MATLAB and Digital Image Processing

Learn to acquire, read, display, and save images in MATLAB using image I/O functions. Save in different formats and load files to verify results.

Acquire images using a webcam with MATLAB's image acquisition toolbox; learn to list devices, preview live video, capture snapshots, and save image data to the workspace.

Capture a series of webcam images using get snapshot and video input, save each frame as image1, image2, image3, and store ten frames in the current folder at two-second intervals.

Practice image arithmetic in MATLAB by resizing two images to a common size and adding them using vector operations, then display the results with a subplot to illustrate the combined image.

Learn to crop images in MATLAB by loading an image, selecting a rectangular region of interest with x, y, width, and height, and applying the crop function to extract it.

Learn how point processing modifies images by mapping each pixel's value to a new image, iterating across rows and columns to apply pixel-wise transformations.

Implement thresholding in MATLAB by writing your own code to convert images to grayscale, loop over pixels, and set values to 0 or 255 for pixels within 25 to 100.

Explore bit manipulation in MATLAB to convert a grayscale image to binary using user-specified values, process each pixel, and display the resulting image.

Explore sliding neighborhood operations in MATLAB for image processing, including block processing, low-pass filtering to reduce noise, and edge sharpening with averaging and median filters.

Design a custom low pass filter in MATLAB to remove noise from an image, adjust data types, apply noise with imnoise, and visualize the filtering results.

Develop and call your own median filter function in MATLAB to smooth images. Convert images to grayscale, manage input and output arguments, and test results across RGB planes.

Explore sobel, prewitt, roberts, and LoG edge detection in MATLAB using the edge function on a grayscale image, and compare results with subplot to visualize edges.

Design and implement a Sobel operator from scratch to detect edges by computing gradients from neighborhood values and produce edge-rich images.

Learn how dilation and erosion, driven by a structuring element, clean binary and grayscale images, fill holes, connect or disconnect regions, and perform closing and opening for segmentation.

Explore MATLAB code for dilation and erosion using structuring elements, including diamond and square shapes, applying imdilate and imerode to binary images, with resizing before processing.

Explore color images and color spaces such as RGB, HSV, YCbCr and NTSC, including grayscale intensity, 24-bit RGB pixels, and decoupled hue, saturation, and brightness concepts.

Convert an RGB image to the YCbCr color space using the standard formula, then separate and visualize the Y, Cb, and Cr components with scaled and grayscale representations.

Process each color plane (red, green, blue) with histogram equalization in MATLAB, then combine the channels and display the resulting color image.

Sharpen images by applying a custom structuring element to red, green, and blue channels, then concatenate them into the final image. Change the structuring element to see different sharpening effects.

Learn color segmentation in MATLAB using RGB model and a distance formula within a specified range to decide if a pixel belongs to the same region as initial box.

Explore color segmentation using the HSV model to isolate hues, thresholds, and ranges from images, converting from RGB to HSV and applying selective value ranges for precise masking.