Corner detection (Harris) in Computer Vision

Introduction

Corner detection helps find points in images where edges meet, which are useful for recognizing shapes and tracking objects.

To detect important points in a photo for object recognition.

When tracking moving objects in video frames.

To help stitch multiple images together in panorama creation.

For robot navigation by recognizing landmarks.

To analyze textures or patterns in images.

Syntax

Computer Vision

cv2.cornerHarris(src_gray, blockSize, ksize, k)

# Parameters:
# src_gray: Grayscale input image (float32 type)
# blockSize: Size of neighborhood considered for corner detection
# ksize: Aperture parameter for Sobel operator
# k: Harris detector free parameter (usually 0.04 to 0.06)

Input image must be grayscale and of type float32.

The function returns a response image where higher values indicate stronger corners.

Examples

Detect corners using a 2x2 neighborhood, Sobel operator size 3, and k=0.04.

Computer Vision

dst = cv2.cornerHarris(gray_img, 2, 3, 0.04)

Use a larger neighborhood and Sobel size with a slightly higher k value.

Computer Vision

dst = cv2.cornerHarris(gray_img, 3, 5, 0.06)

Sample Model

This program loads a chessboard image, converts it to grayscale, and applies the Harris corner detector. It marks detected corners in red and saves the result. It also prints the maximum corner response value and how many corners were detected above the threshold.

Computer Vision

import cv2
import numpy as np

# Load image and convert to grayscale
img = cv2.imread('chessboard.png')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = np.float32(gray)

# Detect corners using Harris
block_size = 2
ksize = 3
k = 0.04
corner_response = cv2.cornerHarris(gray, block_size, ksize, k)

# Dilate corner points to mark them
corner_response = cv2.dilate(corner_response, None)

# Threshold to mark strong corners in red
img[corner_response > 0.01 * corner_response.max()] = [0, 0, 255]

# Save result image
cv2.imwrite('chessboard_corners.png', img)

# Print some stats
print(f"Max corner response: {corner_response.max():.2f}")
print(f"Number of corners detected: {(corner_response > 0.01 * corner_response.max()).sum()}")

Important Notes

Choosing the right threshold is important to detect meaningful corners without noise.

Harris corner detection is rotation invariant but not scale invariant.

For color images, convert to grayscale before applying the detector.

Summary

Harris corner detection finds points where edges meet in images.

It uses gradients in a small neighborhood to compute a corner response.

Strong corners have high response values and can be marked or used for further tasks.

Practice

1. What is the main goal of the Harris corner detection algorithm in computer vision?

easy

A. To detect straight lines in an image

B. To find points in an image where edges meet, called corners

C. To blur the image for noise reduction

D. To segment the image into different color regions

Solution

1. Step 1: Understand the purpose of Harris corner detection

   Harris corner detection is designed to find corners, which are points where two edges meet in an image.

2. Step 2: Compare with other options

   Blurring, line detection, and segmentation are different tasks not performed by Harris corner detection.

3. Final Answer:

   To find points in an image where edges meet, called corners -> Option B

4. Quick Check:

   Harris detects corners = C [OK]

Hint: Corners are where edges meet, Harris finds these points [OK]

Common Mistakes:

• Confusing corner detection with edge detection
• Thinking Harris blurs or segments images
• Mixing up line detection with corner detection

2. Which of the following is the correct formula for the Harris corner response R?

easy

A. R = det(M) + k * (trace(M))^2

B. R = trace(M) - k * det(M)

C. R = det(M) - k * (trace(M))^2

D. R = det(M) / trace(M)

Solution

1. Step 1: Recall the Harris corner response formula

   The Harris response is calculated as R = det(M) - k * (trace(M))^2, where M is the second moment matrix and k is a sensitivity factor.

2. Step 2: Verify other options

   Other formulas either add instead of subtract or mix det and trace incorrectly.

