Edge detection on dim edges using Python

Question

I want to find dim edges using Python.

Input images (100 X 100) :

It consists of several horizontal boards: top, middle, bottom.

I want to find middle board bounding box like:

I used several edge detection methods (prewitt_x, sobel_x, cv2.findContours) but cannot detect well.

Because edge btw black region and board region is dim.

How can I find bounding box like red box?

Code below is example using prewitt_x and cv2.findContours:

import cv2
import numpy as np

img = cv2.imread('my_dir/my_img.bmp',0)

# prewitts_x
kernelx = np.array([[1,1,1],[0,0,0],[-1,-1,-1]])
img_prewittx = cv2.filter2D(img, -1, kernelx)
img_prewittx_gray = cv2.cvtColor(img_prewittx, cv2.COLOR_BGR2GRAY)
cv2.imwrite('my_outdir/my_outimg.bmp',img_prewittx)

# cv2.findContours
image, contours, hierarchy = cv2.findContours(img_prewittx_gray, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
rects = [cv2.boundingRect(cnt) for cnt in contours]
print(rects)

In fact, I don't want to use slower one like Canny detector.

Help me :)

I am not sure if I understood your problem. What do you mean by several boards? What exactly do you want to find? Anyway, your image seems very noise. Can't you change colors or apply a noise reduction filter? — Fred Guth
– Fred Guth, Commented Jun 11, 2018 at 14:29
You could blur the image with a huge kernel and then apply a spatial closing operation. You will not get the smallest cut but at least you could get the different regions. When I understand the problem it is independent of the x coordinate. Now you can search for the longest white are in both of the identified sets and adjust the y value. — Max Krappmann
– Max Krappmann, Commented Jun 11, 2018 at 15:32
@fredguth Each image, they have total 5 part. From up to down : gray-black-gray-black-gray. The gray part is what I mean "borad". What you mean "change color"? It's like using HSV filter? — Kanjae Park
– Kanjae Park, Commented Jun 15, 2018 at 8:28
@MaxKrappmann Do you mean a huge kernel is like [[10,10,10],[0,0,0],[10,10,10]] rather than [[1,1,1],[0,0,0],[1,1,1]] ? — Kanjae Park
– Kanjae Park, Commented Jun 15, 2018 at 8:31
No you have to increase your size of the filter. docs.opencv.org/3.1.0/d4/d13/tutorial_py_filtering.html — Max Krappmann
– Max Krappmann, Commented Jun 15, 2018 at 8:42

score 1 · Accepted Answer · 2018-06-14 09:00:11Z

1

My suggestion:

use a simple edge detection filter such as Prewitt
project horizontally (sum of the pixels in every row)
analyze the resulting profile to detect the regions of low/high activity and delimit the desired slabs.

You can also try the maximum along rows instead of the sum.

But don't expect miracles, this is a hard problem.

edited Jun 14, 2018 at 9:00

answered Jun 14, 2018 at 8:55

user1196549

Sign up to request clarification or add additional context in comments.

1 Comment

Kanjae Park Over a year ago

Thanks for your comment :) I'll try it

Collectives™ on Stack Overflow

Edge detection on dim edges using Python

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related