从opencv中的数独中提取框 [英] Extract boxes from sudoku in opencv

问题描述

我已经使用 opencv 将数独图像转换为数独网格

现在我想从图像中提取每个框，最好的方法是什么?

据我所知，我正在尝试找到线的交点以找到每个框的角

类 SudokuSolverPlay:def __init__(自我，图像):def __preProcess(self, img):""""返回灰度图像""""def __maskSudoku(self, img):""""返回蒙版图像""""def __dectactEdge(self, img):""""返回数独格子""""def drawLines(src, dest, 迭代=1):minLineLength = 100src = cv2.convertScaleAbs(src)对于 _ 在范围内(迭代):线 = cv2.HoughLinesP(image=src, rho=1, theta=np.pi/180,阈值=100，行=np.array([])，minLineLength=minLineLength, maxLineGap=100)a, b, c = 线条.形状对于范围内的 i (a):x1, y1, x2, y2 = 线[i][0][0], 线[i][0][1], 线[i][0][2], 线[i][0][3]cv2.line(dest, (x1, y1), (x2, y2),255, 1, cv2.LINE_AA)src = cv2.convertScaleAbs(dest)def findVerticalLines(img):imgX = cv2.GaussianBlur(img, (5, 5), 0)kernelx = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 10))imgY = cv2.Sobel(img, cv2.CV_64F, 1, 0)imgY = cv2.convertScaleAbs(imgY)cv2.normalize(imgY, imgY, 0, 255, cv2.NORM_MINMAX)imgY = cv2.morphologyEx(imgY, cv2.MORPH_CLOSE, kernelx, 迭代次数=1)返回 imgYdef findHorizo​​ntalLines(img):""与上面相同，只是参数不同""img1 = np.zeros(img.shape)边缘 = cv2.Canny(img, 50, 150, 孔径 = 3)拉普拉斯算子 = cv2.拉普拉斯算子(边，cv2.CV_64F)drawLines(拉普拉斯算子，img1，迭代=1)sby = findVerticalLines(img1)sbx = findHorizo​​ntalLines(img1)返回图片1def 解决数独(自我):灰色 = self.__preProcess(self.__originalImg)蒙面 = self.__maskSudoku(灰色)网格 = self.__dectactGrid(蒙面)如果 __name__ == '__main__':colorImg = cv2.imread('sudoku1.jpg')求解器 = SudokuSolverPlay(colorImg)求解器.solveSudoku()

这里的 findVerticalLines() 和 findHorizo​​ntalLines() 无法正确识别水平线和垂直线

• 假设最小盒子尺寸为 20*20

  line_min_width = 20

  寻找水平线

  kernal_h = np.ones((1,line_min_width), np.uint8)img_bin_h = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernal_h)

  寻找垂直线

  kernal_v = np.ones((line_min_width,1), np.uint8)img_bin_v = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernal_v)

  合并并添加膨胀层以缩小小间隙

  img_bin_final=img_bin_h|img_bin_vfinal_kernel = np.ones((3,3), np.uint8)img_bin_final=cv2.dilate(img_bin_final,final_kernel,iterations=1)

  应用连通分量分析

  ret, labels, stats,centroids = cv2.connectedComponentsWithStats(~img_bin_final, connected=8, ltype=cv2.CV_32S)

  可视化连接组件图像

  如您所见，我们检测到一些文本也是框，我们可以通过简单的过滤条件轻松删除它们，这里我过滤的区域应至少为 1000 像素条件.

  在检测到的盒子上绘制矩形.

  ### 1 和 0 以及我们不需要的背景和残差连接组件对于 stats[2:] 中的 x,y,w,h,area:# cv2.putText(image,'box',(x-10,y-10),cv2.FONT_HERSHEY_SIMPLEX, 1.0,(0,255,0), 2)如果面积＞1000:cv2.rectangle(图像,(x,y),(x+w,y+h),(0,255,0),2)

  最终输出图片

  此答案基于我使用 OpenCV 在图像中查找复选框/表格的解决方案.您可以在我的 博客中找到详细说明走向数据科学.希望这将使您更接近解决方案.

  编码愉快 :)

  -- 编辑 1

  进行连接组件可视化的代码

  def imshow_components(labels):### 创建一个 hsv 图像，每个标签都有一个唯一的色调值label_hue = np.uint8(179*labels/np.max(labels))###使饱和度和音量为255empty_channel = 255*np.ones_like(label_hue)label_img = cv2.merge([label_hue, empty_channel, empty_channel])### 将 hsv 图像转换为 BGR 图像标记的_img = cv2.cvtColor(标记的_img，cv2.COLOR_HSV2BGR)标记的_img[label_hue==0] = 0### 返回用于可视化连接组件的彩色图像返回labeled_img

  i have converted sudoku image into sudoku grid using opencv

  now i want to extract each box from image what is best way to do this?

