A Novel Feature Extraction Method for Scene Recognition Based on Centered Convolutional Restricted Boltzmann Machines

TL;DR

This paper introduces CCRBM, an improved feature extraction method for scene recognition that enhances stability and generalization by incorporating centered factors into convolutional restricted Boltzmann machines, leading to better performance on natural scene datasets.

Contribution

The paper proposes CCRBM, a novel convolutional RBM variant with centered factors, improving stability and effectiveness in scene recognition tasks.

Findings

Outperforms existing methods in stability and discrimination

Shows better generalization on natural scene datasets

Effective for scene recognition with convolutional deep belief networks

Abstract

Scene recognition is an important research topic in computer vision, while feature extraction is a key step of object 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 is an improved 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 using natural scenes, MIT-indoor scenes, and Caltech 101 datasets show that the proposed approach performs better than other counterparts in terms of stability, generalization, and discrimination. The CCDBN model is more suitable for natural scene image recognition by virtue of convolutional property.