Python: Sorting items from top left to bottom right with OpenCV

The resulting numbering depends on how many rows you want there to be. With the program I will show you how to make, you can specify the number of rows before you run the program.

For example, here is the original image:

Here is the numbered image when you specify 4 rows:

Here is the numbered image when you specify 6 rows:

For the other image you provided (with its frame cropped so the frame won’t be detected as a shape), you can see there will be 4 rows, so putting 4 into the program will give you:

---

Let’s have a look at the workflow considering 4 rows. The concept I used is to divide the image into 4 segments along the y axis, forming 4 rows. For each segment of the image, find every shape that has its center in that segment. Finally, order the shapes in each segment by their x coordinate.

1. Import the necessary libraries:

import cv2
import numpy as np

2. Define a function that will take in an image input and return the image processed to something that will allow python to later retrieve their contours:

def process_img(img):
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    img_canny = cv2.Canny(img_gray, 100, 100)
    kernel = np.ones((2, 3))
    img_dilate = cv2.dilate(img_canny, kernel, iterations=1)
    img_erode = cv2.erode(img_dilate, kernel, iterations=1)
    return img_erode

3. Define a function that will return the center of a contour:

def get_centeroid(cnt):
    length = len(cnt)
    sum_x = np.sum(cnt[..., 0])
    sum_y = np.sum(cnt[..., 1])
    return int(sum_x / length), int(sum_y / length)

4. Define a function that will take in a processed image and return the center points of the shapes found in the image:

def get_centers(img):
    contours, hierarchies = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
    for cnt in contours:
        if cv2.contourArea(cnt) > 100:
            yield get_centeroid(cnt)

5. Define a function that will take in an image array, img, an array of coordinates, centers, the number of segments for the image, row_amt, and the height of each segment, row_h, as input. It will return row_amt arrays (sorted by their x coordinates), each containing every point in centers that lies in its corresponding row of the image:

def get_rows(img, centers, row_amt, row_h):
    centers = np.array(centers)
    d = row_h / row_amt
    for i in range(row_amt):
        f = centers[:, 1] - d * i
        a = centers[(f < d) & (f > 0)]
        yield a[a.argsort(0)[:, 0]]

6. Read in the image, get its processed form using the processed function defined, and get the center of each shape in the image using the centers function defined:

img = cv2.imread("shapes.png")
img_processed = process_img(img)
centers = list(get_centers(img_processed))

7. Get the height of the image to use for the get_rows function defined, and define a count variable, count, to keep track of the numbering:

h, w, c = img.shape
count = 0

8. Loop through the centers of the shape divided into 4 rows, drawing the line that connects the rows for visualization:

for row in get_rows(img, centers, 4, h):
    cv2.polylines(img, [row], False, (255, 0, 255), 2)
    for x, y in row:

9. Add to the count variable, and draw the count onto the specific location on the image from the row array:

        count += 1
        cv2.circle(img, (x, y), 10, (0, 0, 255), -1)  
        cv2.putText(img, str(count), (x - 10, y + 5), 1, cv2.FONT_HERSHEY_PLAIN, (0, 255, 255), 2)

10. Finally, show the image:

cv2.imshow("Ordered", img)
cv2.waitKey(0)

---

Altogether:

import cv2
import numpy as np

def process_img(img):
    img_gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    img_canny = cv2.Canny(img_gray, 100, 100)
    kernel = np.ones((2, 3))
    img_dilate = cv2.dilate(img_canny, kernel, iterations=1)
    img_erode = cv2.erode(img_dilate, kernel, iterations=1)
    return img_erode
    
def get_centeroid(cnt):
    length = len(cnt)
    sum_x = np.sum(cnt[..., 0])
    sum_y = np.sum(cnt[..., 1])
    return int(sum_x / length), int(sum_y / length)

def get_centers(img):
    contours, hierarchies = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
    for cnt in contours:
        if cv2.contourArea(cnt) > 100:
            yield get_centeroid(cnt)

def get_rows(img, centers, row_amt, row_h):
    centers = np.array(centers)
    d = row_h / row_amt
    for i in range(row_amt):
        f = centers[:, 1] - d * i
        a = centers[(f < d) & (f > 0)]
        yield a[a.argsort(0)[:, 0]]

img = cv2.imread("shapes.png")
img_processed = process_img(img)
centers = list(get_centers(img_processed))

h, w, c = img.shape
count = 0

for row in get_rows(img, centers, 4, h):
    cv2.polylines(img, [row], False, (255, 0, 255), 2)
    for x, y in row:
        count += 1
        cv2.circle(img, (x, y), 10, (0, 0, 255), -1)  
        cv2.putText(img, str(count), (x - 10, y + 5), 1, cv2.FONT_HERSHEY_PLAIN, (0, 255, 255), 2)

cv2.imshow("Ordered", img)
cv2.waitKey(0)