Bottom-up saliency detection with sparse representation of learnt texture atoms

被引:16
作者
Xu, Mai [1 ]
Jiang, Lai [1 ]
Ye, Zhaoting [1 ]
Wang, Zulin [1 ,2 ]
机构
[1] Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China
[2] Collaborat Innovat Ctr Geospatial Technol, 129 Luoyu Rd, Wuhan 430079, Peoples R China
基金
中国国家自然科学基金;
关键词
Visual attention; Saliency detection; Sparse representation; Dictionary learning; VISUAL SALIENCY; ATTENTION; RECONSTRUCTION;
D O I
10.1016/j.patcog.2016.05.023
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper proposes a saliency detection method by exploring a novel low level feature on sparse representation of learnt texture atoms (SR-LTA). The learnt texture atoms are encoded in salient and non salient dictionaries. For salient dictionary, a formulation is proposed to learn salient texture atoms from image patches attracting extensive attention. Then, the online salient dictionary learning (OSDL) algorithm is presented to solve the proposed formulation. Similarly, the non-salient dictionary is learnt from image patches without any attention. Then, the pixel-wise SR-LTA feature is yielded based on the difference of sparse representation errors, regarding the learnt salient and non-salient dictionaries. Finally, image saliency can be predicted by linearly combining the proposed SR-LTA feature and conventional features, luminance and contrast. For the linear combination, the weights of different feature channels are determined by least square estimation on the training data. The experimental results show that our method outperforms 9 state-of-the-art methods for bottom-up saliency detection. (C) 2016 Elsevier Ltd. All rights reserved.
引用
收藏
页码:348 / 360
页数:13
相关论文
共 49 条
[1]  
Anantrasirichai N, 2015, IEEE IMAGE PROC, P3957, DOI 10.1109/ICIP.2015.7351548
[2]  
[Anonymous], 1987, Shifts in selective visual attention: Towards the underlying neural circuitry. matters of intelligence
[3]  
[Anonymous], P AS C COMP VIS
[4]  
[Anonymous], 2008, 2008 IEEE C COMP VIS, DOI DOI 10.1109/CVPR.2008.4587652
[5]  
[Anonymous], 2007, PROC IEEE C COMPUT V, DOI 10.1109/CVPR.2007.383267
[6]   Esaliency (Extended Saliency): Meaningful Attention Using Stochastic Image Modeling [J].
Avraham, Tamar ;
Lindenbaum, Michael .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (04) :693-708
[7]   Robust Image Analysis With Sparse Representation on Quantized Visual Features [J].
Bao, Bing-Kun ;
Zhu, Guangyu ;
Shen, Jialie ;
Yan, Shuicheng .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (03) :860-871
[8]   State-of-the-Art in Visual Attention Modeling [J].
Borji, Ali ;
Itti, Laurent .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (01) :185-207
[9]  
Bruce N., 2005, ADV NEURAL INFORM PR, V18, P155
[10]  
Cerf M., 2008, Advances in Neural Information Processing Systems, V20, P241