OpenCV cheat sheet

A scannable OpenCV reference: 6 short snippets across 3 topics, each linking back to the lesson it came from.

At a glance

Quick snippets

Reading, writing and inspecting images

Load and save

import cv2

img = cv2.imread("photo.jpg")                 # BGR order, dtype uint8
if img is None:
    raise SystemExit("could not read photo.jpg - missing file, wrong path or unsupported format")

print(img.shape, img.dtype)                   # (1080, 1920, 3) uint8

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)  # shape (1080, 1920)
ok = cv2.imwrite("out/gray.png", gray)        # returns True/False, never raises
print(ok)

Indexing, colour and resizing

# Slicing is (y, x) - rows first, then columns
crop = img[100:250, 300:500]                 # region of interest, a view not a copy

cv2.rectangle(img, (300, 100), (500, 250), (0, 255, 0), 2)   # (x1, y1), (x2, y2)
cv2.putText(img, "plate", (300, 92), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 1)

small = cv2.resize(img, (640, 360), interpolation=cv2.INTER_AREA)   # shrink
big = cv2.resize(small, None, fx=2, fy=2, interpolation=cv2.INTER_CUBIC)   # enlarge

Full lesson: Reading, writing and inspecting images →

Filters and edge detection

Smoothing before anything else

gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

gauss = cv2.GaussianBlur(gray, (5, 5), sigmaX=1.4)    # kernel size must be odd
median = cv2.medianBlur(gray, 5)                      # great against speckle
bilateral = cv2.bilateralFilter(gray, 9, 75, 75)      # slow, but preserves edges

print(gauss.shape, bilateral.shape)                   # same spatial size as input

Gradients and Canny

# Magnitude of the gradient: an edge is a place where brightness changes fast
gx = cv2.Sobel(gray, cv2.CV_32F, 1, 0, ksize=3)
gy = cv2.Sobel(gray, cv2.CV_32F, 0, 1, ksize=3)
magnitude = cv2.magnitude(gx, gy)              # float - uint8 would saturate at 255

# Canny keeps strong edges, then keeps weak ones only if linked to a strong one
edges = cv2.Canny(gauss, threshold1=80, threshold2=160)
print(edges.shape, edges.dtype, edges.max())   # single channel, uint8, 255 at an edge

Full lesson: Filters and edge detection →

Contours and object detection basics

Threshold, find, filter

_, mask = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5, 5)))

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

kept = [c for c in contours if cv2.contourArea(c) > 500]    # drop noise specks
for c in kept:
    x, y, w, h = cv2.boundingRect(c)
    area = cv2.contourArea(c)
    circularity = 4 * 3.14159 * area / (cv2.arcLength(c, True) ** 2)
    cv2.rectangle(img, (x, y), (x + w, y + h), (0, 255, 0), 2)
    print(x, y, w, h, round(circularity, 2))                # near 1.0 means a circle

When a threshold is not enough

# A trained detector via cv2.dnn: same preprocessing contract as the training pipeline
net = cv2.dnn.readNetFromONNX("yolov8n.onnx")
blob = cv2.dnn.blobFromImage(frame, scalefactor=1 / 255.0, size=(640, 640),
                             mean=(0, 0, 0), swapRB=True, crop=False)
net.setInput(blob)
outputs = net.forward()          # shape depends on the exported model - inspect it

for det in outputs[0].T:         # [x, y, w, h, class scores...]
    scores = det[4:]
    class_id = int(scores.argmax())
    if scores[class_id] > 0.4:
        print(class_id, round(float(scores[class_id]), 3))

Full lesson: Contours and object detection basics →

FAQ

Related cheat sheets

AI Basics AI Agents Math for AI Machine Learning scikit-learn TensorFlow

Last refreshed 2026-09-27.