Image processing is a key part of computer vision algorithms. The tutorials describe how to process and extract various image features. Each manual provides a detailed description and sample source code of various image processing algorithms.
The watershed transform is a computer vision algorithm that serves for image segmentation. This method can extract image objects and separate foreground from background. This tutorial shows how can implement Watershed transformation via Meyer’s flooding algorithm.
The Skin Detection and Segmentation is a process of finding skin-colored image regions from video frames or still pictures. Typically this is a preprocessing step in the digital image analysis to find significant regions such as body, hands, faces, etc.
The Symmetric Nearest Neighbor Filter (SNN) is a non-linear edge preserving image processing filter. It is a very effective noise reduction technique that removes noise while maintaining sharp image edges. This graphic filter produce results very close to these of Median and Kuwahara filters.
The gradient Non-maximum suppression also known as edge thinning is a process of extracting thin, one pixel wide object’s contours. This process follows edge detection as a post processing step. The non-maximum contour suppression is one of the main steps of the popular Canny edge detector.
The Sobel filter (also called Sobel-Feldman operator) is an edge detection algorithm, that results in image emphasizing edges. Computer vision apps often use this image processing technique to extract the objects contours.
The Median filter is a nonlinear noise reduction technique that is widely used in image processing. It is very effective in cases of salt and paper noise (impulsive noise) and speckle noise. However, in cases of high noise levels, its performance becomes compatible with Gaussian blur filtering.