Computer Vision {{ currentPage ? currentPage.title : "" }}

What are major algorithms for computer vision?

  • SIFT and SURF for feature-point extraction. Used for object recognition, Image registration.

  • Viola-Jones algorithm, for object (especially face) detection in real time. One of the most elegant algorithms, one of my favorites.

  • 'Eigenfaces' approach, using PCA for dimension reduction. Used in face recognition. Has a very intuitive approach and yet it is mathematically strong.

  • Lucas-Kanade algorithm for optical flow calculation. Used for tracking, stereo registration. Also the Horn-Schunk algorithm.

  • Mean-shift algorithm for fast tracking of object. Not very robust, but easy to use, and very useful in specific applications.

  • Kalman filter, again for object tracking, using point features for tracking. Great use in many fields like computer vision, control systems, etc.

  • Adaptive thresholding (and other thresholding techniques), because thresholding is much more important than thought.

  • Machine learning algorithms like SVM's, KNN, Naive Bayes, etc. are also very important in the field of computer vision.

  • Iterative Closest Point (ICP) to co-register two or more 3D pointclouds together

  • Semi Global Matching (SGM) and Semi Global Block Matching (SGBM) algorithms which generate a depth image from stereo images

  • Feature Point Histograms for detecting features in 3D space

Tutorial Videos

{{{ content }}}