Java OCR 影象智慧字元識別技術[可識別中文]
阿新 • • 發佈：2019-02-04
http://www.open-open.com/lib/view/open1363156299203.html
國內最專業的OCR軟體只有2家，清華TH-OCR和漢王OCR，看了很多的OCR技術發現好多對英文與數字的支援都很好，可惜很多都不支援中文字元。 Asprise-OCR，Tesseract 3.0以前的版本，都不支援中文，其實我用了下Asprise-OCR算是速度比較的快了，可惜他鄙視中文，這個沒有辦法，正好這段時間知名的開源OCR 引擎Tesseract 3.0版本釋出了，他給我們帶來的好訊息就是支援中文，相關的下載專案網站是：http://code.google.com/p/tesseract-ocr
雖然速度不是很客觀可是畢竟人家開始支援中文也算是不錯的，一個英文的語言包大概是1.8M,中文簡體的語言包是39.5M,中文繁體的語言包是53M，這樣就知道為什麼識別中文慢的原因了.
package com.ocr; import java.awt.Graphics2D; import java.awt.color.ColorSpace; import java.awt.geom.AffineTransform; import java.awt.image.AffineTransformOp; import java.awt.image.BufferedImage; import java.awt.image.ColorConvertOp; import java.awt.image.ColorModel; import java.awt.image.MemoryImageSource; import java.awt.image.PixelGrabber; /** * * 影象過濾,增強OCR識別成功率 * */ public class ImageFilter { private BufferedImage image; private int iw, ih; private int[] pixels; public ImageFilter(BufferedImage image) { this.image = image; iw = image.getWidth(); ih = image.getHeight(); pixels = new int[iw * ih]; } /** 影象二值化 */ public BufferedImage changeGrey() { PixelGrabber pg = new PixelGrabber(image.getSource(), 0, 0, iw, ih, pixels, 0, iw); try { pg.grabPixels(); } catch (InterruptedException e) { e.printStackTrace(); } // 設定二值化的域值，預設值為100 int grey = 100; // 對影象進行二值化處理，Alpha值保持不變 ColorModel cm = ColorModel.getRGBdefault(); for (int i = 0; i < iw * ih; i++) { int red, green, blue; int alpha = cm.getAlpha(pixels[i]); if (cm.getRed(pixels[i]) > grey) { red = 255; } else { red = 0; } if (cm.getGreen(pixels[i]) > grey) { green = 255; } else { green = 0; } if (cm.getBlue(pixels[i]) > grey) { blue = 255; } else { blue = 0; } pixels[i] = alpha << 24 | red << 16 | green << 8 | blue; } // 將陣列中的象素產生一個影象 return ImageIOHelper.imageProducerToBufferedImage(new MemoryImageSource(iw, ih, pixels, 0, iw)); } /** 提升清晰度,進行銳化 */ public BufferedImage sharp() { PixelGrabber pg = new PixelGrabber(image.getSource(), 0, 0, iw, ih, pixels, 0, iw); try { pg.grabPixels(); } catch (InterruptedException e) { e.printStackTrace(); } // 象素的中間變數 int tempPixels[] = new int[iw * ih]; for (int i = 0; i < iw * ih; i++) { tempPixels[i] = pixels[i]; } // 對影象進行尖銳化處理，Alpha值保持不變 ColorModel cm = ColorModel.getRGBdefault(); for (int i = 1; i < ih - 1; i++) { for (int j = 1; j < iw - 1; j++) { int alpha = cm.getAlpha(pixels[i * iw + j]); // 對影象進行尖銳化 int red6 = cm.getRed(pixels[i * iw + j + 1]); int red5 = cm.getRed(pixels[i * iw + j]); int red8 = cm.getRed(pixels[(i + 1) * iw + j]); int sharpRed = Math.abs(red6 - red5) + Math.abs(red8 - red5); int green5 = cm.getGreen(pixels[i * iw + j]); int green6 = cm.getGreen(pixels[i * iw + j + 1]); int green8 = cm.getGreen(pixels[(i + 1) * iw + j]); int sharpGreen = Math.abs(green6 - green5) + Math.abs(green8 - green5); int blue5 = cm.getBlue(pixels[i * iw + j]); int blue6 = cm.getBlue(pixels[i * iw + j + 1]); int blue8 = cm.getBlue(pixels[(i + 1) * iw + j]); int sharpBlue = Math.abs(blue6 - blue5) + Math.abs(blue8 - blue5); if (sharpRed > 255) { sharpRed = 255; } if (sharpGreen > 255) { sharpGreen = 255; } if (sharpBlue > 255) { sharpBlue = 255; } tempPixels[i * iw + j] = alpha << 24 | sharpRed << 16 | sharpGreen << 8 | sharpBlue; } } // 將陣列中的象素產生一個影象 return ImageIOHelper.imageProducerToBufferedImage(new