A robust saliency detection approach for images with a complex background is proposed. The absorbing Markov chain integrating low-level, mid-level and high-level cues dynamically evolves by using the similarity between pixels to detect saliency objects. The experimental results show that the proposed algorithm has advantages in saliency detection, especially for images with a chaotic background or low contrast.
Pengfei LV
Northeastern University
Xiaosheng YU
Northeastern University
Jianning CHI
Northeastern University
Chengdong WU
Northeastern University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Pengfei LV, Xiaosheng YU, Jianning CHI, Chengdong WU, "Saliency Detection via Absorbing Markov Chain with Multi-Level Cues" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 6, pp. 1010-1014, June 2022, doi: 10.1587/transfun.2021EAL2071.
Abstract: A robust saliency detection approach for images with a complex background is proposed. The absorbing Markov chain integrating low-level, mid-level and high-level cues dynamically evolves by using the similarity between pixels to detect saliency objects. The experimental results show that the proposed algorithm has advantages in saliency detection, especially for images with a chaotic background or low contrast.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021EAL2071/_p
Copy
@ARTICLE{e105-a_6_1010,
author={Pengfei LV, Xiaosheng YU, Jianning CHI, Chengdong WU, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Saliency Detection via Absorbing Markov Chain with Multi-Level Cues},
year={2022},
volume={E105-A},
number={6},
pages={1010-1014},
abstract={A robust saliency detection approach for images with a complex background is proposed. The absorbing Markov chain integrating low-level, mid-level and high-level cues dynamically evolves by using the similarity between pixels to detect saliency objects. The experimental results show that the proposed algorithm has advantages in saliency detection, especially for images with a chaotic background or low contrast.},
keywords={},
doi={10.1587/transfun.2021EAL2071},
ISSN={1745-1337},
month={June},}
Copy
TY - JOUR
TI - Saliency Detection via Absorbing Markov Chain with Multi-Level Cues
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1010
EP - 1014
AU - Pengfei LV
AU - Xiaosheng YU
AU - Jianning CHI
AU - Chengdong WU
PY - 2022
DO - 10.1587/transfun.2021EAL2071
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2022
AB - A robust saliency detection approach for images with a complex background is proposed. The absorbing Markov chain integrating low-level, mid-level and high-level cues dynamically evolves by using the similarity between pixels to detect saliency objects. The experimental results show that the proposed algorithm has advantages in saliency detection, especially for images with a chaotic background or low contrast.
ER -