Page 1 of 9

Table of Contents
OpenCV Python Image Processing Cheat Sheet
1. Installation

2. Read, Write, and Display Images

3. Resize & Crop

4. Convert Color Spaces

5. Drawing Shapes

6. Image Thresholding

7. Blurring & Smoothing

8. Edge Detection

9. Morphological Operations

10. Contours Detection

11. Object Detection with Haar Cascades

12. Perspective Transformation

13. Histogram Equalization

14. Bitwise Operations

15. Template Matching

16. Optical Flow (Motion Tracking)

17. Video Capture & Processing

18. Background Subtraction

19. Image Translation (Shifting)

20. Image Rotation

OpenCV Python Image Processing Cheat Sheet

Make me a cheetsheet on opencv py for image proccessing

 Page 2 of 9
Here's a cheat sheet for OpenCV (Python) for image processing covering the most common operations:

OpenCV Python Image Processing Cheat

Sheet
1. Installation
bash

pip install opencv-python numpy

python

import cv2
import numpy as np

2. Read, Write, and Display Images

python

img = cv2.imread('image.jpg') # Read image

cv2.imshow('Image', img) # Display image
cv2.waitKey(0) # Wait for key press
cv2.destroyAllWindows() # Close window

cv2.imwrite('output.jpg', img) # Save image

3. Resize & Crop

python

resized = cv2.resize(img, (300, 300)) # Resize to 300x300

cropped = img[50:200, 100:300] # Crop ROI (y1:y2, x1:x2)

4. Convert Color Spaces

python
 Page 3 of 9

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Convert to grayscale

hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV) # Convert to HSV
lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB) # Convert to LAB

5. Drawing Shapes
python

cv2.line(img, (50, 50), (200, 50), (0, 255, 0), 3) # Line

cv2.rectangle(img, (50, 50), (200, 200), (255, 0, 0), 2) # Rectangle
cv2.circle(img, (150, 150), 50, (0, 0, 255), -1) # Filled Circle
cv2.putText(img, 'OpenCV', (50, 250), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2)

6. Image Thresholding
python

_, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY) # Simple Threshold

adaptive = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
cv2.THRESH_BINARY, 11, 2) # Adaptive Threshold

7. Blurring & Smoothing

python

blurred = cv2.GaussianBlur(img, (5, 5), 0) # Gaussian Blur

median = cv2.medianBlur(img, 5) # Median Blur
bilateral = cv2.bilateralFilter(img, 9, 75, 75) # Bilateral Filtering

8. Edge Detection
python

edges = cv2.Canny(gray, 50, 150) # Canny Edge Detection

9. Morphological Operations
 Page 4 of 9
python

kernel = np.ones((5, 5), np.uint8)

dilated = cv2.dilate(binary, kernel, iterations=1) # Dilation
eroded = cv2.erode(binary, kernel, iterations=1) # Erosion
opened = cv2.morphologyEx(binary, cv2.MORPH_OPEN, kernel) # Opening (erosion + dilation)
closed = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel) # Closing (dilation + erosion)

10. Contours Detection

python

contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

cv2.drawContours(img, contours, -1, (0, 255, 0), 2) # Draw all contours

11. Object Detection with Haar Cascades

python

face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)

12. Perspective Transformation

python

pts1 = np.float32([[50, 50], [200, 50], [50, 200], [200, 200]])

pts2 = np.float32([[10, 100], [180, 50], [50, 250], [220, 220]])
matrix = cv2.getPerspectiveTransform(pts1, pts2)
transformed = cv2.warpPerspective(img, matrix, (300, 300))

13. Histogram Equalization

python

equalized = cv2.equalizeHist(gray)
14. Bitwise Operations
Page 5 of 9

python

bitwise_and = cv2.bitwise_and(img1, img2)

bitwise_or = cv2.bitwise_or(img1, img2)
bitwise_xor = cv2.bitwise_xor(img1, img2)
bitwise_not = cv2.bitwise_not(img1)

15. Template Matching

python

template = cv2.imread('template.jpg', 0)
res = cv2.matchTemplate(gray, template, cv2.TM_CCOEFF_NORMED)
min_val, max_val, min_loc, max_loc = cv2.minMaxLoc(res)
top_left = max_loc
bottom_right = (top_left[0] + template.shape[1], top_left[1] + template.shape[0])
cv2.rectangle(img, top_left, bottom_right, (0, 255, 0), 2)

16. Optical Flow (Motion Tracking)

python

old_gray = cv2.cvtColor(prev_frame, cv2.COLOR_BGR2GRAY)

new_gray = cv2.cvtColor(curr_frame, cv2.COLOR_BGR2GRAY)
flow = cv2.calcOpticalFlowFarneback(old_gray, new_gray, None, 0.5, 3, 15, 3, 5, 1.2, 0)

17. Video Capture & Processing

python

cap = cv2.VideoCapture(0) # Capture from webcam

while True:
ret, frame = cap.read()
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
cv2.imshow('Video', gray)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
18. Background Subtraction
Page 6 of 9

python

fgbg = cv2.createBackgroundSubtractorMOG2()
fgmask = fgbg.apply(frame)

19. Image Translation (Shifting)

python

M = np.float32([[1, 0, 100], [0, 1, 50]])

shifted = cv2.warpAffine(img, M, (img.shape[1], img.shape[0]))

20. Image Rotation

python

(h, w) = img.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, 45, 1.0) # Rotate by 45 degrees
rotated = cv2.warpAffine(img, M, (w, h))

This cheat sheet should help you quickly reference image processing techniques using OpenCV in
Python! Let me know if you need any specific implementations.

