Computer Vision:Learn OpenCV & Mediapipe with 5 projects!!

Explore NumPy's mathematical functions, including addition, subtraction, trigonometric, logarithmic, exponential, square root and absolute operations, rounding, and statistics like max, min, mean, median, and standard deviation, with practical array operations.

Explore numpy array comparison and filtering: compare two arrays element-wise, use any and all, logical and/or/not, and the numpy where function to filter and substitute elements.

Explore creating multidimensional arrays with numpy, including 1D, 2D, and 3D arrays, their shapes and dimensions. Learn reshaping, flattening, and generating identity matrices, zeros, and ones for computer vision applications.

Learn to draw lines on a black image with OpenCV's cv2.line using a numpy array canvas, with blue color and thickness, then display and close the window.

Draw a rectangle on a black image using the rectangle method with image, start and opposite vertices, color, and thickness; negative thickness fills, supporting OpenCV detections and a bounding box.

Draw a circle on an image in OpenCV by specifying the image, the center coordinates, radius, color, and thickness. Increase the radius to enlarge the circle.

Learn to write text on an OpenCV image using the text method, choosing font style, size, color, and thickness, and position coordinates to display 'Hello Python'.

Learn to draw an interactive star in OpenCV using circles and lines, driven by mouse events and a mouse callback to capture points and update the star in real time.

Master the basics of cropping in computer vision by reading an image with cv2, determining its shape with numpy, and slicing to obtain precise regions.

Explore flipping in OpenCV by using cv2.flip to flip images vertically, horizontally, or both axes with flip codes 0, 1, and minus one, and compare results on sample images.

Learn image scaling and interpolation using cv2.resize, comparing linear interpolation for zooming and cubic methods, and applying area-based shrinking to resize images.

Explore erosion in OpenCV, a binary-image morphological operation driven by a neighborhood kernel that thins foreground regions and removes white noise while detaching connected objects.

Explore dilation, the opposite of erosion, which expands the foreground using a kernel to enlarge the white region and join broken parts while aiding noise removal.

Explore automatic image brightness with OpenCV by adding or subtracting pixel values using cv2.add and cv2.subtract, applying a numpy ones matrix scaled by a scalar.

Explore image blurring in computer vision by learning the averaging technique, a low-pass filter kernel applied through convolution to smooth images, reduce noise, and note that larger kernels increase blur.

Learn how to implement averaging blur in OpenCV with cv2.blur, adjust kernel size to control blur, and compare input and blurred images to understand the effect.

Learn how gaussian blur uses a gaussian window to emphasize center pixels and reduce noise with cv2 GaussianBlur, using odd kernel sizes and automatic or manual sigma.

Learn how median blurring removes salt-and-pepper noise by replacing the central pixel with the neighborhood median using a square kernel, via cv2.medianBlur.

Explore bilateral filtering in OpenCV to blur regions while preserving edges, using diameter, sigma color, and sigma space, and compare with Gaussian blurring.

Explore image thresholding as a key image segmentation technique that separates foreground from background and creates binary images from grayscale inputs.

Explore thresholding in OpenCV, including binary, binary inverse, trunc, and to-zero variants, and learn grayscale conversion and threshold application for image segmentation.

Learn to build a real-time sketch app with OpenCV in Python by capturing video, converting frames to grayscale, denoising with Gaussian blur, and using canny edge detection and thresholding.

Learn to restore damaged photos with image inpainting using OpenCV's fast marching method and a Navier–Stokes based fluid dynamics approach, including mask creation and practical coding steps.