Computer Vision with Python

Learn to read, write, and display images in Python using OpenCV, including loading sample images, handling file paths, and converting images to grayscale or color with BGR channels.

Learn to read, write, and show images from a webcam by capturing video frames, displaying them, and saving photos in a Python computer vision workflow.

Draw lines, rectangles, and text on images using Python, while adjusting coordinates, colors, thickness, and font to annotate and edit visuals in computer vision projects.

Learn mouse event handling to build interactive image tools for computer vision with Python, including selecting areas, drawing rectangles, left and right clicks, and coordinates.

Explore arithmetic operations on images, applying addition, multiplication, and division to pixel values. Learn how these operations affect brightness, color intensities, and image shapes with saturation up to 255.

Apply image translation using a translation matrix to shift pixels along the x and y axes, enabling animated motion. Explore origin changes and destination images.

Apply a rotation matrix to an image by specifying an angle, explore rotating the image by 90 degrees, and observe how axis choice and angle affect the result.

Explore image scaling in computer vision with Python, comparing upscaling and downscaling and how interpolation methods like nearest and cubic affect detail and accuracy.

Explore blurring and smoothing techniques that reduce image noise with kernels from 5x5 to 9x9, including mean, median, and bilateral filters.

Explore image sharpening techniques by applying edge-enhancing kernels to emphasize edges, reduce blur, and manage border effects, using different matrix sizes and values.

Explore thresholding as a key image processing technique to separate foreground from background, using binary thresholding and a chosen value to convert images to black-and-white.

Learn adaptive thresholding in image processing with two methods—mean and gaussian—adjusting block size and a constant to compensate for varying illumination and produce clear binary results.

Apply erosion and dilation to images to modify edges and boundaries using morphological operations; explore opening and closing with kernels and iterations to refine shapes.

Learn edge detection to identify object outlines by highlighting edges, adjust thresholds to refine edge clarity, and compare grayscale and binary results on faces and various images.

Explore image pyramids in computer vision by downscaling and upscaling images, observing blur and detail loss, and applying blending and subtraction across scales to reveal features.

Explore image blending with pyramid-based techniques to merge apple and orange into a single composite, addressing size, edges, and reconstruction.

learn how contours form around object edges to draw boundaries. apply thresholding and grayscale steps to detect, outline, and compare shapes for object detection.

Learn to detect, sort, and analyze contours in Python using OpenCV, identify the largest and smallest contours by area, and label them for image processing tasks.

Learn to match contours using template shapes to detect and recognize objects in images, with grayscale preprocessing, thresholding, and contour-based similarity methods.

Demonstrate creating a live sketch from webcam video by converting frames to black-and-white and applying thresholding and edge detection. Tune on-screen thresholds to optimize sketch quality under varying lighting.