OpenCV Java从场景

时间:2017-05-14 01:11:32

标签: java opencv ocr tesseract

我已经成功检测到了边界框,现在我想删除图像中的其他所有内容并保留边界框的内容以提高tesseract的准确性,下面是我已经完成和需要的图​​像表示(I希望二进制图像只包含字母,所有其他要删除的对象):

I want the binary images to only contain the letters, all the other objects to be removed

和我的代码:

 public static ProcessedFrame preProcessImage(Mat image){
    originalFrame = image.clone();
    roiColor = image.clone();
    Imgproc.cvtColor(image, image, Imgproc.COLOR_BGR2GRAY, 0);
    originalFrameGrayScale = image.clone();
    Mat morph = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(9, 9));
    Imgproc.morphologyEx(image, image, Imgproc.MORPH_TOPHAT, morph);
    Imgproc.Sobel(image, image, -1, 2, 0);
    Imgproc.GaussianBlur(image, image, new Size(5,5), 3,3);
    Imgproc.morphologyEx(image, image, Imgproc.MORPH_CLOSE, morph);
    Imgproc.threshold(image, image, 200, 255, Imgproc.THRESH_OTSU);
    Vector<Rect> rectangles = detectionContour(image);
    Mat roi = originalFrameGrayScale.clone();
    if(!rectangles.isEmpty()){
    roi = originalFrameGrayScale.submat(rectangles.get(0));
    roiBlack = roi.clone();
    roiColor = roiColor.submat(rectangles.get(0));
      Imgproc.rectangle(originalFrame, rectangles.get(0).br(), rectangles.get(0).tl(), new Scalar(0,0,255), 2);
    }
   Imgproc.medianBlur(roi, roi, 3); 
   Imgproc.adaptiveThreshold(roi, roi, 225, Imgproc.ADAPTIVE_THRESH_GAUSSIAN_C, Imgproc.THRESH_BINARY, 15, 3);
   Imgproc.medianBlur(roi, roi, 3);
   Imgproc.medianBlur(roi, roi, 3); 
   Imgproc.adaptiveThreshold(roi, roi, 225, Imgproc.ADAPTIVE_THRESH_GAUSSIAN_C, Imgproc.THRESH_BINARY, 15, 3);
   Imgproc.medianBlur(roi, roi, 3);
   roiBinarize = roi.clone();
   Mat erode = Imgproc.getStructuringElement(Imgproc.MORPH_RECT, new Size(3, 3));
   Mat dilate = Imgproc.getStructuringElement(Imgproc.MORPH_RECT,new Size(3, 3));
   Imgproc.morphologyEx(roi, roi, Imgproc.MORPH_CLOSE, dilate);
   Imgproc.morphologyEx(roi, roi, Imgproc.MORPH_CLOSE, erode);
   Vector<Rect> letters = detectionPlateCharacterContour(roi);
   doTesseractOCR(letters, roiBinarize);
    return  new ProcessedFrame(originalFrame, roiColor, roiBinarize, roi);

}






private static void doTesseractOCR(Vector<Rect> letters, Mat plate){
    Tesseract instance = new Tesseract(); //
    instance.setLanguage(LANGUAGE);
    String resultPlate = "AAA0000";
    for(int i= 0; i < letters.size(); i++){

     BufferedImage letter = OpenCvUtils.Mat2bufferedImage(plate.submat(letters.get(i)));
        try {
        String result = instance.doOCR(letter);
        String character = result.replace("\n", "");
        resultPlate = new StringBuilder(resultPlate).replace(i ,i+1, character).toString();
        } catch (TesseractException e) {
        System.err.println(e.getMessage());
        }

        System.out.println("Tesseract output: "+resultPlate);
    }

     try {
        String result = instance.doOCR(OpenCvUtils.Mat2bufferedImage(roiBinarize));
        System.out.println("Tesseract output2: "+result.replace("\n", ""));
         } catch (TesseractException e) {
        System.err.println(e.getMessage());
        }
}





 private static Vector<Rect> detectionPlateCharacterContour(Mat roi) {
    Mat contHierarchy = new Mat();
    Mat imageMat = roi.clone();
    Rect rect = null;
    List<MatOfPoint> contours = new ArrayList<>();
    Imgproc.findContours(imageMat, contours, contHierarchy, Imgproc.RETR_CCOMP, Imgproc.CHAIN_APPROX_SIMPLE);
    Vector<Rect> rect_array = new Vector<>();

    for (int i = 0; i < contours.size(); i++) {
        rect = Imgproc.boundingRect(contours.get(i));
        double ratio = 0;

               if(rect.height > rect.width){
            ratio = rect.height/rect.width;

            }else{
                ratio = rect.width/rect.height;

            }
         Logger.printMessage("Ratio of letter: "+ratio);
      double contourarea = Imgproc.contourArea(contours.get(i));
         if (contourarea >= 160 && contourarea <= 1000 && ( ratio >= 1 && ratio <= 2)) {
         Imgproc.rectangle(roiColor, rect.br(), rect.tl(), new Scalar(10,50,255));
           rect_array.add(rect);
         }
    }


    contHierarchy.release();
    return rect_array;
}




 private static Vector<Rect> detectionContour(Mat outmat) {
    Mat contHierarchy = new Mat();
    Mat imageMat = outmat.clone();

