java從圖片中識別文字
阿新 • • 發佈:2019-01-04
package com.dream.common; import java.awt.image.BufferedImage; import java.io.File; import java.io.IOException; import java.util.Iterator; import java.util.Locale; import javax.imageio.IIOImage; import javax.imageio.ImageIO; import javax.imageio.ImageReader; import javax.imageio.ImageWriteParam; import javax.imageio.ImageWriter; import javax.imageio.metadata.IIOMetadata; import javax.imageio.stream.FileImageInputStream; import javax.imageio.stream.ImageInputStream; import javax.imageio.stream.ImageOutputStream; import com.github.jaiimageio.plugins.tiff.TIFFImageWriteParam; /** * 識別圖片中的文字 * * @author zlj * */ public class ImageIOHelper { /** * 建立臨時圖片檔案 * * @param imageFile * @return * @throws IOException */ public File createImage(File imageFile) throws IOException { Iterator<ImageReader> readers = ImageIO.getImageReaders(new FileImageInputStream(imageFile)); ImageReader reader = readers.next(); ImageInputStream iis = ImageIO.createImageInputStream(imageFile); reader.setInput(iis); IIOMetadata streamMetadata = reader.getStreamMetadata(); TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.CHINESE); tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); Iterator<ImageWriter> writers = ImageIO.getImageWritersByFormatName("tiff"); ImageWriter writer = writers.next(); BufferedImage bi = reader.read(0); IIOImage image = new IIOImage(bi, null, reader.getImageMetadata(0)); File tempFile = tempImageFile(imageFile); ImageOutputStream ios = ImageIO.createImageOutputStream(tempFile); writer.setOutput(ios); writer.write(streamMetadata, image, tiffWriteParam); ios.close(); iis.close(); writer.dispose(); reader.dispose(); return tempFile; } /** * 新增字尾 tempfile * * @param imageFile * @return * @throws IOException */ private File tempImageFile(File imageFile) throws IOException { String path = imageFile.getPath(); StringBuffer strB = new StringBuffer(path); strB.insert(path.lastIndexOf('.'), "_text_recognize_temp"); String s = strB.toString().replaceFirst("(?<=//.)(//w+)$", "tif"); Runtime.getRuntime().exec("attrib " + "\"" + s + "\"" + " +H"); // 設定檔案隱藏 return new File(strB.toString()); } }package com.dream.common; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.IOException; import java.io.InputStreamReader; import java.util.ArrayList; import java.util.List; import org.jdesktop.swingx.util.OS; /** * 從圖片中識別文字 * @author zlj * */ public class OCRUtil { private final String LANG_OPTION = "-l"; // 英文字母小寫l,並非數字1 private final String EOL = System.getProperty("line.separator"); private String tessPath = "C://Program Files (x86)//Tesseract-OCR";// ocr預設安裝路徑 private String transname = "chi_sim";// 預設中文語言包,識別中文 /** * 從圖片中識別文字 * @param imageFile * @param imageFormat * @return text recognized in image * @throws Exception */ public String recognizeText(File imageFile) throws Exception { File tempImage = new ImageIOHelper().createImage(imageFile); return ocrImages(tempImage, imageFile); } /** * 識別圖片中的文字 * @param tempImage * @param imageFile * @return * @throws IOException * @throws InterruptedException */ private String ocrImages(File tempImage, File imageFile) throws IOException, InterruptedException { File outputFile = new File(imageFile.getParentFile(), "output"); Runtime.getRuntime().exec("attrib " + "\"" + outputFile.getAbsolutePath() + "\"" + " +H"); // 設定檔案隱藏 StringBuffer strB = new StringBuffer(); List<String> cmd = new ArrayList<String>(); if (OS.isWindowsXP()) { cmd.add(tessPath + "//tesseract"); } else if (OS.isLinux()) { cmd.add("tesseract"); } else { cmd.add(tessPath + "//tesseract"); } cmd.add(""); cmd.add(outputFile.getName()); cmd.add(LANG_OPTION); cmd.add(transname); ProcessBuilder pb = new ProcessBuilder(); pb.directory(imageFile.getParentFile()); cmd.set(1, tempImage.getName()); pb.command(cmd); pb.redirectErrorStream(true); Process process = pb.start(); int w = process.waitFor(); tempImage.delete();// 刪除臨時正在工作檔案 if (w == 0) { BufferedReader in = new BufferedReader( new InputStreamReader(new FileInputStream(outputFile.getAbsolutePath() + ".txt"), "UTF-8")); String str; while ((str = in.readLine()) != null) { strB.append(str).append(EOL); } in.close(); } else { String msg; switch (w) { case 1: msg = "Errors accessing files.There may be spaces in your image's filename."; break; case 29: msg = "Cannot recongnize the image or its selected region."; break; case 31: msg = "Unsupported image format."; break; default: msg = "Errors occurred."; } tempImage.delete(); throw new RuntimeException(msg); } new File(outputFile.getAbsolutePath() + ".txt").delete(); return strB.toString(); } public static void main(String[] args) throws Exception { System.out.println("begin"); String path = "F://test1.png"; String valCode = new OCRUtil().recognizeText(new File(path)); System.out.println(valCode); System.out.println("end"); } }