Share Email Print
cover

Proceedings Paper

Image classification with a new kind of shape representation
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

As one of the research hotspots in recent years, especially in pattern recognition, Convolutional Neural Network (CNN) is widely known for its high efficiency. However some researches show that there is a problem in the CNN which cannot learn the high-level features. In order to solve this problem, this paper proposes a new kind of image representation, which we call it “shape encoding maps”. Our experimental results show that, in most cases, the recognition accuracies obtained by inputting the shape encoded maps to a CNN are higher than that of using the original image data for a CNN to learn directly without shape encoding.

Paper Details

Date Published: 29 October 2018
PDF: 7 pages
Proc. SPIE 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence, 108360I (29 October 2018); doi: 10.1117/12.2513989
Show Author Affiliations
Shaowu Xu, Beijing Information Science and Technology Univ. (China)
Jun Miao, Beijing Information Science and Technology Univ. (China)
Laiyun Qing, Univ. of Chinese Academy of Sciences (China)
Yuanhua Qiao, Beijing Univ. of Technology (China)
Baixian Zou, Beijing Union Univ. (China)


Published in SPIE Proceedings Vol. 10836:
2018 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top