real Time Text detection like this Apple project. https://aninterestingwebsite.com/documentation/vision/extracting-phone-numbers-from-text-in-images
I want to use the new iOS18 RecognizeTextRequest instead of the old VNRecognizeTextRequest in my SwiftUI project.
This is my delegate code with the camera setup. I removed region of interest for debugging but I'm trying to scan English words in books. The idea is to get one word in the ROI in the future. But I can't even get proper words so testing without ROI incase my math is wrong.
@Observable
class CameraManager: NSObject, AVCapturePhotoCaptureDelegate
...
override init() {
super.init()
setUpVisionRequest()
}
private func setUpVisionRequest() {
textRequest = RecognizeTextRequest(.revision3)
}
...
func setup() -> Bool {
captureSession.beginConfiguration()
guard
let captureDevice = AVCaptureDevice.default(
.builtInWideAngleCamera, for: .video, position: .back)
else {
return false
}
self.captureDevice = captureDevice
guard let deviceInput = try? AVCaptureDeviceInput(device: captureDevice)
else {
return false
}
/// Check whether the session can add input.
guard captureSession.canAddInput(deviceInput) else {
print("Unable to add device input to the capture session.")
return false
}
/// Add the input and output to session
captureSession.addInput(deviceInput)
/// Configure the video data output
videoDataOutput.setSampleBufferDelegate(
self, queue: videoDataOutputQueue)
if captureSession.canAddOutput(videoDataOutput) {
captureSession.addOutput(videoDataOutput)
videoDataOutput.connection(with: .video)?
.preferredVideoStabilizationMode = .off
} else {
return false
}
// Set zoom and autofocus to help focus on very small text
do {
try captureDevice.lockForConfiguration()
captureDevice.videoZoomFactor = 2
captureDevice.autoFocusRangeRestriction = .near
captureDevice.unlockForConfiguration()
} catch {
print("Could not set zoom level due to error: \(error)")
return false
}
captureSession.commitConfiguration()
// potential issue with background vs dispatchqueue ??
Task(priority: .background) {
captureSession.startRunning()
}
return true
}
}
// Issue here ???
extension CameraManager: AVCaptureVideoDataOutputSampleBufferDelegate {
func captureOutput(
_ output: AVCaptureOutput, didOutput sampleBuffer: CMSampleBuffer,
from connection: AVCaptureConnection
) {
guard let pixelBuffer = CMSampleBufferGetImageBuffer(sampleBuffer) else { return }
Task {
textRequest.recognitionLevel = .fast
textRequest.recognitionLanguages = [Locale.Language(identifier: "en-US")]
do {
let observations = try await textRequest.perform(on: pixelBuffer)
for observation in observations {
let recognizedText = observation.topCandidates(1).first
print("recognized text \(recognizedText)")
}
} catch {
print("Recognition error: \(error.localizedDescription)")
}
}
}
}
The results I get look like this ( full page of English from a any book)
recognized text Optional(RecognizedText(string: e bnUI W4, confidence: 0.5))
recognized text Optional(RecognizedText(string: ?'U, confidence: 0.3))
recognized text Optional(RecognizedText(string: traQt4, confidence: 0.3))
recognized text Optional(RecognizedText(string: li, confidence: 0.3))
recognized text Optional(RecognizedText(string: 15,1,#, confidence: 0.3))
recognized text Optional(RecognizedText(string: jllÈ, confidence: 0.3))
recognized text Optional(RecognizedText(string: vtrll, confidence: 0.3))
recognized text Optional(RecognizedText(string: 5,1,: 11, confidence: 0.5))
recognized text Optional(RecognizedText(string: 1141, confidence: 0.3))
recognized text Optional(RecognizedText(string: jllll ljiiilij41, confidence: 0.3))
recognized text Optional(RecognizedText(string: 2f4, confidence: 0.3))
recognized text Optional(RecognizedText(string: ktril, confidence: 0.3))
recognized text Optional(RecognizedText(string: ¥LLI, confidence: 0.3))
recognized text Optional(RecognizedText(string: 11[Itl,, confidence: 0.3))
recognized text Optional(RecognizedText(string: 'rtlÈ131, confidence: 0.3))
Even with ROI set to a specific rectangle Normalized to Vision, I get the same results with single characters returning gibberish.
Any help would be amazing thank you.
Am I using the buffer right ?
Am I using the new perform(on: CVPixelBuffer) right ?
Maybe I didn't set up my camera properly? I can provide code
