“What” and “Where” Information Based Attention Guidance Model
Visual system can be defined as consisting of two pathways. The classic definition labeled a “what” pathway to process object information and a “where” pathway to process spatial information. In this paper, we propose a novel attention guidance model based on “what” and “where” information. Context-centered “where” information is used to control top-down attention, and guide bottom-up attention which is driven by “what” information. The procedure of top-down attention can be divided into two stages: pre-attention and focus attention. In the stage of pre-attention, “where” information can be used to provide prior knowledge of presence or absence of objects which decides whether search operation is followed. By integrating the result of focus attention with “what” information, attention is directed to the region that is most likely to contain the object and series of salient regions are detected. Results of experiment on natural images demonstrate its effectiveness.
KeywordsVisual Attention Gaussian Mixture Model Focus Attention Independent Component Analysis Salient Region
Unable to display preview. Download preview PDF.
- 2.Marr, D.: Vision: a Computational Investigation into the Human Representation and Processing of Visual Information. Freeman, W. H, San Francisco (1982)Google Scholar
- 5.Frintrop, S., Rome, E.: Simulating Visual Attention for Object Recognition. In: Proceedings of the Workshop on Early Cognitive Vision (2004)Google Scholar
- 7.Ouerhani, N.: Visual Attention: from Bio-Inspired Modeling to Real-Time Implementation. Institute of Micro technology, Switzerland (2003)Google Scholar
- 8.Long, F.H., Zheng, N.N.: A Visual Computing Model Based on Attention Mechanism. Journal of Image and Graphics 3, 592–595 (1998)Google Scholar
- 11.Itti, L.: Models of Bottom-Up and Top-Down Visual Attention. California Institute of Technology, Pasadena (2000)Google Scholar
- 17.Lee, T.W., Lewicki, M.S.: The Generalized Gaussian Mixture Model Using ICA. In: International Workshop on Independent Component Analysis (ICA 2000), pp. 239–244 (2000)Google Scholar
- 18.Liu, Y.H., Luo, S.W., Li, A.J., Yu, H.B.: A New Model Selection Criterion Based on Information Geometry. In: 7th Intern. Conf. on Signal Processing (ICSP 2004), vol. 2, pp. 1562–1565 (2004)Google Scholar
- 19.Bilmes, J.A.: A Gentle Tutorial of the EM Algorithm and Its Application to Parameter Estimation for Gaussian Mixture and Hidden Markov Models. Technical Report, ICSI-TR-97-021, University of Berkeley, Berkeley (1998)Google Scholar