SwiftUI - 如何识别单词并在 Vision 中获取位置

Question

下面的代码只能识别单词，但我不知道如何获取位置。 我可以获取文本，但不能获取边界框。

来自：https://medium.com/@jakir/text-recognition-or-ocr-using-vision-framework-ios-swiftui-b9c5df36ec32

import SwiftUI
import Vision

struct ContentView: View {
    
    @State var recognizedText = ""
    
    var body: some View {
        VStack {
            Text("OCR using Vission")
                .font(.title)
            
            Image("quote")
                .resizable()
                .scaledToFit()
            
            Button("Recognize Text"){
                ocr()
            }
            
            TextEditor(text: $recognizedText)
        }
        .padding()
        
    }
    
    func ocr() {
        let image = UIImage(named: "quote")
        
        if let cgImage = image?.cgImage {
            
            // Request handler
            let handler = VNImageRequestHandler(cgImage: cgImage)
            
            let recognizeRequest = VNRecognizeTextRequest { (request, error) in
                
                // Parse the results as text
                guard let result = request.results as? [VNRecognizedTextObservation] else {
                    return
                }
                
                // Extract the data
                let stringArray = result.compactMap { result in
                    result.topCandidates(1).first?.string
                }
                
                // Update the UI
                DispatchQueue.main.async {
                    recognizedText = stringArray.joined(separator: "\n")
                }
            }
            
            // Process the request
            recognizeRequest.recognitionLevel = .accurate
            do {
                try handler.perform([recognizeRequest])
            } catch {
                print(error)
            }
            
        }
    }
}

我访问了很多网站但没有找到结果

Answer 1

这个答案告诉我们如何识别句子边界框而不是单词 在 Vision Framework - SwiftUI 中使用 VNRecognizeTextRequest 的 .accurate 提取字级边界框