Share Email Print
cover

Proceedings Paper

Object detection in images with low light condition
Author(s): Roman Kvyetnyy; Roman Maslii; Volodymyr Harmash; Ilona Bogach; Andrzej Kotyra; Żaklin Grądz; Aizhan Zhanpeisova; Nursanat Askarova
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Images acquired by computer vision systems under low light conditions are characterized by the existence of noises. As a rule, it results in decreasing object detection rate. To increase the object detection rate, the proper image preprocessing algorithm is needed. The paper presents the image denoising method based on bilateral filtering and wavelet thresholding. The boosting method for object detection that uses the modified Haar-like features which include Haar-like features and symmetrical local binary patterns are proposed. The proposed algorithm allows increasing object detection rate in comparison with Viola-Jones method for a case of face detection task. The algorithm was tested on the two image sets, Yale B and the proprietary – VNTU-458.

Paper Details

Date Published: 7 August 2017
PDF: 10 pages
Proc. SPIE 10445, Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2017, 104450W (7 August 2017); doi: 10.1117/12.2281001
Show Author Affiliations
Roman Kvyetnyy, Vinnytsia National Technical Univ. (Ukraine)
Roman Maslii, Vinnytsia National Technical Univ. (Ukraine)
Volodymyr Harmash, Vinnytsia National Technical Univ. (Ukraine)
Ilona Bogach, Vinnytsia National Technical Univ. (Ukraine)
Andrzej Kotyra, Lublin Univ. of Technology (Poland)
Żaklin Grądz, Lublin Univ. of Technology (Poland)
Aizhan Zhanpeisova, M.Kh. Dulaty Taraz State Univ. (Kazakhstan)
Nursanat Askarova, Kazakh National Research Technical Univ. after K. I. Satpaev (Kazakhstan)


Published in SPIE Proceedings Vol. 10445:
Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments 2017
Ryszard S. Romaniuk; Maciej Linczuk, Editor(s)

© SPIE. Terms of Use
Back to Top