A multi-scale visual salient feature points extraction method based on Gabor wavelets

Keypoints are important features in the perceptual system of humans. They provide important information for focus-of-attention (FoA) and object categorization/recognition. Different types of keypoints have been used in computer vision applications. In this paper, we propose a method which extracts “salient” points in the meaning of biological vision by utilizing the multi-scale Gabor energy operator. The resulting operator responds strongly to corners, isolated lines, edges, and contours. And with the increase of scale, the extracted keypoints tend to illustrate important structures of the image. We show that the Gabor energy map provides very useful information of a saliency map for FoA and object recognition.

[1]  João M. F. Rodrigues,et al.  Multi-scale Keypoints in V1 and Face Detection , 2005, BVAI.

[2]  Nicolai Petkov,et al.  Contour detection based on nonclassical receptive field inhibition , 2003, IEEE Trans. Image Process..

[3]  Xosé R. Fernández-Vidal,et al.  Using models of feature perception in distortion measure guidance , 1998, Pattern Recognit. Lett..

[4]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[5]  Rolf P. Würtz,et al.  Corner detection in color images through a multiscale combination of end-stopped cortical cells , 2000, Image Vis. Comput..

[6]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

[7]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[8]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[9]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 2002, IEEE Trans. Image Process..

[10]  Xinting Gao,et al.  Multiscale Corner Detection of Gray Level Images Based on Log-Gabor Wavelet Transform , 2007, IEEE Transactions on Circuits and Systems for Video Technology.

[11]  P. Baranyi,et al.  Visual Cortex Inspired Vertex and Corner Detection , 2006, 2006 IEEE International Conference on Mechatronics.

[12]  S Marcelja,et al.  Mathematical description of the responses of simple cortical cells. , 1980, Journal of the Optical Society of America.

[13]  Tony Lindeberg,et al.  Edge Detection and Ridge Detection with Automatic Scale Selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Péter Baranyi,et al.  Cognitive Vision Inspired Contour and Vertex Detection , 2006, J. Adv. Comput. Intell. Intell. Informatics.

[15]  João M. F. Rodrigues,et al.  Multi-scale Cortical Keypoint Representation for Attention and Object Detection , 2005, IbPRIA.

[16]  Xinting Gao,et al.  Corner detection of gray level images using Gabor wavelets , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[17]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[18]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[19]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[20]  João M. F. Rodrigues,et al.  Visual Cortex Frontend: Integrating Lines, Edges, Keypoints, and Disparity , 2004, ICIAR.

[21]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[22]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 1999, Proceedings 10th International Conference on Image Analysis and Processing.