Image processing how to detect specific custom shape in image

user_4101188 0
Viewed 1175

I want to detect a specific shape which is combination of 2 shapes Pentagon and a square. However side of a square should be around 3 times of a pentagon to match a valid shape as shown in the image.

enter image description here

I'm learning different image processing techniques for my requirement.

  1. Contour Detection: Issue is knowing there are 7 corners is not enough as x : 3x need to be validated.

  2. Haar features: Issue is images consist of background and there are text inside these object. So haar will not optimal method in my opinion.

My idea

I think may be I can detect lines corners and using side lengths I can do some math and identify the image.Is there any image processing technique that use mathematical distance, scale, location to identify object?

Original image

matching

enter image description here

not matching

enter image description here

object-detection computer-vision opencv image-processing image
1 Answers

Here's a simple approach:

  1. Obtain binary image. Load image, convert to grayscale, Gaussian blur, then Otsu's threshold.

  2. Filter for desired contour. We find contours then filter using a combination of contour approximation + contour area. With the observation that the shapes have a large area difference, we can use a predetermined threshold area to identify between the two.

Input -> Binary image -> Detected shape

Result

Match

Input -> Binary image -> Detected shape

Result

No Match

Since you didn't specify a language, I implemented in Python

import cv2
import numpy as np

# Load image, grayscale, Gaussian blur, Otsus threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray, (3,3), 0)
thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Find contours
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.04 * peri, True)
    area = cv2.contourArea(c)
    # Filter using contour approximation and area filtering (Remove small noise)
    if len(approx) > 4 and len(approx) < 8 and area > 200:
        # This is the larger version
        if area >= 5500:
            print('Match')
        # Smaller version
        elif area < 5500:
            print('No Match')
        cv2.drawContours(image, [c], -1, (255,0,12), 3)

cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()
user_111621650
Related