Improved Itti Visual Saliency Detection Based on Multi-scale Tensor Space

Authors

Shimin Wang, College of Computer Information and Engineering, Jiangxi Normal University, Nanchang 330022, China;
Jihua Ye, College of Computer Information and Engineering, Jiangxi Normal University, Nanchang 330022, China;
Bailiang Cheng, College of Computer Information and Engineering, Jiangxi Normal University, Nanchang 330022, China;
Mingwen Wang, College of Computer Information and Engineering, Jiangxi Normal University, Nanchang 330022, China;

Abstract

Abstract: In view of internal dense uniform and clear borders image, through the saliency detection the target boundary is vague, so that the target object is not connected. In order to solve this problem, an improved Itti visual saliency detection method based on multi-scale tensor space was proposed. The method introduced the tensor space features, which preserved the original image spatial structure and correlation features, that could extract internal dense uniform image features, which made the target object connect, combining with saliency detection algorithm to finish feature extraction and target detection. Experimental results show that the proposed method can clearly and accurately extract saliency regions and achieve better detection results.

Recommended Citation

Wang, Shimin; Ye, Jihua; Cheng, Bailiang; and Wang, Mingwen (2020) "Improved Itti Visual Saliency Detection Based on Multi-scale Tensor Space," Journal of System Simulation: Vol. 28: Iss. 9, Article 32.
Available at: https://dc-china-simulation.researchcommons.org/journal/vol28/iss9/32

First Page

2138

Revised Date

2016-07-11

DOI Link

https://doi.org/

Last Page

2145

CLC

TP301

Recommended Citation

Wang Shimin, Ye Jihua, Cheng Bailiang, Wang Mingwen. Improved Itti Visual Saliency Detection Based on Multi-scale Tensor Space[J]. Journal of System Simulation, 2016, 28(9): 2138-2145.