RESEARCH OF DESCRIPTOR BASED IMAGE NORMALIZATION AND COMPARATIVE ANALYSIS OF SURF, SIFT, BRISK, ORB, KAZE, AKAZE DESCRIPTORS

RESEARCH OF DESCRIPTOR BASED IMAGE NORMALIZATION AND COMPARATIVE ANALYSIS OF SURF, SIFT, BRISK, ORB, KAZE, AKAZE DESCRIPTORS

Blog Article

The subject of research is image normalization based on key points analysis.The purpose is development of mathematical models and their software implementation for normalization of image geometric transformations based on the analysis of SIFT, SURF, ORB, BRISK, KAZE, AKAZE descriptors; the model application for comparative analysis of descriptors based on expert assessments of normalization quality, time costs and other indicators; construction and usage in experiments the own dataset with 100 real image pairs which contains scenes of five types: buildings, plane images outside, plane images inside, natural and artificial textures; making conclusions about the performance of Evaluation of User Experience, Cognitive Load, and Training Performance of a Gamified Cognitive Training Application for Children With Learning Disabilities the considered descriptors to solve the normalization problem.Such methods are applied: SIFT, SURF, ORB, BRISK, KAZE, AKAZE descriptors for describing key points, the Nearest Neighbor Distance Ratio method or symmetric method for search of corresponding pairs of key points from Performance measures for public transport accessibility: Learning from international practice different images, the RANSAC method for rejecting false correspondences and obtaining a homography matrix, similarity measures, software modeling.The results obtained: experimental normalization results by SIFT, SURF, ORB, BRISK, KAZE, AKAZE descriptors for 100 real pairs of own dataset (normalized images, their overlaps, quantitative descriptor evaluation, precision and recall estimation, time costs estimation, expert quality assessment, conversion of all indicator values to an 8-point rating scale); summary diagrams and conclusions about advantages and weaknesses of the compared descriptors; recommendations about the most-suitable-algorithm selection for solving normalization problem in specific cases.