Laser & Optoelectronics Progress, Volume. 55, Issue 6, 061011(2018)
Object Shape Classification Based on Bayesian Optimized Neural Network
In order to solve the problems of traditional object classification methods, such as the inaccurate expression of spatial structure features, and the classification model parameters trapped in local optimum, we propose a method that combines the overlapping pyramid method with the Bayesian optimized neural network. Firstly, we extract the contour fragments of different lenghts from the object contour as features, and encode them with the locality-constrained linear coding encoder. Then, the proposed spatial overlapping pyramid histogram is used to represent the images. Finally, the Bayesian optimized feedforward neural network classifier is used to accomplish the classification. The experimental results based on the standard Animal dataset show that the accuracy of the proposed method is improved by 1.4% as compared to the Bag of Contour Fragment method, indicating that the proposed method can accurately represent the context and structure of the shape and is effective in object classification.
Get Citation
Copy Citation Text
Shanxin Zhang, Qiang Fan, Zhiping Zhou. Object Shape Classification Based on Bayesian Optimized Neural Network[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061011
Category: Image Processing
Received: Nov. 14, 2017
Accepted: --
Published Online: Sep. 11, 2018
The Author Email: Fan Qiang ( 478581367@qq.com)