Image classification with a new kind of shape representation

Shaowu Xu; Jun Miao; Laiyun Qing; Yuanhua Qiao; Baixian Zou

doi:10.1117/12.2513989

29 October 2018 Image classification with a new kind of shape representation

Shaowu Xu, Jun Miao, Laiyun Qing, Yuanhua Qiao, Baixian Zou

Proceedings Volume 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence; 108360I (2018) https://doi.org/10.1117/12.2513989
Event: 2018 International Conference on Image, Video Processing and Artificial Intelligence, 2018, Shanghai, China

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.

Citation Download Citation

Shaowu Xu, Jun Miao, Laiyun Qing, Yuanhua Qiao, and Baixian Zou "Image classification with a new kind of shape representation", Proc. SPIE 10836, 2018 International Conference on Image and Video Processing, and Artificial Intelligence, 108360I (29 October 2018); https://doi.org/10.1117/12.2513989

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available