Square detection in image

Question

I am trying to detect all the squared shaped dice images so that i can crop them individually and use that for OCR. Below is the Original image:

Here is the code i have got but it is missing some squares.

def find_squares(img):
    img = cv2.GaussianBlur(img, (5, 5), 0)
    squares = []
    for gray in cv2.split(img):
        for thrs in range(0, 255, 26):
            if thrs == 0:
                bin = cv2.Canny(gray, 0, 50, apertureSize=5)
                bin = cv2.dilate(bin, None)
            else:
                _retval, bin = cv2.threshold(gray, thrs, 255, cv2.THRESH_BINARY)
            bin, contours, _hierarchy = cv2.findContours(bin, cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
            for cnt in contours:
                cnt_len = cv2.arcLength(cnt, True)
                cnt = cv2.approxPolyDP(cnt, 0.02*cnt_len, True)
                if len(cnt) == 4 and cv2.contourArea(cnt) > 1000 and cv2.isContourConvex(cnt):
                    cnt = cnt.reshape(-1, 2)
                    max_cos = np.max([angle_cos( cnt[i], cnt[(i+1) % 4], cnt[(i+2) % 4] ) for i in range(4)])
                    #print(cnt)
                    a = (cnt[1][1] - cnt[0][1])

                    if max_cos < 0.1 and a < img.shape[0]*0.8:

                        squares.append(cnt)
    return squares

dice = cv2.imread('img1.png')
squares = find_squares(dice)
cv2.drawContours(dice, squares, -1, (0, 255, 0), 3)

Here are the Output images:

As per my analysis, some squares are missing due to missing canny edges along the dice because of smooth intensity transition between dice and background.

Given the constraint that there will always be 25 dices in square grid pattern (5*5) can we predict the missing square positions based on recognised squares? Or can we modify above algorithm for square detection algorithm?

Answer 1

Here's an approach

• Convert image to grayscale and median blur to smooth image
• Sharpen image to enhance edges
• Threshold. Depending on the image, Otsu's thresholding or Adaptive thresholding would work
• Perform morphological transformations
• Find contours and filter using minimum/maximum threshold area
• Crop and save ROI

---

Sharpen image with cv2.filter2D(). We use a generic sharpen kernel, other kernels can be found here

Now threshold to get a binary image

Perform morphological operations

From here we find contours and filter using cv2.contourArea() with minimum/maximum threshold areas.

We can crop each desired square region using Numpy slicing and save each ROI like this

x,y,w,h = cv2.boundingRect(c)
ROI = image[y:y+h, x:x+w]
cv2.imwrite('ROI_{}.png'.format(image_number), ROI)

import cv2
import numpy as np

image = cv2.imread('1.png')

gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.medianBlur(gray, 5)
sharpen_kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
sharpen = cv2.filter2D(blur, -1, sharpen_kernel)

thresh = cv2.threshold(sharpen,160,255, cv2.THRESH_BINARY_INV)[1]
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3,3))
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=2)

cnts = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

min_area = 100
max_area = 1500
image_number = 0
for c in cnts:
    area = cv2.contourArea(c)
    if area > min_area and area < max_area:
        x,y,w,h = cv2.boundingRect(c)
        ROI = image[y:y+h, x:x+w]
        cv2.imwrite('ROI_{}.png'.format(image_number), ROI)
        cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 2)
        image_number += 1

cv2.imshow('sharpen', sharpen)
cv2.imshow('close', close)
cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()