A scene recognition method based on image complexity

Qinghuan Song; Zhongbi Chen; Shaohua Sun; Jinlong Hu; Hua Cheng

doi:10.1117/12.2069491

Translator Disclaimer

18 September 2014 A scene recognition method based on image complexity

Qinghuan Song, Zhongbi Chen, Shaohua Sun, Jinlong Hu, Hua Cheng

Author Affiliations +

Proceedings Volume 9282, 7th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment; 928221 (2014) https://doi.org/10.1117/12.2069491
Event: 7th International Symposium on Advanced Optical Manufacturing and Testing Technologies (AOMATT 2014), 2014, Harbin, China

Abstract

During the image processing, in order to solve the problem of target automatic extraction and tracking under multiple scenarios, we present a method of image complexity description, in this paper. Based on the global features about the appearance of gray level, the appearance of target and the randomness of image texture, this method describe the image complexity using the information entropy, the edge entropy and the texture entropy. The experiments show that this method could measure image complexity qualitatively. The complexity given by this method is according with the difficulty of the work to extract and track the target.

Citation Download Citation

Qinghuan Song, Zhongbi Chen, Shaohua Sun, Jinlong Hu, and Hua Cheng "A scene recognition method based on image complexity", Proc. SPIE 9282, 7th International Symposium on Advanced Optical Manufacturing and Testing Technologies: Optical Test and Measurement Technology and Equipment, 928221 (18 September 2014); https://doi.org/10.1117/12.2069491

ACCESS THE FULL ARTICLE