Research on Image Scene Semantics Recognition System

Abstract:

In order to get better image Semantics recognition, in this paper, a scene Semantics recognition system based on fuzzy reasoning is presented. The system contains three parts: image preprocessing, target recognition, and fuzzy reasoning machine. Compared with other methods, the outputs of pattern classifiers are fuzzed, the fuzzy relationships between targets are extracted, and fuzzy inference is performed using fuzzy automata. The experiment indicates that this method could overcome the problems of false positive and false negative of pattern classifiers, and perform relatively more accurate image semantics recognition than other existing methods.

• Periodical: Applied Mechanics and Materials (Volumes 433-435)
• Pages: 330-333
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.433-435.330
• Online since: October 2013
• Authors: Li Jie Yin*, Ya Zhen, Qi Li Fan
• Keywords: Fuzzy Reasoning, Pattern Recognition, Scene Semantics Recognition

References

[1] Viola P., Rapid Target Detection Using a Boosted Cascade of Simple Features, Proc IEEE Conference on Computer Vision and Pattern Recognition, 2001, 511-518.

DOI: 10.1109/cvpr.2001.990517

[2] LI F. Z., HU K. H., Proceeding of Non-rigid Motion Analysis, Journal of Image and Graphics, 2005, 10(1): 12-13.

[3] Dalal N., Triggs B., Histograms of Oriented Gradients for Human Detection, IEEE International Conference on Computer Vision and Pattern Recognition, 2005, 886-893.

DOI: 10.1109/cvpr.2005.177

[4] Dalal N., Finding People in Images and Videos, Institute National Poly technique de Grenoble, (2006).

[5] Duan L. J., Cui G. Q., Gao W., etc. A Hierarchical Method for Nude Image Filtering, Journal of Computer Aided Design & Computer Graphics, 2002, 14(5): 404-409.

[6] Yin X. D., Tang D., Deng J., etc. Content-based Method for Nude Image Filtering, Computer Automated Measurement & Control, 2004, 12(3): 283-286.