Global Contrast Based Salient Region Detection
Global Contrast Based Salient Region Detection
复制标题
DOI：
10.1109/tpami.2014.2345401
复制
发表时间：
2015-03-01
影响因子：
23.6
通讯作者：
Hu, Shi-Min
中科院分区：
文献类型：
--
作者：
Cheng, Ming-Ming;Mitra, Niloy J.;Hu, Shi-Min
在没有任何先验假设或相应场景的内容的知识的情况下，跨图像的显著对象区域的自动估计增强了许多计算机视觉和计算机图形应用。提出了一种基于区域对比度的显著目标检测算法，该算法同时评估全局对比度差异和空间加权一致性得分。该算法简单、高效、自然多尺度，并生成全分辨率、高质量的显著图。这些显著图被进一步用于初始化新的GrabCut迭代版本，即SaliencyCut，用于高质量的无监督显著对象分割。我们使用传统的显著目标检测数据集以及更具挑战性的互联网图像数据集对我们的算法进行了广泛的评估。我们的实验结果表明，我们的算法始终优于现有的15种显著目标检测和分割方法，获得了更高的准确率和更好的召回率。我们还表明，我们的算法可以有效地从互联网图像中提取显著的对象掩模，通过简单的形状比较实现有效的基于草图的图像检索(SBIR)。尽管有这些噪声的互联网图像，其中显著区域是模糊的，我们的显著制导图像检索实现了比最先进的SBIR方法更好的检索率，并且另外提供了重要的目标对象区域信息。
Automatic estimation of salient object regions across images, without any prior assumption or knowledge of the contents of the corresponding scenes, enhances many computer vision and computer graphics applications. We introduce a regional contrast based salient object detection algorithm, which simultaneously evaluates global contrast differences and spatial weighted coherence scores. The proposed algorithm is simple, efficient, naturally multi-scale, and produces full-resolution, high-quality saliency maps. These saliency maps are further used to initialize a novel iterative version of GrabCut, namely SaliencyCut, for high quality unsupervised salient object segmentation. We extensively evaluated our algorithm using traditional salient object detection datasets, as well as a more challenging Internet image dataset. Our experimental results demonstrate that our algorithm consistently outperforms 15 existing salient object detection and segmentation methods, yielding higher precision and better recall rates. We also show that our algorithm can be used to efficiently extract salient object masks from Internet images, enabling effective sketch-based image retrieval (SBIR) via simple shape comparisons. Despite such noisy internet images, where the saliency regions are ambiguous, our saliency guided image retrieval achieves a superior retrieval rate compared with state-of-the-art SBIR methods, and additionally provides important target object region information.