Computational model for salient object detection with anisotropy.

An innovative computational model for salient objects detection is proposed. The model is based on the exploitation of the anisotropy property of images by means of pixelwise directional entropy. The generalized Rényi entropy and the discrete cosine transform (DCT) coefficients are selected for this purpose. An entropy map of an input image can be obtained by calculating the Rényi entropy via local patch-based DCT. Analyzing the statistical property of the power spectrum of the entropy map on log-log scale, we find the power law is also appropriate for entropy maps. Accordingly, a saliency map can be derived from the entropy residual computation. Salient objects are detected using a seeded region growing algorithm. Both qualitative and quantitative experiments are conducted. The corresponding results demonstrate the outstanding performance of the proposed model.

[1]  J. H. van Hateren,et al.  Modelling the Power Spectra of Natural Images: Statistics and Information , 1996, Vision Research.

[2]  T. Poggio,et al.  Predicting the visual world: silence is golden , 1999, Nature Neuroscience.

[3]  B. Julesz,et al.  Withdrawing attention at little or no cost: Detection and discrimination tasks , 1998, Perception & psychophysics.

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

[5]  A. Rényi.  On Measures of Entropy and Information , 1961 .

[6]  LJubisa Stankovic,et al.  A measure of some time-frequency distributions concentration , 2001, Signal Process..

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

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

[9]  S. Süsstrunk,et al.  Frequency-tuned salient region detection , 2009, CVPR 2009.

[10]  Michael S. Landy,et al.  Detection and Discrimination , 1991 .

[11]  G. Cristóbal,et al.  A new Rényi entropy-based local image descriptor for object recognition , 2010, Photonics Europe.

[12]  Michael G. Sadovsky,et al.  Entropy Approach in the Analysis of Anisotropy of Digital Images , 2002, Open Syst. Inf. Dyn..

[13]  Christophe Charrier,et al.  A DCT Statistics-Based Blind Image Quality Index , 2010, IEEE Signal Processing Letters.

[14]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Antonio Torralba,et al.  Statistics of natural image categories , 2003, Network.

[16]  Olivier J. J. Michel,et al.  Time-frequency complexity and information , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  Liqing Zhang,et al.  Saliency Detection: A Spectral Residual Approach , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  I Pitas,et al.  Image watermarking using block site selection and DCT domain constraints. , 1998, Optics express.

[19]  Eero P. Simoncelli,et al.  On Advances in Statistical Modeling of Natural Images , 2004, Journal of Mathematical Imaging and Vision.

[20]  Shahram Latifi,et al.  Edge enhancement of remote sensing image data in the DCT domain , 1998, Defense, Security, and Sensing.

[21]  Ramon Baldrich,et al.  Saliency of color image derivatives: a comparison between computational models and human perception. , 2010, Journal of the Optical Society of America. A, Optics, image science, and vision.

[22]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[23]  S. Gabarda,et al.  Blind image quality assessment through anisotropy. , 2007, Journal of the Optical Society of America. A, Optics, image science, and vision.

[24]  Yuan Zhao,et al.  Salient target detection based on pseudo-Wigner-Ville distribution and Rényi entropy. , 2010, Optics letters.

[25]  John K. Tsotsos,et al.  Saliency Based on Information Maximization , 2005, NIPS.

[26]  Edward A Essock,et al.  A horizontal bias in human visual processing of orientation and its correspondence to the structural components of natural scenes. , 2004, Journal of vision.

[27]  Majid Nili Ahmadabadi,et al.  Online learning of task-driven object-based visual attention control , 2010, Image Vis. Comput..

[28]  Nanning Zheng,et al.  Learning to Detect a Salient Object , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.