显著区域检测是计算机视觉领域中一个极具挑战性的问题。当前，多数显著区域检测算法通过直接计算图像中每个像素或图像块与其一定范围内邻域的差异来判断像素的显著性。当图像背景杂乱或者图像中的前景和背景有相似特征时，这些传统方法的检测性能明显下降。该文提出一个基于再聚类的显著区域检测算法框架：首先，利用聚类算法将图像过分割得到的超像素再聚类成多个超像素簇，其中提出了自动确定尺度参数和聚类个数的方法；其次，基于聚类得到的超像素簇，该文又提出一个自动选择可能的背景簇的方法，并将其作为排序算法中的查询项来估计全图的显著性。在两个差异较大的公开数据集上，该算法实现了相对稳定的显著区域检测结果，而且在部分性能指标上明显优于其他5种算法。
Salient region detection is an extremely challenging problem in computer vision. Most salient region detection algorithms determine the saliency of pixels in the image by directly computing the contrast between a pixel or a patch and its neighborhood within a certain range. When the image background is cluttered or the background and the salient objects in the image have some of the same image features, the detection capabilities of these traditional methods are decreased. A salient region detection framework based on re-clustering is used here. First, a clustering algorithm is used to group superpixels into a number of superpixel clusters by automatically computing the scale parameter and the number of clusters. The algorithm automatically selects possible background clusters from the superpixel clusters with the selected clusters used as queries in a ranking algorithm to obtain the final saliency map. Tests on two public salient region detection datasets show that the algorithm gives stable salient region detection results with better performance metrics than five other algorithms.
[1] Papageorgiou C, Poggio T. A trainable system for object detection [J]. International Journal of Computer Vision, 2000, 38(1): 15-33.
[2] Mishra A K, Aloimonos Y, Cheong L F, et al. Active visual segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(4): 639-653.
[3] ZHENG Liang, WANG Shengjin, LIU Z, et al. Fast image retrieval: Query pruning and early termination [J]. IEEE Transactions on Multimedia, 2015, 17(5): 648-659.
[4] LIU Jie, WANG Shengjin, Salient region detection via simple local and global contrast representation [J]. Neurocomputing, 2015, 147(1): 435-443.
[5] REN Zhixiang, GAO Shenghua, Chia L T, et al. Region-based saliency detection and its application in object recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(5): 769-779.
[6] Brin S, Page L. The anatomy of a large-scale hypertextual Web search engine [J]. Computer Networks & Isdn Systems, 1998, 30(98): 107-117.
[7] YANG Chuan, ZHANG Lihe, LU Huchuan, et al. Saliency detection via graph-based manifold ranking [C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Portland, OR, USA: IEEE, 2013: 3166-3173.
[8] Achanta R, Shaji A, Smith K, et al. SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2274-2282.
[9] Von Luxburg U. A tutorial on spectral clustering [J]. Statistics and computing, 2007, 17(4): 395-416.
[10] Van De Weijer J, Schmid C, Verbeek J, et al. Learning color names for real-world applications [J]. IEEE Transactions on Image Processing, 2009, 18(7): 1512-1523.
[11] ZHU Wangjiang, LIANG Shuang, WEI Yichen, et al. Saliency optimization from robust background detection [C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 2814-2821.
[12] ZHOU Dengyong, Weston J, Gretton A, et al. Ranking on data manifolds [J]. Advances in Neural Information Processing Systems, 2004, 16(1): 169-176.
[13] ZHOU Dengyong, Bousquet O, Lal T N, et al. Learning with local and global consistency [J]. Advances in Neural Information Processing Systems, 2004, 16(16): 321-328.
[14] Achanta R, Hemami S, Estrada F, et al. Frequency-tuned salient region detection [C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Miami, FL, USA: IEEE, 2009: 1597-1604.
[15] SHI Jianping, YAN Qiong, XU Li, et al. Hierarchical image saliency detection on extended CSSD [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(4): 717-729.
[16] CHENG Mingming, Mitra N J, HUANG Xiaolei, et al. Global contrast based salient region detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 569-582.
[17] Perazzi F, Krähenbühl P, Pritch Y, et al. Saliency filters: Contrast based filtering for salient region detection [C]//Proc of IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE, 2012: 733-740.
