Detect with noisy background/object - OpenCV

Question

i'm trying to detect a card, but the problem is that sometimes the image is not good and has several backgrounds, like this:

Not well define edges

![Not well define edges][1]

Example background

![Example background][2]

I did this:

gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
gray = cv2.GaussianBlur(gray,(11,11),0)

edg = cv2.Canny(gray, 10, 20)
contours,_ = cv2.findContours(edg.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
cv2.drawContours(image,contours,-1,[0,255,0],2)

cv2.imshow('image',image)
cv2.waitKey(0)

But sometimes he detects other stuff, and not the card. Anyone has ideias how to solve this? I've tried Object Detection with YOLO, but it's hard

Can you add original image ? So that can try some experiments — venkata krishnan, Aug 22 '19 at 10:39
Please look at this post. https://stackoverflow.com/questions/1364976/rectangle-detection-with-hough-transform — Faroq AL-Tam, Aug 23 '19 at 17:27

Peyman habibi · Answer 1 · 2019-08-22T12:14:07.677

1

first of all, note that, there are some condition like light condition and medium condition in take photo which if you can control them, the image processing section load will decreases. for example in your example image, you can put A4 white paper in the background to reduce small contours and so on(Of course it's impossible to change condition).

Well, i try on your test image with this code :

import cv2

rectKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (8, 8))
sqKernel = cv2.getStructuringElement(cv2.MORPH_RECT, (17, 17))

img = cv2.imread('edge.jpg')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)


gradX = cv2.Sobel(gray, ddepth=cv2.CV_32F, dx=1, dy=0,
    ksize=-1)

morph1 = cv2.morphologyEx(gradX, cv2.MORPH_OPEN, rectKernel)
morph2 = cv2.morphologyEx(morph1, cv2.MORPH_CLOSE, sqKernel)


cv2.imshow("img",img)
cv2.imshow("gradx",gradX)
cv2.imshow("tophat",morph1)
cv2.imshow("tophat2",morph2)
cv2.waitKey()

here is the results:

You can use contours and remove unwanted contours using contour properties : Contour Properties

edited Aug 22 '19 at 12:14

answered Aug 22 '19 at 12:03

Peyman habibi

680
1
6
17

that is a pseudo code which you can complete it. Main algorithm needs to see all photos and condition of your project. you can try yourself. – Peyman habibi Aug 22 '19 at 16:48
my code applied on Test1 image. in the final step you can add findcountour method and select contour with largest area and then mask it from original image. – Peyman habibi Aug 22 '19 at 16:52
please give real images for test. – Peyman habibi Aug 22 '19 at 16:53
Added 2 test images – tentativa123 Aug 22 '19 at 17:30

Detect with noisy background/object - OpenCV

1 Answers1