  as per my knowledge i am trying to find intersection points of lines to find corner of each box

  class SudokuSolverPlay:
        def __init__(self, image):
           
        def __preProcess(self, img):
          """return grayscale image"""
        def __maskSudoku(self, img):
          """return masked image"""
        def __dectactEdge(self, img):
          """return sudoku grid"""
          def drawLines(src, dest, iteration=1):
              minLineLength = 100
              src = cv2.convertScaleAbs(src)
              for _ in range(iteration):
                  lines = cv2.HoughLinesP(image=src, rho=1, theta=np.pi / 180,
                                      threshold=100, lines=np.array([]),
                                      minLineLength=minLineLength, maxLineGap=100)
                  a, b, c = lines.shape
                  for i in range(a):
                      x1, y1, x2, y2 = lines[i][0][0], lines[i][0][1], lines[i][0][2], lines[i][0][3]
                      cv2.line(dest, (x1, y1), (x2, y2),255, 1, cv2.LINE_AA)
                  src = cv2.convertScaleAbs(dest)
  
          def findVerticalLines(img):
              imgX = cv2.GaussianBlur(img, (5, 5), 0)
              kernelx = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 10))
              imgY = cv2.Sobel(img, cv2.CV_64F, 1, 0)
              imgY = cv2.convertScaleAbs(imgY)
              cv2.normalize(imgY, imgY, 0, 255, cv2.NORM_MINMAX)
              imgY = cv2.morphologyEx(imgY, cv2.MORPH_CLOSE, kernelx, iterations=1)
              return imgY
  
          def findHorizontalLines(img):
              """same as above only args different"""
  
          img1 = np.zeros(img.shape)
  
          edges = cv2.Canny(img, 50, 150, apertureSize=3)
          laplacian = cv2.Laplacian(edges, cv2.CV_64F)
          drawLines(laplacian, img1, iteration=1)
  
          sby = findVerticalLines(img1)
          sbx = findHorizontalLines(img1)
          return img1
        def solveSudoku(self):
            gray = self.__preProcess(self.__originalImg)
            masked = self.__maskSudoku(gray)
            grid = self.__dectactGrid(masked)
                     
  
  if __name__ == '__main__':
      colorImg = cv2.imread('sudoku1.jpg')
      solver = SudokuSolverPlay(colorImg)
      solver.solveSudoku()
  

  here findVerticalLines() and findHorizontalLines() are not able to dictect horizontal and vertical lines properly

  • original image
  • masked image
  • Canny edge dictation
  • hough line transform
  • horizontal lines
  • Vertical Lines

  解决方案

  One way to solve is to do a morphological operation to find vertical and horizontal lines from the canny edge image, then do a connected component analysis to find the boxes. I have done a sample version below. You can finetune it further to make it better. I started with the masked image as input.

  ### reading input image
  gray_scale=cv2.imread('masked_image.jpg',0)
  

  Performing canny edge detection and adding a dilation layer

  img_bin = cv2.Canny(gray_scale,50,110)
  dil_kernel = np.ones((3,3), np.uint8)
  img_bin=cv2.dilate(img_bin,dil_kernel,iterations=1)
  

  Now, the dilated binary image looks like this.

  assuming minimum box size would be 20*20

  line_min_width = 20
  

  finding horizontal lines

  kernal_h = np.ones((1,line_min_width), np.uint8)
  img_bin_h = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernal_h)
  

  finding vertical lines

  kernal_v = np.ones((line_min_width,1), np.uint8)
  img_bin_v = cv2.morphologyEx(img_bin, cv2.MORPH_OPEN, kernal_v)
  

  merging and adding a dilation layer to close small gaps

  img_bin_final=img_bin_h|img_bin_v
  final_kernel = np.ones((3,3), np.uint8)
  img_bin_final=cv2.dilate(img_bin_final,final_kernel,iterations=1)
  

  applying connected component analysis

  ret, labels, stats,centroids = cv2.connectedComponentsWithStats(~img_bin_final, connectivity=8, ltype=cv2.CV_32S)
  

  visualising Connected component image

  AS you can see, we have detected some text also as boxes, we can easily remove them with simple filter conditions, Here I'm filtering with the area should be minimum 1000 pixels condition.

  drawing rectangles on the detected boxes.

  ### 1 and 0 and the background and residue connected components whihc we do not require
  for x,y,w,h,area in stats[2:]:
  #     cv2.putText(image,'box',(x-10,y-10),cv2.FONT_HERSHEY_SIMPLEX, 1.0,(0,255,0), 2)
      if area>1000:
          cv2.rectangle(image,(x,y),(x+w,y+h),(0,255,0),2)
  

  final output image

  This answer is based on my solution to find checkboxes/tables in an image using OpenCV. You can find a detailed explanation in my blog at Towards Data Science. Hope this will take you closer to a solution.

  Happy coding :)

  -- edit 1

  code to do connected component visualisation

  def imshow_components(labels):
      ### creating a hsv image, with a unique hue value for each label
      label_hue = np.uint8(179*labels/np.max(labels))
      ### making saturation and volume to be 255
      empty_channel = 255*np.ones_like(label_hue)
      labeled_img = cv2.merge([label_hue, empty_channel, empty_channel])
      ### converting the hsv image to BGR image
      labeled_img = cv2.cvtColor(labeled_img, cv2.COLOR_HSV2BGR)
      labeled_img[label_hue==0] = 0
      ### returning the color image for visualising Connected Componenets
      return labeled_img
  

  这篇关于从opencv中的数独中提取框的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！