Study on Rotary Object Recognition Technique from the Complex Background

Abstract:

Target recognition from complex background is the emphasis and difficulty of computer vision, and rotary objects is widely used in the military and manufacturing field. Rotary object recognition in complex background based on improved BP neural network is proposed in the dissertation. Median filter is adopted to get rid of the noise and an improved method of maximum classes square error is used to compute the threshold of the image segmentation. The target recognition system based on improved BP neural network is established to recognize the rotary objects, and seven invariant moments of rotary objects serve as the input feature vector. The experiment results show that the image noise could be gotten rid of effectively and the image could be segmented exactly by the image preprocessing method put forward in the dissertation, and the seven invariant moments is appropriate for the character of rotary objects, and the rotary object recognition system based on BP neural network acquires an excellent recognition result.

• Periodical: Advanced Materials Research (Volumes 418-420)
• Pages: 494-500
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.418-420.494
• Online since: December 2011
• Authors: Bao Zhang Li, Mo Yu Sha, Yan Ping Cui
• Keywords: BP Neural Network (BPNN), Complex Background, Invariant Moment, Rotary Object, Target Recognition

References

[1] ZHANG Hong-tao, DUAN Fa-jie: Acta Metrologica Sinica, 2002, 23(4), pp.263-266

[2] Ghosal S, Mehrotra R: Pattern Recognition, 1993, 26(2): pp.295-306

[3] Liu Xiangdong, Ehrich R W, :IEEE Trans. on Pattern Analysis and Machine Intelligence, 1995, 17(6) , pp.629-634

DOI: 10.1109/34.387511

[4] ZHANG Yong-hong, HU De-jin, XU Jun-jie: Chinese Journal of Mechanical Engneering, 2004, 40(6), pp.179-182.(In Chinese)

[5] Shen Li-qin, Shen Ding-gang, Qi fei-hu: IEEE International Symposium on Speech, Image Processing and Neural Network, 1994, 1, pp.37-40

[6] Edward P. Lyvers, Owen Robert Mitchell, Mark L. Akey: IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(12) , pp.1293-1309

DOI: 10.1109/34.41367