Wavelet-based Scale Saliency

Both pixel-based scale saliency (PSS) and basis project methods focus on multiscale analysis of data content and structure. Their theoretical relations and practical combination are previously discussed. However, no models have ever been proposed for calculating scale saliency on basis-projected descriptors since then. This paper extend those ideas into mathematical models and implement them in the wavelet-based scale saliency (WSS). While PSS uses pixel-value descriptors, WSS treats wavelet sub-bands as basis descriptors. The paper discusses different wavelet descriptors: discrete wavelet transform (DWT), wavelet packet transform (DWPT), quaternion wavelet transform (QWT) and best basis quaternion wavelet packet transform (QWPTBB). WSS saliency maps of different descriptors are generated and compared against other saliency methods by both quantitative and quanlitative methods. Quantitative results, ROC curves, AUC values and NSS values are collected from simulations on Bruce and Kootstra image databases with human eye-tracking data as ground-truth. Furthermore, qualitative visual results of saliency maps are analyzed and compared against each other as well as eye-tracking data inclusive in the databases.

[1]  N. Kingsbury.  Complex Wavelets for Shift Invariant Analysis and Filtering of Signals , 2001 .

[2]  Michael Brady,et al.  Saliency, Scale and Image Description , 2001, International Journal of Computer Vision.

[3]  Dirk Walther,et al.  Interactions of visual attention and object recognition : computational modeling, algorithms, and psychophysics. , 2006 .

[4]  Leslie G. Valiant,et al.  Cognitive computation , 1995, Proceedings of IEEE 36th Annual Foundations of Computer Science.

[5]  Sebastiano Battiato,et al.  Advanced Concepts for Intelligent Vision Systems , 2015, Lecture Notes in Computer Science.

[6]  Thomas Bülow,et al.  Hypercomplex signals-a novel extension of the analytic signal to the multidimensional case , 2001, IEEE Trans. Signal Process..

[7]  Ivan W. Selesnick,et al.  On the Dual-Tree Complex Wavelet Packet and $M$-Band Transforms , 2008, IEEE Transactions on Signal Processing.

[8]  Xiaodong Gu,et al.  An Information Theoretic Model of Spatiotemporal Visual Saliency , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[9]  Richard Baraniuk,et al.  The Dual-tree Complex Wavelet Transform , 2007 .

[10]  Nick Kingsbury,et al.  The dual-tree complex wavelet transform: a new technique for shift invariance and directional filters , 1998 .

[11]  J. B. Kernan,et al.  An Information‐Theoretic Approach* , 1971 .

[12]  Andrew B. Watson,et al.  The cortex transform: rapid computation of simulated neural images , 1987 .

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

[14]  Fionn Murtagh,et al.  Multiscale entropy filtering , 1999, Signal Process..

[15]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[16]  Pablo Suau,et al.  A New Feasible Approach to Multi-dimensional Scale Saliency , 2009, ACIVS.

[17]  Ali Borji,et al.  Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study , 2013, IEEE Transactions on Image Processing.

[18]  John K. Tsotsos,et al.  Saliency, attention, and visual search: an information theoretic approach. , 2009, Journal of vision.

[19]  Richard G. Baraniuk,et al.  Coherent Multiscale Image Processing Using Dual-Tree Quaternion Wavelets , 2008, IEEE Transactions on Image Processing.

[20]  Abdelhakim Saadane,et al.  Image coding in the context of a psychovisual image representation with vector quantization , 1995, Proceedings., International Conference on Image Processing.

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

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

[23]  Dan Stowell,et al.  Fast Multidimensional Entropy Estimation by $k$-d Partitioning , 2009, IEEE Signal Processing Letters.

[24]  Israel Cohen,et al.  Orthonormal shift-invariant wavelet packet decomposition and representation , 1997, Signal Process..

[25]  R. Siezen,et al.  others , 1999, Microbial Biotechnology.

[26]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[27]  Gert Kootstra,et al.  Predicting Eye Fixations on Complex Visual Stimuli Using Local Symmetry , 2011, Cognitive Computation.

[28]  Eero P. Simoncelli,et al.  Image compression via joint statistical characterization in the wavelet domain , 1999, IEEE Trans. Image Process..

[29]  Pierre Baldi,et al.  Of bits and wows: A Bayesian theory of surprise with applications to attention , 2010, Neural Networks.

[30]  Nuno Vasconcelos,et al.  The discriminant center-surround hypothesis for bottom-up saliency , 2007, NIPS.