Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK)

Qinhuangdao,China,7.9-7.13,2010

ISBN: 978-1-935068-15-0 Scientific Research Publishing, USA

E-Book 840pp Pub. Date: July 2010

Category: Computer Science & Communications

Price: $120

Title: A New Algorithm of Extracting Top-Down Attention Information
Source: Proceedings of 2010 Cross-Strait Conference on Information Science and Technology (CSCIST 2010 E-BOOK) (pp 555-559)
Author(s): Mei Tian, School of Computer & Information Technology, Beijing Jiaotong University, Beijing, 100044
Qi Zou, School of Computer & Information Technology, Beijing Jiaotong University, Beijing, 100044
Yaping Huang, School of Computer & Information Technology, Beijing Jiaotong University, Beijing, 100044
Hui Yin, School of Computer & Information Technology, Beijing Jiaotong University, Beijing, 100044
Abstract: A novel algorithm is proposed for extracting top-down attention information. Three procedures are carried out in algorithm: 1) extracting high dimensional code of top-down attention information; 2) sub- sampling the high dimensional code of top-down attention information; 3) computing statistical feature of subsampled high dimensional code of top-down attention information. The final coefficient of statistical feature is defined as top-down attention information. The top-down attention information can motivate top-down attention and process contextual information over a large area. The information of entire scene is coded in the top-down attention information. It can provide reliable prior knowledge for bottom-up attention.
Free SCIRP Newsletters
Copyright © 2006-2024 Scientific Research Publishing Inc. All Rights Reserved.
Top