An Improved Bilinear Deep Belief Network Algorithm for Image Classification

Author

Niu Jie ; Bu Xiongzhu ; Li Zhong ; Wang Yao

Author_Institution

Sch. of Mech. Eng., Nanjing Univ. of Sci. & Technol., Nanjing, China

fYear

2014

fDate

15-16 Nov. 2014

Firstpage

189

Lastpage

192

Abstract

A novel image recognition method based on the improved BDBN (Bilinear Deep Belief Network) model is presented, optimized with a MKL (Multiple Kernel Learning) strategy. All kernel functions in MKL are replaced by hierarchical feature representations, and the number of kernels is set to the number of layers of BDBN. The method is performed on the standard Caltech101 image dataset. The experiments show that the proposed method can improve the accuracy of traditional BDBN methods by up to 2.8%, and the accuracy of the method is superior to some methods in the literature.

Keywords

belief networks; image classification; image representation; learning (artificial intelligence); visual databases; BDBN model; MKL strategy; bilinear deep belief network algorithm; hierarchical feature representations; image classification; image recognition method; multiple kernel learning strategy; standard Caltech101 image dataset; Accuracy; Classification algorithms; Computer vision; Educational institutions; Feature extraction; Image classification; Kernel; BDBN; Multiple Kernel Learning; deep learning; image classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Security (CIS), 2014 Tenth International Conference on

Conference_Location

Kunming

Print_ISBN

978-1-4799-7433-7

Type

conf

DOI

10.1109/CIS.2014.38

Filename

7016880