Year: 2013
Type: preprint
Abstract: The first contribution of this paper is architecture of a multipurpose system, which delegates a range of object detection tasks to a classifier, applied in special grid positions of the tested image. The second contribution is Gray Level-Radius Co-occurrence Matrix, which describes local image texture and topology and, unlike common second order statistics methods, is robust to image resolution. The third contribution is a parametrically controlled automatic synthesis of unlimited number of numerical features for classification. The fourth contribution is a method of optimizing parameters C and gamma in LibSVM-based classifier, which is 20-100 times faster than the commonly applied method. The work is essentially experimental, with demonstration of various methods for definition of objects of interest in images and video sequences.
Source: arXiv (Cornell University)
Author: Gleibman, Andrew
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1758970381