MemoryImageSource(iw, ih, tempPixels, 0, iw)); } /** 中值濾波 */ public BufferedImage median() { PixelGrabber pg = new PixelGrabber(image.getSource(), 0, 0, iw, ih, pixels, 0, iw); try { pg.grabPixels(); } catch (InterruptedException e) { e.printStackTrace(); } // 對影象進行中值濾波，Alpha值保持不變 ColorModel cm = ColorModel.getRGBdefault(); for (int i = 1; i < ih - 1; i++) { for (int j = 1; j < iw - 1; j++) { int red, green, blue; int alpha = cm.getAlpha(pixels[i * iw + j]); // int red2 = cm.getRed(pixels[(i - 1) * iw + j]); int red4 = cm.getRed(pixels[i * iw + j - 1]); int red5 = cm.getRed(pixels[i * iw + j]); int red6 = cm.getRed(pixels[i * iw + j + 1]); // int red8 = cm.getRed(pixels[(i + 1) * iw + j]); // 水平方向進行中值濾波 if (red4 >= red5) { if (red5 >= red6) { red = red5; } else { if (red4 >= red6) { red = red6; } else { red = red4; } } } else { if (red4 > red6) { red = red4; } else { if (red5 > red6) { red = red6; } else { red = red5; } } } // int green2 = cm.getGreen(pixels[(i - 1) * iw + j]); int green4 = cm.getGreen(pixels[i * iw + j - 1]); int green5 = cm.getGreen(pixels[i * iw + j]); int green6 = cm.getGreen(pixels[i * iw + j + 1]); // int green8 = cm.getGreen(pixels[(i + 1) * iw + j]); // 水平方向進行中值濾波 if (green4 >= green5) { if (green5 >= green6) { green = green5; } else { if (green4 >= green6) { green = green6; } else { green = green4; } } } else { if (green4 > green6) { green = green4; } else { if (green5 > green6) { green = green6; } else { green = green5; } } } // int blue2 = cm.getBlue(pixels[(i - 1) * iw + j]); int blue4 = cm.getBlue(pixels[i * iw + j - 1]); int blue5 = cm.getBlue(pixels[i * iw + j]); int blue6 = cm.getBlue(pixels[i * iw + j + 1]); // int blue8 = cm.getBlue(pixels[(i + 1) * iw + j]); // 水平方向進行中值濾波 if (blue4 >= blue5) { if (blue5 >= blue6) { blue = blue5; } else { if (blue4 >= blue6) { blue = blue6; } else { blue = blue4; } } } else { if (blue4 > blue6) { blue = blue4; } else { if (blue5 > blue6) { blue = blue6; } else { blue = blue5; } } } pixels[i * iw + j] = alpha << 24 | red << 16 | green << 8 | blue; } } // 將陣列中的象素產生一個影象 return ImageIOHelper.imageProducerToBufferedImage(new MemoryImageSource(iw, ih, pixels, 0, iw)); } /** 線性灰度變換 */ public BufferedImage lineGrey() { PixelGrabber pg = new PixelGrabber(image.getSource(), 0, 0, iw, ih, pixels, 0, iw); try { pg.grabPixels(); } catch (InterruptedException e) { e.printStackTrace(); } // 對影象進行進行線性拉伸，Alpha值保持不變 ColorModel cm = ColorModel.getRGBdefault(); for (int i = 0; i < iw * ih; i++) { int alpha = cm.getAlpha(pixels[i]); int red = cm.getRed(pixels[i]); int green = cm.getGreen(pixels[i]); int blue = cm.getBlue(pixels[i]); // 增加了影象的亮度 red = (int) (1.1 * red + 30); green = (int) (1.1 * green + 30); blue = (int) (1.1 * blue + 30); if (red >= 255) { red = 255; } if (green >= 255) { green = 255; } if (blue >= 255) { blue = 255; } pixels[i] = alpha << 24 | red << 16 | green << 8 | blue; } // 將陣列中的象素產生一個影象 return ImageIOHelper.imageProducerToBufferedImage(new MemoryImageSource(iw, ih, pixels, 0, iw)); } /** 轉換為黑白灰度圖 */ public BufferedImage grayFilter() { ColorSpace cs = ColorSpace.getInstance(ColorSpace.CS_GRAY); ColorConvertOp op = new ColorConvertOp(cs, null); return op.filter(image, null); } /** 平滑縮放 */ public BufferedImage scaling(double s) { AffineTransform tx = new