A novel feature extraction method for scene recognition based on Centered Convolutional Restricted Boltzmann Machines

NEUROCOMPUTING

卷:214

Article

Gao, Jingyu¹  Yang, Jinfu¹  Wang, Guanghui²  Li, Mingai¹ 

[1] Beijing Univ Technol, Dept Control & Engn, 100 Chaoyang Dist, Beijing 100124, Peoples R China

[2] Univ Kansas, Dept Elect Engn & Comp Sci, Lawrence, KS 66045 USA

关键词: Centered Convolution Restricted Boltzmann;    Machines;    Centering trick;    Deep belief networks;    Feature extraction;    Scene recognition;   

DOI  :  10.1016/j.neucom.2016.06.055

来源: Elsevier

【 摘 要 】

Scene recognition is an important research topic in computer vision, while feature extraction is a key step of scene recognition. Although classical Restricted Boltzmann Machines (RBM) can efficiently represent complicated data, it is hard to handle large images due to its complexity in computation. In this paper, a novel feature extraction method, named Centered Convolutional Restricted Boltzmann Machines (CCRBM), is proposed for scene recognition. The proposed model improves the Convolutional Restricted Boltzmann Machines (CRBM) by introducing centered factors in its learning strategy to reduce the source of instabilities. First, the visible units of the network are redefined using centered factors. Then, the hidden units are learned with a modified energy function by utilizing a distribution function, and the visible units are reconstructed using the learned hidden units. In order to achieve better generative ability, the Centered Convolutional Deep Belief Networks (CCDBN) is trained in a greedy layer-wise way. Finally, a softmax regression is incorporated for scene recognition. Extensive experimental evaluations on the datasets of natural scenes, MIT-indoor scenes, MIT-Places 205, SUN 397, Caltech 101, CIFAR-10, and NORB show that the proposed approach performs better than its counterparts in terms of stability, generalization, and discrimination. The CCDBN model is more suitable for natural scene image recognition by virtue of convolutional property. (C) 2016 Elsevier B.V. All rights reserved.

【 授权许可】

Free