【发布时间】：2017-10-13 01:20:59
【问题描述】：
我已成功检测到边界框，现在我想删除图像中的所有其他内容，只保留边界框的内容以提高 tesseract 精度，下面是我所做和需要的图像表示（我希望二进制图像只包含字母，所有其他要删除的对象）：
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;
}
当我运行这段代码打印出每个矩形的质心时，我发现 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 一个 x: 29.0 y: 61.0 C x: 52.0 y: 58.0 P x: 77.0 y: 58.0
【问题讨论】：
-
OpenCv enhancing image for OCR 的可能重复项 - 请不要发布另一个关于明显相同问题的问题，而是适当地增强原始问题。
-
我把帖子删了，问错了。
-
OK :) |你想用什么来替换你“删除”的图像部分？ （我假设我们正在讨论与附加图像右下角的图像有关的一些进一步步骤。）由于您向 tesseract 提供了一个指定单个检测到的字母的边界框向量，我认为这只是一些外观要求用于展示？
-
不，这不是为了美观，逐个处理字符的问题是我无法定位它们，因此最后我得到一个纠结的字符串，有一种方法可以知道哪个边界框 js我可以从第一行从左到右开始第二个，但我不知道
-
你确定你得到的结果没有可预测的顺序吗？您肯定会从已经分割的符号中受益。你能发布一个你的结果的例子吗？所有的车牌都保证有两条线吗？您可以根据 y 坐标将符号分成两组，然后在每组中按 x 排序。 |为了摆脱其他东西，我只需制作一个相同大小的新图像，填充白色，然后从源中复制每个符号 ROI。