An algorithm of image classification based on BP neural network

Author

Xiong, Zhiyong ; Chen, Ke ; Gu, Caidong ; Liang, Yinhong ; Yu, Fusheng

Author_Institution

JiangSu Province Support Software Eng. R&D, Center for Modern Inf. Technol. Applic. in Enterprise, Suzhou, China

Volume

1

fYear

2012

fDate

25-27 May 2012

Firstpage

523

Lastpage

526

Abstract

To improve the performance of image classification, we propose an image classification method based on BP neural network. Firstly, one image is segmented and clustered several visual objects. By means of the unit image library, we calculate one probability vector, which is composed by probability of every visual object of the image and every unit image of the unit image library. So a total feature vector of one image can been attain. By means of the BP neural network, which we construct, we attain a class about the image, thereby we can realize image classification. The end, Ground Truth Database is adopted experimental image library in this paper. The method attains good effect based on experimental result.

Keywords

backpropagation; image classification; image segmentation; neural nets; pattern clustering; probability; vectors; BP neural network; experimental image library; ground truth database; image classification; image segmentation; probability vector; unit image library; visual object clustering; Algorithm design and analysis; Classification algorithms; Image classification; Libraries; Neural networks; Support vector machine classification; Training; BP neural network; content vector; feature vector; image classification; unit image;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Science and Automation Engineering (CSAE), 2012 IEEE International Conference on

Conference_Location

Zhangjiajie

Print_ISBN

978-1-4673-0088-9

Type

conf

DOI

10.1109/CSAE.2012.6272651

Filename

6272651