基于引导Boosting算法的显著性检测

doi:10.11772/j.issn.1001-9081.2017.09.2652

摘要/Abstract

摘要： 针对现有的基于引导学习的显著性检测模型存在的训练样本不纯净和特征提取方式过于简单的问题，提出一种改进的基于引导（Boosting）的算法来检测显著性，从提升训练样本集的准确度和改进特征提取的方式来达到学习效果的提升。首先，根据显著性检测的自底向上模型产生粗选样本图，并通过元胞自动机对粗选样本图进行快速有效优化来建立可靠的引导样本，完成对原图的标注建立训练样本集；然后，在训练集上对样本进行颜色纹理特征提取；最后，使用不同特征不同核的支持向量机（SVM）弱分类器生成基于Boosting学习一个强分类器，对每幅图像的超像素点进行前景背景分类，得到显著图。在ASD数据库和SED1数据库上的实验结果显示该模型能对复杂和简单的图像生成完备清晰的显著图，并在准确率召回率曲线和曲线下面积（AUC）测评值上有较大提升。由于其准确性，能应用在计算机视觉预处理阶段。

关键词: 显著性检测, boosting, 自底向上模型, 粗选样本优化, 颜色特征提取

Abstract: Aiming at the problem of impure simplicity and too simple feature extraction of training samples in the existing saliency detection model based on guided learning, an improved algorithm based on Boosting was proposed to detect saliency, which improve the accuracy of the training sample set and improve the way of feature extraction to achieve the improvement of learning effect. Firstly, the coarse sample map was generated from the bottom-up model for saliency detection, and the coarse sample map was quickly and effectively optimized by the cellular automata to establish the reliable Boosting samples. The training samples were set up to mark the original images. Then, the color and texture features were extracted from the training set. Finally, Support Vector Machine (SVM) weak classifiers with different feature and different kernel were used to generate a strong classifier based on Boosting, and the foreground and background of each pixel of the image was classified, and a saliency map was obtained. On the ASD database and the SED1 database, the experimental results show that the proposed algorithm can produce complete clear and salient maps for complex and simple images, with good AUC (Area Under Curve) evaluation value for accuracy-recall curve. Because of its accuracy, the proposed algorithm can be applied in pre-processing stage of computer vision.

Key words: saliency detection, boosting, bottom-up model, coarse reference optimization, color feature extraction

中图分类号:

TP391.4

叶子童, 邹炼, 颜佳, 范赐恩. 基于引导Boosting算法的显著性检测[J]. 计算机应用, 2017, 37(9): 2652-2658.

YE Zitong, ZOU Lian, YAN Jia, FAN Ci'en. Saliency detection based on guided Boosting method[J]. Journal of Computer Applications, 2017, 37(9): 2652-2658.

