Fast Overlapping Block Processing Algorithm for Feature Extraction

0556266 - ÚTIA 2023 RIV CH eng J - Článek v odborném periodiku
Abdulhussain, S. H. - Mahmmod, B. M. - Flusser, Jan - AL-Utaibi, K. A.
Fast Overlapping Block Processing Algorithm for Feature Extraction.
Symmetry-Basel. Roč. 14, č. 4 (2022), č. článku 715. E-ISSN 2073-8994
Grant CEP: GA ČR GA21-03921S
Institucionální podpora: RVO:67985556
Klíčová slova: overlapping block processing * feature extraction * orthogonal polynomials * orthogonal moments
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impakt faktor: 2.7, rok: 2022
Způsob publikování: Open access
http://library.utia.cas.cz/separaty/2022/ZOI/flusser-0556266.pdf https://www.mdpi.com/2073-8994/14/4/715

In many video and image processing applications, the frames are partitioned into blocks, which are extracted and processed sequentially. In this paper, we propose a fast algorithm for calculation of features of overlapping image blocks. We assume the features are projections of the block on separable 2D basis functions (usually orthogonal polynomials) where we benefit from the symmetry with respect to spatial variables. The main idea is based on a construction of auxiliary matrices that virtually extends the original image and makes it possible to avoid a time-consuming computation in loops. These matrices can be pre-calculated, stored and used repeatedly since they are independent of the image itself. We validated experimentally that the speed up of the proposed method compared with traditional approaches approximately reaches up to 20 times depending on the block parameters.
Trvalý link: http://hdl.handle.net/11104/0330838