3. Final Answer:

   R = det(M) - k * (trace(M))^2 -> Option C

4. Quick Check:

   Harris R formula uses det minus k times trace squared [OK]

Hint: Remember: R = det minus k times trace squared [OK]

Common Mistakes:

• Adding instead of subtracting in the formula
• Confusing determinant with trace
• Using division instead of subtraction

3. Given the following Python code snippet using OpenCV, what will be the output type of corners?

import cv2
import numpy as np
img = cv2.imread('image.jpg', 0)
corners = cv2.cornerHarris(img, 2, 3, 0.04)
print(type(corners))

medium

A. <class 'float'>

B. <class 'list'>

C. <class 'int'>

D. <class 'numpy.ndarray'>

Solution

1. Step 1: Understand OpenCV cornerHarris output

   The function cv2.cornerHarris returns a numpy array representing the corner response for each pixel.

2. Step 2: Check the printed type

   Printing type(corners) will show <class 'numpy.ndarray'> because corners is a numpy array.

3. Final Answer:

   <class 'numpy.ndarray'> -> Option D

4. Quick Check:

   cornerHarris returns numpy array [OK]

Hint: cornerHarris returns a numpy array of responses [OK]

Common Mistakes:

• Assuming output is a list instead of numpy array
• Thinking output is a single number
• Confusing output type with image type

4. In the code below, why does the Harris corner detection not highlight any corners?

import cv2
import numpy as np
img = cv2.imread('image.jpg', 0)
corners = cv2.cornerHarris(img, 2, 3, 0.04)
corners = cv2.dilate(corners, None)
img[corners > 0.01 * corners.max()] = 255
cv2.imshow('Corners', img)
cv2.waitKey(0)
cv2.destroyAllWindows()

medium

A. The dilation step is missing a kernel argument

B. The threshold 0.01 * corners.max() is too high, no pixels pass

C. The image is grayscale, so corners cannot be detected

D. The assignment img[corners > threshold] = 255 modifies the original image incorrectly

Solution

1. Step 1: Analyze the dilation step

   The line corners = cv2.dilate(corners, None) fails with a TypeError because cv2.dilate requires a kernel (e.g., np.ones((3,3), np.uint8)). None is invalid, causing the code to crash before imshow.

2. Step 2: Rule out other options

   Grayscale works fine (A wrong), 0.01 threshold is standard (B wrong), direct modification to 255 is common for grayscale marking (D ok).

3. Final Answer:

   The dilation step is missing a kernel argument -> Option A

4. Quick Check:

   cv2.dilate requires kernel [OK]

Hint: cv2.dilate needs kernel like np.ones((3,3)); None causes TypeError [OK]

Common Mistakes:

• Thinking grayscale images can't have corners
• Assuming threshold is too high
• Believing img modification is incorrect (common for grayscale)

5. You want to detect strong corners in a noisy image using Harris corner detection. Which combination of steps will best improve corner detection accuracy?

hard

A. Apply Gaussian blur before detection, use a moderate window size, and set a proper threshold to filter weak corners

B. Use raw noisy image, large window size, and low threshold for more corners

C. Apply Gaussian blur before detection, use a smaller window size, and increase threshold

D. Skip blurring, use smallest window size, and no threshold to detect all corners

Solution

1. Step 1: Understand noise impact and preprocessing

   Noise can cause false corners, so applying Gaussian blur smooths the image and reduces noise effects.

2. Step 2: Choose window size and threshold carefully

   A moderate window size balances detail and noise, and a proper threshold filters out weak corners, improving accuracy.

3. Final Answer:

   Apply Gaussian blur before detection, use a moderate window size, and set a proper threshold to filter weak corners -> Option A

4. Quick Check:

   Blur + moderate window + threshold = better corners [OK]

Hint: Blur first, then moderate window and threshold for best corners [OK]

Common Mistakes:

• Ignoring noise and skipping blur
• Using too small or too large window size
• Setting threshold too low or too high