opencv+tesseract实现验证码识别的示例

tesseract.exe 01.png output.txt -l eng

rem 执行改批处理前先要目录下创建font_properties文件  
  
echo Run Tesseract for Training..  
tesseract.exe jtbnum.font.exp0.tif jtbnum.font.exp0 nobatch box.train  
  
echo Compute the Character Set..  
unicharset_extractor.exe jtbnum.font.exp0.box  
mftraining -F font_properties -U unicharset -O jtbnum.unicharset jtbnum.font.exp0.tr  
  
echo Clustering..  
cntraining.exe jtbnum.font.exp0.tr  
  
echo Rename Files..  
 
del jtbnum.nORMproto
rename normproto jtbnum.normproto
 
del jtbnum.inttemp
rename inttemp jtbnum.inttemp
 
del jtbnum.pffmtable
rename pffmtable jtbnum.pffmtable
 
del jtbnum.shapetable
rename shapetable jtbnum.shapetable
  
echo Create Tessdata..  
combine_tessdata.exe jtbnum. 
 
pause

tesseract.exe 01.png output.txt -l jtbnum

if(!hasLoad){
            System.load(opencvPath+"/build/java/x64/opencv_java440.dll");
            hasLoad = true;
        }
 
        byte [] bytes = Base64Utils.decodeFromString(base64);
        String path = savePath+"/"+System.currentTimeMillis()+".png";
        try {
            OutputStream outputStream = new FileOutputStream(new File(path));
            outputStream.write(bytes);
            outputStream.flush();
            outputStream.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
 
        Mat image0 = ImGCodecs.imread(path);
        Mat image1 = new Mat();
        //灰度处理
        Imgproc.cvtColor(image0, image1, Imgproc.COLOR_BGR2GRAY);
        Imgproc.adaptiveThreshold(image1,image1,255,Imgproc.ADAPTIVE_THRESH_MEAN_C,Imgproc.THRESH_BINARY,11, 2);
        Core.bitwise_not(image1,image1);
        Mat kernel = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(2, 2), new Point(-1, -1));
        Mat temp = new Mat();
        Imgproc.erode(image1, temp, kernel);
        Imgproc.dilate(temp, temp, kernel);
        String newPath = path.substring(0,path.lastIndexOf(".")) +"_1.png";
        Imgcodecs.imwrite(newPath,temp);

tesseract.exe 01.png output.txt -l jtbnum