Saliency detection algorithm of deep guidance

doi:10.11772/j.issn.1001-9081.2018061194

Abstract

Abstract: As current saliency detection algorithms based on deep convolutional network have problems of incomplete target and noisy background detected from complex scene images, a new algorithm of deep feature-oriented saliency detection composed with basic feature extraction and high-level feature which guided cross-level aggregating delivery was proposed. It was based on the improvement of an extant Encoded Low level distance map with Deep features (ELD) model. Firstly, according to the characteristics of convolutional features at different levels, a cross-level feature fusion network model of high-level feature guidance was established. Then, saliency clustering propagation by using high-level feature guidance on initial saliency map that generated by improved neural network was implemented. Finally, final saliency map with more details and less noise was generated by using fully-connected conditional random field after saliency propagation. The experimental results on ECSSD and DUT-ORMON data sets show that, the Precision-Recall (PR) performance of the proposed algorithm is better than ELD algorithms, and F-measure(F) is increased by 7.5% and 11%, respectively, while its Mean Average Errors (MAE) are decreased by 16% and 15%, respectively,which also can obtain more robust results in complex image scene fields of target recognition, pattern recognition, image indexing, and so on.

Key words: saliency detection, deep feature, neural network, feature guidance, salient map

摘要： 针对目前基于深度卷积神经网络的显著性检测算法存在对复杂场景图像目标检测不完整、背景噪声多的问题，提出一种深度特征导向显著性检测算法。该算法是基于现有底层特征与深度卷积特征融合模型（ELD）的改进，网络模型包含基础特征提取、高层语义特征跨层级引导传递两个部分。首先，根据不同层级卷积特征的差异性，构建跨层级特征联合的高层语义特征引导模型；然后，用改进的网络模型生成初始显著图，利用高层语义特征引导的方式进行显著性聚类传播；最后，用完全联系条件随机场对聚类传播的结果进行优化，使其能够获取更多结构边缘信息和降低噪声并生成完整显著图。在ECSSD上和DUT-ORMON两个数据集上进行实验测试，实验结果表明，所提算法的准确率和召回率（PR）优于ELD模型，其F-measure（F）值分别提升了7.5%和11%，平均绝对误差（MAE）值分别降低了16%和15%，说明了所提算法模型能够在目标识别、模式识别、图像索引等复杂图像场景应用领域得到更加鲁棒的结果。

关键词: 显著性检测, 深度特征, 神经网络, 特征引导, 显著图

CLC Number:

ZHAO Heng, AN Weisheng, FU Weigang. Saliency detection algorithm of deep guidance[J]. Journal of Computer Applications, 2019, 39(1): 143-147.

赵恒, 安维胜, 付为刚. 深度导向显著性检测算法[J]. 计算机应用, 2019, 39(1): 143-147.

References

[1] BORJI A, CHENG M M, JIANG H Z, et al. Salient object detection:a benchmark[J]. IEEE Transactions on Image Processing, 2015, 24(12):5706.
[2] GAO Y, WANG M, TAO D C, et al. 3-D object retrieval and recognition with hypergraph analysis[J]. IEEE Transactions on Image Processing, 2012, 21(9):4290-4303.
[3] HADIZADEH H, BAJIC I V. Saliency-aware video compression[J]. IEEE Transactions on Image Processing, 2014, 23(1):19-33.
[4] ACHANTA R, HEMAMI S, ESTRADA F, et al. Frequency-tuned salient region detection[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2009:1597-1604.
[5] ZHU W, LIANG S, WEI Y, et al. Saliency optimization from robust background detection[C]//Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:2814-2821.
[6] LI X, LU H, ZHANG L, et al. Saliency detection via dense and sparse reconstruction[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2013:2976-2983.
[7] JIANG H Z, WANG J D, YUAN Z J, et al. Salient object detection:a discriminative regional feature integration approach[J]. International Journal of Computer Vision, 2014, 123(2):251-268.
[8] VIG E, DORR M, COX D. Large-scale optimization of hierarchical features for saliency prediction in natural images[C]//Proceedings of the 2014 Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2014:2798-2805.
[9] ZHAO R, OUYANG W, LI H, et al. Saliency detection by multi-context deep learning[C]//Proceedings of the 2015 Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:1265-1274.
[10] LIU N, HAN J W, ZHANG D W, et al. Predicting eye fixations using convolutional neural networks[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:362-370.
[11] LI G B, YU Y Z. Visual saliency based on multiscale deep features[C]//Proceedings of the 2015 IEEE Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:5455-5463.
[12] LI X, ZHAO L M, WEI L N, et al. DeepSaliency:multi-task deep neural network model for salient object detection[J]. IEEE Transactions on Image Processing, 2016, 25(8):3919-3930.
[13] LEE G, TAI Y W, KIM J. Deep saliency with encoded low level distance map and high level features[C]//Proceedings of the 2016 IEEE Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2016:660-668.
[14] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. ArXiv Preprint, 2014, 2014:1409.1556.
[15] 李啸宇,张秋菊.融合局部纹理特征的颗粒图像SLIC超像素分割方法[J].食品与机械,2016,32(12):31-34.(LI X Y, ZHANG Q J. A SLIC-based superpixel segmentation method by using local texture feature for granular image[J]. Food and Machinery, 2016, 32(12):31-34.)
[16] 刘彤,黄修添,马建设,等.基于完全联系的条件随机场的图像标注[J].计算机应用,2017,37(10):2841-2846.(LIU T, HUANG X T, MA J S, et al. Image labeling based on fully-connected conditional random field[J]. Journal of Computer Applications, 2017, 37(10):2841-2846.)
[17] HOU Q, CHENG M M, HU X, et al. Deeply supervised salient object detection with short connections[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2017:5300-5309.
[18] JIA Y Q, SHELHAMER E, DONAHUE J, et al. Caffe:Convolutional architecture for fast feature embedding[C]//Proceedings of the 2014 ACM Conference on Multimedia. New York:ACM, 2014:675-678.