    List<MatOfPoint> contours = new ArrayList<>();

    Imgproc.findContours(imageMat, contours, contHierarchy, Imgproc.RETR_EXTERNAL, Imgproc.CHAIN_APPROX_NONE);

    Vector<Rect> rect_array = new Vector<>();
    for (int i = 0; i < contours.size(); i++) {
        Rect rect = Imgproc.boundingRect(contours.get(i));

        Mat contour = contours.get(i);
        double contourarea = Imgproc.contourArea(contour);

            double ratio = 0;
            int radius = 0;
            if(rect.height > rect.width){
            ratio = rect.height/rect.width;
            radius = rect.height/2;
            }else{
                ratio = rect.width/rect.height;
                radius = rect.width/2;
            }
        if (contourarea >= 2000 && contourarea <= 10000 && ( ratio == 1 || ratio == 2)) {   
            Logger.printMessage("Rectangle ratio: "+ratio);
            MatOfPoint2f mat2f = new MatOfPoint2f();
            contours.get(i).convertTo(mat2f, CvType.CV_32FC2);
            RotatedRect rotatedRect = Imgproc.minAreaRect( mat2f );
            double rotationAngle = rotatedRect.angle;
            if(rotatedRect.angle > 0)
                rotationAngle = 90 - rotatedRect.angle;
            else
               rotationAngle = rotatedRect.angle; 
            Logger.printMessage("Rotation is: "+(rotationAngle));
            rect = enlargeROI(originalFrame, rect, 10);
            rect_array.add(rect);
        }
    }


    contHierarchy.release();
    return rect_array;
}





private Vector<Rect> detectionContours(Mat outmat) {
    Mat contHierarchy = new Mat();
    Mat imageMat = outmat.clone();
    Rect contourRect = null;
    List<MatOfPoint> contours = new ArrayList<>();
    Imgproc.findContours(imageMat, contours, contHierarchy, Imgproc.RETR_LIST, Imgproc.CHAIN_APPROX_SIMPLE);
    Vector<Rect> rect_array = new Vector<>();
    for (int i = 0; i < contours.size(); i++) {
        Mat contour = contours.get(i);
        double contourarea = Imgproc.contourArea(contour);
        if (contourarea > minBlob && contourarea < maxBlob) {
            contourRect = Imgproc.boundingRect(contours.get(i));
            rect_array.add(contourRect);
        }
    }


    contHierarchy.release();
    return rect_array;
}

当我运行此代码打印出每个矩形的质心时,我发现了这一点  2 x:18.0 y:111.0 2 x:42.0 y:109.0 7 x:65.0 y:108.0 0x:89.0 y:108.0 A x:29.0 y:61.0 C x:52.0 y:58.0 P x:77.0 y:58.0

1 个答案:

答案 0 :(得分:0)

看起来你只需要在你的字母边框上做一些预处理,在将它们送到Tesseract之前做它可能是有意义的,尽管它并不是绝对必要的。让我们首先用轮廓索引注释我们的样本图像,并将它们的属性制成表格。

Annotated LP

contour | bbox centroid | recognised
index   |   x   |   y   | symbol
--------+-------+-------+-----------
0       |  18.0 | 111.0 |   2
1       |  42.0 | 109.0 |   2
2       |  65.0 | 108.0 |   7
3       |  89.0 | 108.0 |   0
4       |  29.0 |  61.0 |   A
5       |  52.0 |  58.0 |   C
6       |  77.0 |  58.0 |   P

当某人阅读此牌照时,他们从最上面的一行符号开始,并从左到右阅读符号。在他们到达最右边的符号后,他们移动到下一行,并再次从左到右。因此,我们应该将一个符号(或代表它们的边界框)组织在一个允许我们轻松完成的结构中。

我们可以使用Vector<Rect>来表示每一行符号。由于总有两行符号,我们需要这个向量的两个实例 - 让我们将它们称为 row0 row1

第一项任务是将符号的边界框分类为两组,并在此基础上将它们添加到适当的行向量中。一个简单的方法可能是这样的:

  • 计算符号质心的y坐标的平均值。在我们的示例中,它大约是mean_y=87.5
  • 对于每个检测到的符号:
    • 如果符号质心的y坐标小于mean_y,请将符号添加到 row0
    • 否则,请将符号添加到 row1

当我们对我们的符号样本集执行此算法时,我们会看到

     | contained
row  | symbol ids
-----+--------------
row0 |  4, 5, 6
row1 |  0, 1, 2, 3

如果这种简单的方法不够充分,您可以尝试一些更高级的means of clustering

第二项任务是对每一行进行排序,使符号从左向右:

  • 每行:
    • 按行中心的x坐标
    • 按升序对行元素进行排序

我的Java非常生疏,但您可以使用comparator执行此操作。您可以参考this SO answer以获取有关如何使用Java对集合进行排序的更多详细信息。

在我们的示例中,每行中的元素已经按顺序排列,所以没有任何事情要做......

     | contained
row  | symbol ids
-----+--------------
row0 |  4, 5, 6
row1 |  0, 1, 2, 3

现在我们可以

  • 每行:
    • 对于行中的每个符号
      • 使用Tesseract进行处理
      • 根据需要处理结果(例如打印)

在我们的示例中,我们得到

ACP
2270