【Android代码】绘本翻页时通过AI识别,自动通过手机/pad朗读绘本
核心功能:
- 打开摄像头(可支持外接摄像头)
- 检测翻页(后续考虑添加图像差异算法)
- 拍照后用 识图
- 自动用 TextToSpeech 朗读文字内容
📌 说明:
-
使用了 CameraX(Android Jetpack)处理摄像头输入
-
使用 ML Kit 做文字识别
-
使用 TextToSpeech 实现朗读
// Project: StoryBookReaderApp
// MainActivity.java — Android Studio 项目主类package com.example.storybookreaderapp;import android.Manifest;
import android.content.pm.PackageManager;
import android.os.Bundle;
import android.speech.tts.TextToSpeech;
import android.util.Log;
import android.view.SurfaceView;
import android.widget.Toast;import androidx.annotation.NonNull;
import androidx.appcompat.app.AppCompatActivity;
import androidx.camera.core.CameraSelector;
import androidx.camera.core.ImageAnalysis;
import androidx.camera.core.ImageCapture;
import androidx.camera.core.ImageCaptureException;
import androidx.camera.core.ImageProxy;
import androidx.camera.lifecycle.ProcessCameraProvider;
import androidx.core.app.ActivityCompat;
import androidx.core.content.ContextCompat;import com.google.common.util.concurrent.ListenableFuture;
import com.google.mlkit.vision.common.InputImage;
import com.google.mlkit.vision.text.TextRecognition;
import com.google.mlkit.vision.text.TextRecognizer;import java.util.Locale;
import java.util.concurrent.ExecutorService;
import java.util.concurrent.Executors;public class MainActivity extends AppCompatActivity {private static final int REQUEST_CODE_PERMISSIONS = 10;private static final String[] REQUIRED_PERMISSIONS = new String[]{Manifest.permission.CAMERA};private ExecutorService cameraExecutor;private ImageCapture imageCapture;private TextToSpeech tts;@Overrideprotected void onCreate(Bundle savedInstanceState) {super.onCreate(savedInstanceState);SurfaceView view = new SurfaceView(this);setContentView(view);if (allPermissionsGranted()) {startCamera();} else {ActivityCompat.requestPermissions(this, REQUIRED_PERMISSIONS, REQUEST_CODE_PERMISSIONS);}cameraExecutor = Executors.newSingleThreadExecutor();tts = new TextToSpeech(this, status -> {if (status != TextToSpeech.ERROR) {tts.setLanguage(Locale.US);}});}private boolean allPermissionsGranted() {for (String permission : REQUIRED_PERMISSIONS) {if (ContextCompat.checkSelfPermission(this, permission) != PackageManager.PERMISSION_GRANTED) {return false;}}return true;}private void startCamera() {ListenableFuture<ProcessCameraProvider> cameraProviderFuture = ProcessCameraProvider.getInstance(this);cameraProviderFuture.addListener(() -> {try {ProcessCameraProvider cameraProvider = cameraProviderFuture.get();imageCapture = new ImageCapture.Builder().build();ImageAnalysis imageAnalysis = new ImageAnalysis.Builder().build();imageAnalysis.setAnalyzer(cameraExecutor, image -> {detectPageTurn(image);image.close();});CameraSelector cameraSelector = CameraSelector.DEFAULT_BACK_CAMERA;cameraProvider.unbindAll();cameraProvider.bindToLifecycle(this, cameraSelector, imageCapture, imageAnalysis);} catch (Exception e) {Log.e("CameraX", "Binding failed", e);}}, ContextCompat.getMainExecutor(this));}private void detectPageTurn(ImageProxy image) {takePhotoAndRead();}private void takePhotoAndRead() {imageCapture.takePicture(ContextCompat.getMainExecutor(this), new ImageCapture.OnImageCapturedCallback() {@Overridepublic void onCaptureSuccess(@NonNull ImageProxy image) {InputImage inputImage = InputImage.fromMediaImage(image.getImage(), image.getImageInfo().getRotationDegrees());TextRecognizer recognizer = TextRecognition.getClient();recognizer.process(inputImage).addOnSuccessListener(result -> {String text = result.getText();tts.speak(text, TextToSpeech.QUEUE_FLUSH, null, null);}).addOnFailureListener(e -> Toast.makeText(MainActivity.this, "Text recognition failed", Toast.LENGTH_SHORT).show());image.close();}@Overridepublic void onError(@NonNull ImageCaptureException exception) {Log.e("CameraX", "Capture failed", exception);}});}@Overrideprotected void onDestroy() {if (tts != null) {tts.stop();tts.shutdown();}cameraExecutor.shutdown();super.onDestroy();}@Overridepublic void onRequestPermissionsResult(int requestCode, @NonNull String[] permissions, @NonNull int[] grantResults) {if (requestCode == REQUEST_CODE_PERMISSIONS) {if (allPermissionsGranted()) {startCamera();} else {Toast.makeText(this, "Permissions not granted", Toast.LENGTH_SHORT).show();finish();}}}
} // End of class