Ummm nice actually... Now this time in a tabular format with all
the details like what the purpose

Here's your OpenCV Python Image Processing Cheat Sheet in a tabular format, including the
operation, purpose, and example code for easy reference.

OpenCV Python Image Processing Cheat Sheet

Operation Purpose Example Code
Install OpenCV Install OpenCV and pip install opencv-python numpy

NumPy for image

 Page 7 of 9

Operation Purpose Example Code

processing

Read an Image Load an image from file img = cv2.imread('image.jpg')

Display an Image Show the loaded image cv2.imshow('Image', img); cv2.waitKey(0);

in a window cv2.destroyAllWindows()

Save an Image Save an image to a file cv2.imwrite('output.jpg', img)

Resize an Image Change image resized = cv2.resize(img, (300, 300))

dimensions

Crop an Image Extract a region of cropped = img[50:200, 100:300]

interest (ROI)

Convert to Grayscale Convert an image to gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

black and white

Convert to HSV Convert image to HSV hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)

color space

Draw a Line Draw a straight line on cv2.line(img, (50,50), (200,50), (0,255,0), 3)

an image

Draw a Rectangle Draw a rectangle cv2.rectangle(img, (50,50), (200,200), (255,0,0), 2)

(bounding box)

Draw a Circle Draw a filled or outlined cv2.circle(img, (150,150), 50, (0,0,255), -1)

circle

Write Text on Image Overlay text on an image cv2.putText(img, 'OpenCV', (50,250), cv2.FONT_HERSHEY_SIMPLEX,
1, (0,255,255), 2)

Simple Thresholding Convert grayscale image _, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

to binary

Adaptive Adjust threshold adaptive = cv2.adaptiveThreshold(gray, 255,

Thresholding dynamically cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY, 11, 2)

Gaussian Blur Reduce noise and blurred = cv2.GaussianBlur(img, (5,5), 0)

smooth an image

Median Blur Remove salt-and-pepper median = cv2.medianBlur(img, 5)

noise

Bilateral Filter Preserve edges while bilateral = cv2.bilateralFilter(img, 9, 75, 75)

blurring

Edge Detection Detect edges in an image edges = cv2.Canny(gray, 50, 150)

(Canny)
 Page 8 of 9

Operation Purpose Example Code

Dilation Expand white regions in dilated = cv2.dilate(binary, np.ones((5,5), np.uint8), iterations=1)

an image

Erosion Shrink white regions in eroded = cv2.erode(binary, np.ones((5,5), np.uint8), iterations=1)

an image

Find Contours Detect objects in an contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL,

image cv2.CHAIN_APPROX_SIMPLE)

Draw Contours Highlight detected cv2.drawContours(img, contours, -1, (0,255,0), 2)

contours

Face Detection Detect faces using Haar faces = face_cascade.detectMultiScale(gray, 1.3, 5)

cascades

Perspective Warp an image to a new transformed = cv2.warpPerspective(img, matrix, (300,300))

Transformation perspective

Histogram Improve contrast in equalized = cv2.equalizeHist(gray)

Equalization grayscale images

Bitwise AND Perform AND operation bitwise_and = cv2.bitwise_and(img1, img2)

on two images

Bitwise OR Perform OR operation on bitwise_or = cv2.bitwise_or(img1, img2)

two images

Template Matching Detect object locations in res = cv2.matchTemplate(gray, template,

an image cv2.TM_CCOEFF_NORMED)

Optical Flow (Motion Detect motion between flow = cv2.calcOpticalFlowFarneback(old_gray, new_gray, None,

Tracking) frames 0.5, 3, 15, 3, 5, 1.2, 0)

Open Webcam Video Capture video from the cap = cv2.VideoCapture(0)

webcam

Display Video Feed Show video frame-by- cv2.imshow('Video', frame)

frame

Background Detect foreground fgmask = fgbg.apply(frame)

Subtraction objects

Translate Image Move an image up/down shifted = cv2.warpAffine(img, M, (img.shape[1], img.shape[0]))

(Shift Position) or left/right

Rotate Image Rotate an image by any rotated = cv2.warpAffine(img, M, (w, h))

angle
 Page 9 of 9
This table provides a quick reference to OpenCV's key functions for image processing. Let me know if
you need further details or modifications!