[机器视觉] 实际场景字提取

Posted 2021-02-05 aoru45

手机场景下字体提取

简介

这是老师突然给的任务，不做吧又不好，做呗。实际做的过程中让我对形态学处理有了新的认识，我真没想到形态学处理这么强大，同时也深化了我对sobel算子的理解和记忆。。强大！
处理过程供分为两步，

1. ROI的获取并矫正
2. 字提取

ROI提取

思路大致是这样的，由于在原图中存在矩形表格框，所以只要能够拿到矩形表格框下的ROI，然后在ROI下提取文字，那么处理起来应该会方便很多，面临的问题主要有特定方向边界的提取、矩形拟合、关键点如何变换的问题。

对于特定方向边界的提取，我采用的是sobel算子在高斯平滑和中值滤波之后进行提取，单独提取x方向和y方向边界，然后按照1:1权重加和，期间kernel size需要调参。二值化，经过形态学膨胀和腐蚀处理将噪声点去掉，然后找contour。

对于举行拟合，计算每个contour的面积，面积满足一定阈值留下，留下的contour使用多边形拟合得到多边形边界，得到的候选多边形边界类似于举行，但仍然有干扰点，通过简单的算法得到举行的四个定点，于是得到拟合后的矩形。

对于关键点变换，由于得到的举行可能是经过翻折、旋转等线性变换的样子，我们需要将举行“摆正”，通过构造变换矩阵，进行线性变换，将举行映射到一张正视图中。

对每个contour执行上述操作，即得到ROI。需要注意的是，应对不同信息需要调参。

# w:240*6 h:160*6
def getROI(frame):
    while True:
        out_imgs = []
        src = copy.copy(frame)
        thre = cv.getTrackbarPos("thre","Trackbar")
        max_e = cv.getTrackbarPos("max_e","Trackbar")
        min_e = cv.getTrackbarPos("min_e","Trackbar")
        gray = cv.cvtColor(src,cv.COLOR_BGR2GRAY)
        gaussian = cv.GaussianBlur(gray,(3,3),0,0,cv.BORDER_DEFAULT)
        median = cv.medianBlur(gaussian,5)
        x = cv.Sobel(median,cv.CV_8U, 1, 0, ksize = 3)
        y = cv.Sobel(median,cv.CV_8U, 0, 1, ksize = 3)
        absX = cv.convertScaleAbs(x)
        absY = cv.convertScaleAbs(y)
        sobel = cv.addWeighted(absX,0.5,absY,0.5,0)
        r,binary = cv.threshold(sobel,thre,255,cv.THRESH_BINARY)
        s = gray.shape
        element1 = cv.getStructuringElement(cv.MORPH_RECT,(1*2+1,2*2+1))
        element2 = cv.getStructuringElement(cv.MORPH_RECT, (min_e*2+1,max_e*2+1))
        dilate = cv.dilate(binary,element1,iterations =1)
        erode = cv.erode(dilate,element2,iterations = 1)
        dilate = cv.dilate(erode,element1,iterations =2)
        binary = dilate
        img,contours,_ = cv.findContours(binary,cv.RETR_EXTERNAL,cv.CHAIN_APPROX_SIMPLE)
        for contour in contours:
            area = cv.contourArea(contour)
            if area > 50000:
                appCurve = cv.approxPolyDP(contour,10,True)
                hulls = cv.convexHull(appCurve)
                i = 0
                min_x_y = 9999999
                max_x_y = 0
                rect_point = [None,(0,0),None,(0,0)]
                for hull in hulls:
                    point = (hull[0][0],hull[0][1])
                    x_y = point[0] + point[1]
                    if x_y > max_x_y:
                        max_x_y = x_y
                        rect_point[2] = point
                    if x_y < min_x_y:
                        min_x_y = x_y
                        rect_point[0] = point
                p1 = (rect_point[2][0],rect_point[0][1])
                p2 = (rect_point[0][0],rect_point[2][1])
                for hull in hulls:
                    point = (hull[0][0],hull[0][1])
                    distance11 = abs(p1[0]-point[0]) + abs(p1[1]-point[1])
                    distance12 = abs(p1[0]-rect_point[1][0]) + abs(p1[1]-rect_point[1][1])
                    if distance11 < distance12:
                        rect_point[1] = point
                    distance21 = abs(p2[0]-point[0]) + abs(p2[1]-point[1])
                    distance22 = abs(p2[0]-rect_point[3][0]) + abs(p2[1]-rect_point[3][1])
                    if distance21 < distance22:
                        rect_point[3] = point
                M = cv.getPerspectiveTransform(np.array(rect_point,dtype=np.float32),np.array([[0,0],[1440,0],[1440,960],[0,960]],dtype=np.float32))
                out = cv.warpPerspective(src,M,(1440,960))
                for p in rect_point:
                    cv.circle(src,p,20,(0,0,255),2)
                #cv.imshow("out",out)
                out_imgs.append(out)
        binary = cv.resize(binary,(int(s[1]/3),int(s[0]/3)),cv.INTER_LINEAR)
        
        cv.imshow("binary",binary)
        src = cv.resize(src,(int(s[1]/3),int(s[0]/3)),cv.INTER_LINEAR)
        cv.imshow("frame",src)
        key = cv.waitKey(0)
        if key ==27:
            for i in range(len(out_imgs)):
                cv.imwrite("image/"+str(i)+".jpg",out_imgs[i])
            break
        cv.destroyAllWindows()

字提取

字提取的关键是找到bbox，思路是通过Canny算子得到轮廓特征，形态学膨胀去除噪声，找contour，对contour进行面积筛选，满足阈值拟合出外接矩形，对外接举行的高度进行阈值判断，除去噪声点拟合的小矩形。由此字区域提取完毕。

def process(ROI):
    while True:
        thre1 =cv.getTrackbarPos("thre1","Trackbar")
        thre2 =cv.getTrackbarPos("thre2","Trackbar")
        max_e = cv.getTrackbarPos("max_e","Trackbar")
        min_e = cv.getTrackbarPos("min_e","Trackbar")
        height = cv.getTrackbarPos("height","Trackbar")
        roi = copy.copy(ROI)
        gray = cv.cvtColor(roi,cv.COLOR_BGR2GRAY)
        gaussian = cv.GaussianBlur(gray,(3,3),0,0,cv.BORDER_DEFAULT)
        median = cv.medianBlur(gaussian,3)
        edges = cv.Canny(median,thre1,thre2)
        element = cv.getStructuringElement(cv.MORPH_RECT,(min_e*2+1,max_e*2+1))
        dilate = cv.dilate(edges,element,iterations = 1)
        img,contours,_ = cv.findContours(dilate,cv.RETR_LIST,cv.CHAIN_APPROX_SIMPLE)
        #cv.drawContours(roi,contours,-1,(0,255,255),2)
        
        for contour in contours:
            area = cv.contourArea(contour)
            if area > 4:
                rect = cv.boundingRect(contour)
                if rect[3]>height:
                    cv.rectangle(roi,(rect[0],rect[1]),(rect[0]+rect[2],rect[1]+rect[3]),(0,255,255),2)
        cv.imshow("roi",roi)
        cv.imshow("dilate",dilate)
        cv.imshow("edges",edges)
        key = cv.waitKey(10)
        if key == 27:
            break
    cv.destroyAllWindows()

效果

原图

bbox提取：

还有图老师说隐私不让发，就两张凑个数。

存在问题

1. 调参严重（不同光线等条件）
2. 提取灰度字只是边界提取，难于辨认
3. 多尺度图片ROI提取需要调参（可以归结到1）