Faster method for Deep Belief Network based Object classification using DWT

TL;DR

This paper introduces a faster object classification method by integrating Deep Belief Networks with Discrete Wavelet Transform, reducing training time and computational complexity while maintaining performance.

Contribution

The paper proposes a novel approach combining DWT with DBNs and a weighted voting scheme to improve speed and efficiency in object classification.

Findings

Reduced training time compared to traditional DBNs

Maintained classification accuracy with lower computational cost

Effective integration of DWT and DBNs for image processing

Abstract

A Deep Belief Network (DBN) requires large, multiple hidden layers with high number of hidden units to learn good features from the raw pixels of large images. This implies more training time as well as computational complexity. By integrating DBN with Discrete Wavelet Transform (DWT), both training time and computational complexity can be reduced. The low resolution images obtained after application of DWT are used to train multiple DBNs. The results obtained from these DBNs are combined using a weighted voting algorithm. The performance of this method is found to be competent and faster in comparison with that of traditional DBNs.