python - Detecting vertical lines using Hough transforms in opencv -
i'm trying remove square boxes(vertical , horizontal lines) using hough transform in opencv (python). problem none of vertical lines being detected. i've tried looking through contours , hierarchy there many contours in image , i'm confused how use them.
after looking through related posts, i've played threshold , rho parameters didn't help. i've attached code more details. why hough transform not find vertical lines in image?. suggestions in solving task welcome. thanks.
input image : 
hough transformed image: 
drawing contours: 
import cv2 import numpy np import pdb img = cv2.imread('/home/user/downloads/cropped/robust_blaze_cpp-300-0000046a-02-hw.jpg') gray = cv2.cvtcolor(img,cv2.color_bgr2gray) ret, thresh = cv2.threshold(gray, 140, 255, 0) im2, contours, hierarchy = cv2.findcontours(thresh, cv2.retr_tree, cv2.chain_approx_simple) cv2.drawcontours(img, contours, -1, (0,0,255), 2) edges = cv2.canny(gray,50,150,aperturesize = 3) minlinelength = 5 maxlinegap = 100 lines = cv2.houghlinesp(edges,rho=1,theta=np.pi/180,threshold=100,minlinelength=minlinelength,maxlinegap=maxlinegap) x1,y1,x2,y2 in lines[0]: cv2.line(img,(x1,y1),(x2,y2),(0,255,0),2) cv2.imwrite('probhough.jpg',img)
to honest, rather looking lines, i'd instead white boxes.
preparation
import cv2 import numpy npload image
img = cv2.imread("digitbox.jpg", 0)binarize it, both boxes , digits black, rest white
_, thresh = cv2.threshold(img, 200, 255, cv2.thresh_binary) cv2.imwrite('digitbox_step1.png', thresh)
find contours. in example image, it's fine external contours.
_, contours, hierarchy = cv2.findcontours(thresh, cv2.retr_external, cv2.chain_approx_simple)process contours, filtering out small area. find convex hull of each contour, create mask of areas outside contour. store bounding boxes of each found contour, sorted x coordinate.
mask = np.ones_like(img) * 255 boxes = [] contour in contours: if cv2.contourarea(contour) > 100: hull = cv2.convexhull(contour) cv2.drawcontours(mask, [hull], -1, 0, -1) x,y,w,h = cv2.boundingrect(contour) boxes.append((x,y,w,h)) boxes = sorted(boxes, key=lambda box: box[0]) cv2.imwrite('digitbox_step2.png', mask)
dilate mask (to shrink black parts), clip off remains the gray frames.
mask = cv2.dilate(mask, np.ones((5,5),np.uint8)) cv2.imwrite('digitbox_step3.png', mask)
fill masked pixels white, erase frames.
img[mask != 0] = 255 cv2.imwrite('digitbox_step4.png', img)
process digits desire -- i'll draw bounding boxes.
result = cv2.cvtcolor(img, cv2.color_gray2bgr) n,box in enumerate(boxes): x,y,w,h = box cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2) cv2.puttext(result, str(n),(x+5,y+17), cv2.font_hershey_simplex, 0.6,(255,0,0),2,cv2.line_aa) cv2.imwrite('digitbox_step5.png', result)
the whole script in 1 piece:
import cv2 import numpy np img = cv2.imread("digitbox.jpg", 0) _, thresh = cv2.threshold(img, 200, 255, cv2.thresh_binary) _, contours, hierarchy = cv2.findcontours(thresh, cv2.retr_external, cv2.chain_approx_simple) mask = np.ones_like(img) * 255 boxes = [] contour in contours: if cv2.contourarea(contour) > 100: hull = cv2.convexhull(contour) cv2.drawcontours(mask, [hull], -1, 0, -1) x,y,w,h = cv2.boundingrect(contour) boxes.append((x,y,w,h)) boxes = sorted(boxes, key=lambda box: box[0]) mask = cv2.dilate(mask, np.ones((5,5),np.uint8)) img[mask != 0] = 255 result = cv2.cvtcolor(img, cv2.color_gray2bgr) n,box in enumerate(boxes): x,y,w,h = box cv2.rectangle(result,(x,y),(x+w,y+h),(255,0,0),2) cv2.puttext(result, str(n),(x+5,y+17), cv2.font_hershey_simplex, 0.6,(255,0,0),2,cv2.line_aa) cv2.imwrite('digitbox_result.png', result)
Comments
Post a Comment