AffineTransform(); tx.scale(s, s); AffineTransformOp op = new AffineTransformOp(tx, AffineTransformOp.TYPE_BILINEAR); return op.filter(image, null); } public BufferedImage scale(Float s) { int srcW = image.getWidth(); int srcH = image.getHeight(); int newW = Math.round(srcW * s); int newH = Math.round(srcH * s); // 先做水平方向上的伸縮變換 BufferedImage tmp=new BufferedImage(newW, newH, image.getType()); Graphics2D g= tmp.createGraphics(); for (int x = 0; x < newW; x++) { g.setClip(x, 0, 1, srcH); // 按比例放縮 g.drawImage(image, x - x * srcW / newW, 0, null); } // 再做垂直方向上的伸縮變換 BufferedImage dst = new BufferedImage(newW, newH, image.getType()); g = dst.createGraphics(); for (int y = 0; y < newH; y++) { g.setClip(0, y, newW, 1); // 按比例放縮 g.drawImage(tmp, 0, y - y * srcH / newH, null); } return dst; } } package com.ocr; import java.awt.Graphics2D; import java.awt.Image; import java.awt.Toolkit; import java.awt.image.BufferedImage; import java.awt.image.DataBufferByte; import java.awt.image.ImageProducer; import java.awt.image.WritableRaster; 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.ImageInputStream; import javax.imageio.stream.ImageOutputStream; import javax.swing.JOptionPane; import com.sun.media.imageio.plugins.tiff.TIFFImageWriteParam; public class ImageIOHelper { public ImageIOHelper() { } public static File createImage(File imageFile, String imageFormat) { File tempFile = null; try { Iterator readers = ImageIO.getImageReadersByFormatName(imageFormat); ImageReader reader = readers.next(); ImageInputStream iis = ImageIO.createImageInputStream(imageFile); reader.setInput(iis); // Read the stream metadata IIOMetadata streamMetadata = reader.getStreamMetadata(); // Set up the writeParam TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); // Get tif writer and set output to file Iterator writers = ImageIO.getImageWritersByFormatName("tiff"); ImageWriter writer = writers.next(); BufferedImage bi = reader.read(0); IIOImage image = new IIOImage(bi, null, reader.getImageMetadata(0)); tempFile = tempImageFile(imageFile); ImageOutputStream ios = ImageIO.createImageOutputStream(tempFile); writer.setOutput(ios); writer.write(streamMetadata, image, tiffWriteParam); ios.close(); writer.dispose(); reader.dispose(); } catch (Exception exc) { exc.printStackTrace(); } return tempFile; } public static File createImage(BufferedImage bi) { File tempFile = null; try { tempFile = File.createTempFile("tempImageFile", ".tif"); tempFile.deleteOnExit(); TIFFImageWriteParam tiffWriteParam = new TIFFImageWriteParam(Locale.US); tiffWriteParam.setCompressionMode(ImageWriteParam.MODE_DISABLED); // Get tif writer and set output to file Iterator writers = ImageIO.getImageWritersByFormatName("tiff"); ImageWriter writer = writers.next(); IIOImage image = new IIOImage(bi, null, null); tempFile = tempImageFile(tempFile); ImageOutputStream ios = ImageIO.createImageOutputStream(tempFile); writer.setOutput(ios); writer.write(null, image, tiffWriteParam); ios.close(); writer.dispose(); } catch (Exception exc) { exc.printStackTrace(); } return tempFile; } public static File tempImageFile(File imageFile) { String path = imageFile.getPath(); StringBuffer strB = new StringBuffer(path); strB.insert(path.lastIndexOf('.'), 0); return new File(strB.toString().replaceFirst("(?<=//.)