图像显著性的理解

       图像显著性是图像中重要的视觉特征,体现了人眼对图像的某些区域的重视程度。自从1998年Itti的工作以来,产生了大量的显著性映射方法,图像显著性也广泛应用于图像压缩、编码、图像边缘和区域加强、显著性目标分割和提取等.

      对于一幅图像来说,用户只对图像中的部分区域感兴趣,这部分感兴趣的区域代表了用户的查询意图,而多数剩余的不感兴趣区域则与用户查询意图无关.显著区域是图像中最能引起用户兴趣、最能表现图像内容的区域.事实上,显著区域的选择是非常主观的,由于用户任务和知识背景的不同,对于同一幅图像,不同的用户可能会选择不同的区域作为显著区域. 常用的方法是利用人的注意力机制为基础计算图像的显著度.认知心理学的研究表明,图像中有些区域能显著的吸引人的注意,这些区域含有较大的信息量.认知科学家已经提出了许多数学模型来模拟人的注意力机制.由于利用了图像认知过程中的一般规律,这样提取的显著区域比较符合人的主观评价.
      图像显著性分析应用广泛,主要包括:基于显著性区域的自适应图像压缩和编码,基于显著性度量的图像边缘或区域加强,基于显著性分析的目标分割或提取等。
      目前出现越来越多的显著性分析算法,有些人将这些算法进行了一定的分类。[8]中提到将目前显著性分析的算法分成三类:第一类是基于低层视觉特征的显著性分析算法,其代表性算法是[1]中提出的算法(Itti算法),这是一种模拟生物体视觉注意机制的选择性注意算法,比较适合处理自然图像。第二类是不基于任何生物视觉原理的纯数学计算方法,这类主要有[7]中提到的一种全分辨率的算法(AC算法)和[9]中提出的基于空间频域分析的剩余谱算法(SR算法)。第三类是将前两种进行融合的方法,其代表性算法是[6]中提出基于图论的算法(GBVS算法),这种算法在特征提取的过程中类似Itti算法去模拟视觉原理,但在显著图生成的过程引入马尔可夫连,用纯数学计算的来得到显著值。而在[10]中又将显著性分析算法分成以下三类:考虑局部特征的,例如Itti算法和GBVS算法;考虑整体性的,例如SR算法和[8]中提出的算法(IG算法);局部与整体结合的,例如[10],[11]中提出的算法。

        常用的显著性方法介绍:

Itti "A Model of Saliency-Based Visual Attention for Rapid Scene Analysis"
      Abstract—A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing saliency. The system breaks down the complex problem of scene understanding by rapidly selecting, in a computationally efficient manner, conspicuous locations to be analyzed in detail.
      Index Terms—Visual attention, scene analysis, feature extraction, target detection, visual search.
GBVS "Graph-Based Visual Saliency"
      Abstract—A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed. It consists of two steps: rst forming activation maps on certain feature channels, and then normalizing them in a way which highlights conspicuity and admits combination with other maps. The model is simple, and biologically plausible insofar as it is naturally parallelized. This model powerfully predicts human xations on 749 variations of 108 natural images, achieving 98% of the ROC area of a human-based control, whereas the classical algorithms of Itti & Koch ([2], [3], [4]) achieve only 84%.
AC "Salient Region Detection and Segmentation"
      Abstract—Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. In this paper we present a novel method to determine salient regions in images using low-level features of luminance and color. The method is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image.We demonstrate the use of the algorithm in the segmentation of semantically meaningful whole objects from digital images.
      Key words: Salient regions, low-level features, segmentation
IG "Frequency-tuned Salient Region Detection"
      Abstract—Detection of visually salient image regions is useful for applications like object segmentation, adaptive compression, and object recognition. In this paper, we introduce a method for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. These boundaries are preserved by retaining substantially more frequency content from the original image than other existing techniques. Our method exploits features of color and luminance, is simple to implement, and is computationally efficient. We compare our algorithm to five state-of-the-art salient region detection methods with a frequency domain analysis, ground truth, and a salient object segmentation application. Our method outperforms the five algorithms both on the ground-truth evaluation and on the segmentation task by achieving both higher precision and better recall.
IG "Saliency Detection: A Spectral Residual Approach"
      Abstract—The ability of human visual system to detect visual saliency is extraordinarily fast and reliable. However, com- putational modeling of this basic intelligent behavior still remains a challenge. This paper presents a simple method for the visual saliency detection.
      Our model is independent of features, categories, or other forms of prior knowledge of the objects. By analyz- ing the log-spectrum of an input image, we extract the spectral residual of an image in spectral domain, and propose a fast method to construct the corresponding saliency map in spatial domain.
      We test this model on both natural pictures and artificial images such as psychological patterns. The result indicate fast and robust saliency detection of our method


参考文献:
[1] L. Itti, C. Koch, & E. Niebur .A model of saliency based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11):1254-1259, 1998.
[2] L. Itti and C. Koch. Computational Model ling of Visual Attention. Nature Reviews Neuroscience, 2(3):194–203, 2001.
[3] C. Koch& S. Ullman . Shifts in selective visual attention: Towards the underlying neural circuitry. Human Neurobiology, 4(4):219-227, 1985.
[4] L. Itti, & P. Baldi . Bayesian surprise attracts human attention. Advances in Neural Information Processing Systems, 19:547-554, 2005.
[5] C. Koch and T. Poggio. Predicting the Visual World: Silence is Golden. Nature Neuroscience, 2(1):9–10, 1999.
[6] J. Harel, C. Koch, &P. Perona. Graph-based visual saliency. Advances in Neural Information Processing Systems, 19:545-552, 2007.
[7] R. Achanta, F. Estrada, P. Wils, & S. S¨usstrunk. Salient region detection and segmentation. International Conference on Computer Vision Systems, 2008, pp.66-75.
[8] R. Achanta, S. Hemami ,F. Estrada,& S. S¨usstrunk Frequency-tuned salient region detection. IEEE International Conference on Computer Vision and Pattern Recognition, 2009, pp.1597-1604.
[9] X,Hou &L,Zhang. Saliency Detection: A spectral residual approach. IEEE Conference on Computer Vision and Pattern Recognition, 2007, pp.1-8.
[10] S. Goferman, L. Zelnik-Manor &A. Tal r. Context-aware saliency detection. Conference on Computer Vision and Pattern Recognition, 2010, pp. 9-16.
[11] T. Liu, J. Sun, N. Zheng, X. Tang, and H. Shum. Learning to detect a salient object. Conference on Computer Vision and Pattern Recognition, 2007, pp.1-8

阅读更多
换一批

没有更多推荐了,返回首页