参考文献

[1] HAN J, NGAN K N, LI M, et al. Unsupervised extraction of visual attention objects in color images[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2006, 16(1):141-145.
[2] KO B C, NAM J Y. Object-of-interest image segmentation based on human attention and semantic region clustering[J]. Journal of the Optical Society of America A, Optics, Image Science, and Vision, 2006, 23(10):2462-2470.
[3] RUTISHAUSER U, WALTHER D, KOCH C, et al. Is bottom-up attention useful for object recognition?[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2004:37-44.
[4] CHEN T, CHENG M M, TAN P, et al. Sketch2Photo:Internet image montage[J]. ACM Transactions on Graphics, 2009, 28(5):Article No. 124.
[5] CHRISTOPOULOS C, SKODRAS A, EBRAHIMI T. The JPEG2000 still image coding system:an overview[J]. IEEE Transactions on Consumer Electronics, 2000, 46(4):1103-1127.
[6] ZHANG G, CHENG M, HU S, et al. A shape-preserving approach to image resizing[J]. Computer Graphics Forum, 2009, 28(7):1897-1906.
[7] HOU X, ZHANG L. Saliency detection:a spectral residual approach[C]//Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2007:18-23.
[8] JIANG H, WANG J, YUAN Z, et al. Automatic salient object segmentation based on context and shape prior[EB/OL].[2016-12-21]. http://www.bmva.org/bmvc/2011/proceedings/paper110/paper110.pdf.
[9] KLEIN D A, FRINTROP S. Center-surround divergence of feature statistics for salient object detection[C]//Proceedings of the 2011 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2011:2214-2219.
[10] TONG N, LU H, ZHANG Y, et al. Salient object detection via global and local cues[J]. Pattern Recognition, 2015, 48(10):3258-3267.
[11] MARCHESOTTI L, CIFARELLI C, CSURKA G. A framework for visual saliency detection with applications to image thumbnailing[C]//Proceedings of the 2009 IEEE 12th International Conference on Computer Vision. Piscataway, NJ:IEEE, 2009:2232-2239.
[12] NG A Y, JORDAN M I, WEISS Y. On spectral clustering:analysis and an algorithm[EB/OL].[2017-01-12]. http://www.csie.ntu.edu.tw/~mhyang/course/u0030/papers/Ng%20Weiss%20Jordan%20Spectral%20Clustering.pdf.
[13] 桑农,李正龙,张天序.人类视觉注意机制在目标检测中的应用[J].红外与激光工程,2004,33(1):38-42.(SANG N, LI Z L, ZHANG T X. Application of human visual attention mechanisms in object detection[J]. Infrared and Laser Engineering, 2004, 33(1):38-42.)
[14] TONG N, LU H, XIANG R, et al. Salient object detection via bootstrap learning[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:1884-1892.
[15] CHENG M M, ZHANG G X, MITRA N J, et al. Global contrast based salient region detection[C]//Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2011:409-416.
[16] CHENG M M, WARRELL J, LIN W Y, et al. Efficient salient region detection with soft image abstraction[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2013:1529-1536.
[17] FENG J. Salient object detection for searched web images via global saliency[C]//Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2012:3194-3201.
[18] HE K, SUN J, TANG X. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353.
[19] QIN Y, LU H, XU Y, et al. Saliency detection via cellular automata[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2015:110-119.
[20] WEI Y, WEN F, ZHU W, et al. Geodesic saliency using background priors[C]//European Conference on Computer Vision, LNCS 7574. Berlin:Springer, 2012:29-42.
[21] SUN J, LU H, LI S. Saliency detection based on integration of boundary and soft-segmentation[C]//Proceedings of the 201219th IEEE International Conference on Image Processing. Piscataway, NJ:IEEE, 2012:1085-1088.
[22] JIANG H, WANG J, YUAN Z, et al. Salient object detection:a discriminative regional feature integration approach[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:2083-2090.
[23] 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.
[24] YANG F, LU H, CHEN Y W. Human tracking by multiple kernel boosting with locality affinity constraints[C]//Proceedings of the 201010th Asian Conference on Computer Vision. Berlin:Springer. 2010:39-50.
[25] 汪成,陈文兵.基于SLIC超像素分割显著区域检测方法的研究[J].南京邮电大学学报(自然科学版),2016,36(1):89-93.(WANG C, CHEN W B, et al. Salient region detection method based on SLIC superpixel segmentation[J]. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 2016, 36(1):89-93.)
[26] WOLFRAM S. Statistical mechanics of cellular automata[J]. Reviews of Modern Physics, 1983, 55(3):601-644.
[27] YILDIRIM G, SÜSSTRUNK S. FASA:fast, accurate, and size-aware salient object detection[C]//Asian Conference on Computer Vision, LNCS 9005. Berlin:Springer, 2014:514-528.
[28] BACH F R, LANCKRIET G R G, JORDAN M I. Multiple kernel learning, conic duality, and the SMO algorithm[C]//Proceedings of the 21st International Conference on Machine Learning. New York:ACM, 2004:6.
[29] BOYKOV Y, KOLMOGOROV V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision[C]//Proceedings of the 3rd International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition. London:Springer, 2001:359-374.
[30] 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.
[31] ZHAI Y, SHAH M. Visual attention detection in video sequences using spatiotemporal cues[C]//Proceedings of the 14th ACM International Conference on Multimedia. New York:ACM, 2006:815-824.
[32] HOU X, ZHANG L. Saliency detection:a spectral residual approach[C]//Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2007:1-8.