(//w+)$", "tif")); } public static BufferedImage getImage(File imageFile) { BufferedImage al = null; try { String imageFileName = imageFile.getName(); String imageFormat = imageFileName.substring(imageFileName.lastIndexOf('.') + 1); Iterator readers = ImageIO.getImageReadersByFormatName(imageFormat); ImageReader reader = readers.next(); if (reader == null) { JOptionPane.showConfirmDialog(null, "Need to install JAI Image I/O package./nhttps://jai-imageio.dev.java.net"); return null; } ImageInputStream iis = ImageIO.createImageInputStream(imageFile); reader.setInput(iis); al = reader.read(0); reader.dispose(); } catch (IOException ioe) { System.err.println(ioe.getMessage()); } catch (Exception e) { System.err.println(e.getMessage()); } return al; } public static BufferedImage imageToBufferedImage(Image image) { BufferedImage bufferedImage = new BufferedImage(image.getWidth(null), image.getHeight(null), BufferedImage.TYPE_INT_RGB); Graphics2D g = bufferedImage.createGraphics(); g.drawImage(image, 0, 0, null); return bufferedImage; } public static BufferedImage imageProducerToBufferedImage(ImageProducer imageProducer) { return imageToBufferedImage(Toolkit.getDefaultToolkit().createImage(imageProducer)); } public static byte[] image_byte_data(BufferedImage image) { WritableRaster raster = image.getRaster(); DataBufferByte buffer = (DataBufferByte) raster.getDataBuffer(); return buffer.getData(); } } package com.ocr; import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.InputStreamReader; import java.util.ArrayList; import java.util.List; import org.jdesktop.swingx.util.OS; public class OCR { private final String LANG_OPTION = "-l"; private final String EOL = System.getProperty("line.separator"); private String tessPath = new File("tesseract").getAbsolutePath(); //private String tessPath="C://Program Files (x86)//Tesseract-OCR//"; public String recognizeText(File imageFile, String imageFormat) throws Exception { File tempImage = ImageIOHelper.createImage(imageFile, imageFormat); File outputFile = new File(imageFile.getParentFile(), "output"); StringBuffer strB = new StringBuffer(); List cmd = new ArrayList(); if (OS.isWindowsXP()) { cmd.add(tessPath + "//tesseract"); //cmd.add(tessPath + "//Tesseract-OCR"); } else if (OS.isLinux()) { cmd.add("tesseract"); } else { //cmd.add(tessPath + "//Tesseract-OCR") cmd.add(tessPath + "//tesseract"); } cmd.add(""); cmd.add(outputFile.getName()); cmd.add(LANG_OPTION); cmd.add("chi_sim"); cmd.add("eng"); ProcessBuilder pb = new ProcessBuilder(); pb.directory(imageFile.getParentFile()); cmd.set(1, tempImage.getName()); pb.command(cmd); pb.redirectErrorStream(true); Process process = pb.start(); //tesseract.exe 1.jpg 1 -l chi_sim int w = process.waitFor(); // delete temp working files tempImage.delete(); 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 recognize 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(); } } package com.ocr; import java.io.File; public class Test { /** * @param args */ public static void main(String[] args) { // TODO Auto-generated method stub OCR ocr=new OCR(); try { String maybe = new OCR().recognizeText(new File("E://temp//222.jpg"), "jpg"); System.out.println(maybe); } catch (Exception e) { // TODO Auto-generated catch block e.printStackTrace(); } } }
java 目錄結構如上圖
效果圖：
解析出來的效果
