Harris Corner detection algorithm was developed to identify the internal corners of an image. The corners of an image are basically identified as the regions in which there are variations in large intensity of the gradient in all possible dimensions and directions. Corners extracted can be a part of the image features, which can be matched with features of other images, and can be used to extract accurate information. Harris Corner Detection is a method to extract the corners from the input image and to extract features from the input image.
About the function used:
Syntax: cv2.cornerHarris(src, dest, blockSize, kSize, freeParameter, borderType)
Parameters:
src – Input Image (Single-channel, 8-bit or floating-point)
dest – Image to store the Harris detector responses. Size is same as source image
blockSize – Neighborhood size ( for each pixel value blockSize * blockSize neighbourhood is considered )
ksize – Aperture parameter for the Sobel() operator
freeParameter – Harris detector free parameter
borderType – Pixel extrapolation method ( the extrapolation mode used returns the coordinate of the pixel corresponding to the specified extrapolated pixel )
Below is the Python implementation :
Python3
# Python program to illustrate# corner detection with# Harris Corner Detection Method # organizing importsimport cv2import numpy as np # path to input image specified and # image is loaded with imread commandimage = cv2.imread('GeekforGeeks.jpg') # convert the input image into# grayscale color spaceoperatedImage = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) # modify the data type# setting to 32-bit floating pointoperatedImage = np.float32(operatedImage) # apply the cv2.cornerHarris method# to detect the corners with appropriate# values as input parametersdest = cv2.cornerHarris(operatedImage, 2, 5, 0.07) # Results are marked through the dilated cornersdest = cv2.dilate(dest, None) # Reverting back to the original image,# with optimal threshold valueimage[dest > 0.01 * dest.max()]=[0, 0, 255] # the window showing output image with cornerscv2.imshow('Image with Borders', image) # De-allocate any associated memory usage if cv2.waitKey(0) & 0xff == 27: cv2.destroyAllWindows() |
Input:
Output:
