Salient Region Extraction provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to extracting the salient region based on bottom-up visual attention. The main contributions are twofold: 1) Instead of the feature parallel integration, the proposed saliencies are derived by serial processing between texture and color features. Hence, the proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. 2) A constructive approach is proposed for rendering an image by a non-linear intensity mapping, which can efficiently eliminate high contrast noise regions in the image. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.
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
Congyan LANG, De XU, Shuoyan LIU, Ning LI, "Adaptive Non-linear Intensity Mapping Based Salient Region Extraction" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 4, pp. 753-756, April 2009, doi: 10.1587/transinf.E92.D.753.
Abstract: Salient Region Extraction provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to extracting the salient region based on bottom-up visual attention. The main contributions are twofold: 1) Instead of the feature parallel integration, the proposed saliencies are derived by serial processing between texture and color features. Hence, the proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. 2) A constructive approach is proposed for rendering an image by a non-linear intensity mapping, which can efficiently eliminate high contrast noise regions in the image. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.753/_p
Copy
@ARTICLE{e92-d_4_753,
author={Congyan LANG, De XU, Shuoyan LIU, Ning LI, },
journal={IEICE TRANSACTIONS on Information},
title={Adaptive Non-linear Intensity Mapping Based Salient Region Extraction},
year={2009},
volume={E92-D},
number={4},
pages={753-756},
abstract={Salient Region Extraction provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to extracting the salient region based on bottom-up visual attention. The main contributions are twofold: 1) Instead of the feature parallel integration, the proposed saliencies are derived by serial processing between texture and color features. Hence, the proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. 2) A constructive approach is proposed for rendering an image by a non-linear intensity mapping, which can efficiently eliminate high contrast noise regions in the image. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.},
keywords={},
doi={10.1587/transinf.E92.D.753},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Adaptive Non-linear Intensity Mapping Based Salient Region Extraction
T2 - IEICE TRANSACTIONS on Information
SP - 753
EP - 756
AU - Congyan LANG
AU - De XU
AU - Shuoyan LIU
AU - Ning LI
PY - 2009
DO - 10.1587/transinf.E92.D.753
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2009
AB - Salient Region Extraction provides an alternative methodology to image description in many applications such as adaptive content delivery and image retrieval. In this paper, we propose a robust approach to extracting the salient region based on bottom-up visual attention. The main contributions are twofold: 1) Instead of the feature parallel integration, the proposed saliencies are derived by serial processing between texture and color features. Hence, the proposed approach intrinsically provides an alternative methodology to model attention with low implementation complexity. 2) A constructive approach is proposed for rendering an image by a non-linear intensity mapping, which can efficiently eliminate high contrast noise regions in the image. And then the salient map can be robustly generated for a variety of nature images. Experiments show that the proposed algorithm is effective and can characterize the human perception well.
ER -