An efficient algorithm for attention-driven image interpretation from segments

In the attention-driven image interpretation process, an image is interpreted as containing several perceptually attended objects as well as the background. The process benefits greatly a content-based image retrieval task with attentively important objects identified and emphasized. An important issue to be addressed in an attention-driven image interpretation is to reconstruct several attentive objects iteratively from the segments of an image by maximizing a global attention function. The object reconstruction is a combinational optimization problem with a complexity of 2^N which is computationally very expensive when the number of segments N is large. In this paper, we formulate the attention-driven image interpretation process by a matrix representation. An efficient algorithm based on the elementary transformation of matrix is proposed to reduce the computational complexity to 3@wN(N-1)^2/2, where @w is the number of runs. Experimental results on both the synthetic and real data show a significantly improved processing speed with an acceptable degradation to the accuracy of object formulation.

[1]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[2]  N. Suga,et al.  Criticisms of 'Specific long-term memory traces in primary auditory cortex' , 2004, Nature Reviews Neuroscience.

[3]  Scott B. Steinman,et al.  Computational Models of Visual Attention , 2002 .

[4]  Fan Chung,et al.  Spectral Graph Theory , 1996 .

[5]  E. Reingold,et al.  Combinatorial Algorithms: Theory and Practice , 1977 .

[6]  Zheru Chi,et al.  Attention-driven image interpretation with application to image retrieval , 2006, Pattern Recognit..

[7]  J ValdésJulio,et al.  2006 Special issue , 2006 .

[8]  Pietro Perona,et al.  Selective visual attention enables learning and recognition of multiple objects in cluttered scenes , 2005, Comput. Vis. Image Underst..

[9]  Weisi Lin,et al.  Modeling visual attention's modulatory aftereffects on visual sensitivity and quality evaluation , 2005, IEEE Transactions on Image Processing.

[10]  B. S. Manjunath,et al.  Unsupervised Segmentation of Color-Texture Regions in Images and Video , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Joachim M. Buhmann,et al.  A minimum entropy approach to adaptive image polygonization , 2003, IEEE Trans. Image Process..

[12]  Lie Lu,et al.  A generic framework of user attention model and its application in video summarization , 2005, IEEE Trans. Multim..

[13]  Laurent Itti,et al.  Automatic foveation for video compression using a neurobiological model of visual attention , 2004, IEEE Transactions on Image Processing.

[14]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  H. Joseph Straight.  Combinatorics: An Invitation , 1993 .

[16]  J Theeuwes,et al.  Visual selective attention: a theoretical analysis. , 1993, Acta psychologica.

[17]  Jeremy M. Wolfe,et al.  The Level of Attention: Mediating Between the Stimulus and Perception , 2003 .

[18]  Patrick Le Callet,et al.  A coherent computational approach to model bottom-up visual attention , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Pietro Perona,et al.  Is bottom-up attention useful for object recognition? , 2004, CVPR 2004.

[20]  Albert Ali Salah,et al.  A Selective Attention-Based Method for Visual Pattern Recognition with Application to Handwritten Digit Recognition and Face Recognition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  A. D. Kraus,et al.  Matrices for engineers , 1987 .

[22]  Wan-Chi Siu,et al.  Multimedia Information Retrieval and Management , 2003 .

[23]  Kosuke Sato,et al.  Real-time gesture recognition by learning and selective control of visual interest points , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Lei Guo,et al.  Automatic attention object extraction from images , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[25]  Christof Koch,et al.  Modeling attention to salient proto-objects , 2006, Neural Networks.

[26]  Takashi Matsuyama,et al.  Multiobject Behavior Recognition by Event Driven Selective Attention Method , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  J. Wolfe,et al.  What attributes guide the deployment of visual attention and how do they do it? , 2004, Nature Reviews Neuroscience.

[28]  Zhuowen Tu,et al.  Image Parsing: Unifying Segmentation, Detection, and Recognition , 2005, International Journal of Computer Vision.

[29]  Gunther Heidemann,et al.  Focus-of-attention from local color symmetries , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[31]  Fuhui Long,et al.  Fundamentals of Content-Based Image Retrieval , 2003 .

[32]  Hemant D. Tagare,et al.  A Maximum-Likelihood Strategy for Directing Attention during Visual Search , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Chun-Jen Tsai,et al.  Visual sensitivity guided bit allocation for video coding , 2006, IEEE Transactions on Multimedia.

[34]  Bärbel Mertsching,et al.  Data- and Model-Driven Gaze Control for an Active-Vision System , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[35]  Michael Lindenbaum,et al.  Attention-based dynamic visual search using inner-scene similarity: algorithms and bounds , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[36]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .