Practical Image Processing with OpenCV & Python with Project

Learn to draw lines, rectangles, and circles on a 300x300 3-channel uint8 OpenCV canvas, using cv2.line, cv2.rectangle, and cv2.circle with specific colors and coordinates.

Draw rectangles in OpenCV by specifying diagonal points, selecting colors, and adjusting thickness or using fill to create solid shapes.

use OpenCV and Python to draw concentric circles on a fresh canvas, computing the center from the image shape, then display the resulting bull's-eye image.

Generate 25 randomly sized and colored circles on a 300 by 300 canvas to create an abstract drawing, then display and save the result as canvas.png.

Learn to load and display video frames using OpenCV, reading a clip frame by frame, showing each frame, handling end of video, and releasing resources after pressing q.

Calculate and display the video frames per second by timing the loop and computing fps, then control the rate with a delay based on 1000 divided by the target fps.

Learn to access the web camera using OpenCV by setting the video capture index to zero for the default webcam, then switch to an external camera and observe real-time frames.

Access multiple webcams with OpenCV and Python by indexing cap0 and cap1, read their frames, and display them side by side with a horizontal stack when their frame sizes match.

Download the cascade classifier (frontal face default) for OpenCV with Python and save the XML file in your project’s model folder, then write code to apply it for face detection.

Apply a cascade classifier in OpenCV with Python to load an image, perform face detection, and enable basic real-time detection in a notebook project.

Apply the Viola-Jones cascade classifier to detect faces in images by converting to grayscale and using multi-scale detection to generate bounding boxes.

Draw a bounding box around detected faces using x, y, width, and height, copy the image, and draw a green rectangle with cv2.rectangle, using the haar cascade classifier.

Implement a face detection function in OpenCV with Python, taking an image input to output an image with detected faces, and preview applying face detection to videos.

Apply real-time face detection from webcam feed using OpenCV in Python, leveraging a cascade classifier and a loop to process frames, display results, and respond to key presses.

Discover real-time face detection with deep neural networks using OpenCV’s DNN module, featuring SSD-style single shot multi box detectors and caffe fp16 phase detection models.

Load a caffe-based ssd resnet-10 model with OpenCV in Python to perform face detection and draw a bounding box on the detected face.

Extract the blob from the image to enable phase detection and bounding box generation, resizing to 300x300 with three channels, then use blobFromImage with scale factor 1 and mean values.

Feed input to the phased reduction dnn model, run forward to obtain detections, and interpret a four-dimensional output to draw bounding boxes for faces using confidence scores to filter results.

Filter detections by a confidence score above 0.5 and draw bounding boxes on detected faces using OpenCV and Python, then print confidences and iterate detections to visualize results.

Extracts bounding box diagonal points from detections, de-normalizes coordinates by multiplying with image width and height, converts to integer points, and derives point one and point two.

Draw a green rectangle around detected faces and display the confidence percentage as text, using OpenCV with Python to annotate the image.

Create a face detection function in Python using OpenCV and a deep neural network to process an image and display the detected faces.

Demonstrates real-time phase detection of faces using a deep neural network with OpenCV, processing webcam video frames, displaying results, and handling keyboard controls and cleanup.

Explore translation by shifting images along the x and y axes with a translation matrix in OpenCV, using warpAffine. See how offsets move the image right, left, up, or down.

Explore image rotation in OpenCV with Python, using theta and scale. Compute the translation and rotation matrix around the image center and apply getRotationMatrix2D for clockwise or anticlockwise angles.

Learn to resize images with OpenCV and Python using cv2.resize, adjust size and shape, choose interpolation methods, and compare enlarged and shrunk results.

Explore image flipping with OpenCV in Python by flipping images horizontally, vertically, and both. Use flip with codes 1, -1, and 0 to generate and compare original and flipped images.

Crop the image by slicing numerical arrays to remove outer parts, using row and column ranges of 100 to 400 on a 640 by 640 image.

Learn how to perform image addition in OpenCV, handle clipping to 0–255 for 8‑bit images, and increase brightness by adding a constant to each pixel with cv2.add.

Learn how image subtraction works in OpenCV with unsigned 8-bit images, using cv2.subtract to clip negatives to zero and reduce image brightness by a constant value.

Learn to blend images in OpenCV with Python using weighted addition: alpha times image one, beta times image two, plus gamma, to achieve transparency effects.

Blend two images using OpenCV Python to create a new image with adjustable alpha and beta weights. Adjust gamma to control brightness, then save and view the blended result.

Build a simple graphical user interface in OpenCV with Python to adjust image brightness via a brightness slider, and extend the approach to video brightness control.

Learn to control image brightness using a GUI slider with OpenCV and Python, loading an image, applying brightness adjustments in real time, and displaying updated results.