A hybrid method for fast computing the curvature scale space image

The curvature scale space (CSS) technique is one of the key techniques of the MPEG-7 international standard in computer vision and image processing. It was selected as a contour shape descriptor for MPEG-7 after substantial and comprehensive testing. However, to compute a CSS image in general needs to wait a long time. This is very disadvantageous when the CSS technique is applied to an object recognition system to perform real-time recognition. In order to solve this bottleneck problem, a hybrid method for fast computing the CSS image is proposed. In the method, firstly the curve is evolved in low scale space, and after image noise is suppressed then the curvature is evolved directly. Numerical experiments show that the hybrid method can perform equally well as the existing method. It is suitable for recognizing a noisy curve of arbitrary shape at any scale or orientation. On the other hand, the hybrid method only requires 1/3 /spl sim/ 1/5 CPU time of the existing one. As a result, the CSS technique is improved significantly for real-time recognition.

[1]  Farzin Mokhtarian,et al.  Silhouette-Based Isolated Object Recognition through Curvature Scale Space , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Chandra Kambhamettu,et al.  A Coarse-to-Fine Deformable Contour Optimization Framework , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Farzin Mokhtarian,et al.  FREE-FORM 3-D SURFACE DESCRIPTION IN MULTIPLE SCALES , 2001 .

[4]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  H. D. Cheng,et al.  Fuzzy homogeneity and scale-space approach to color image segmentation , 2003, Pattern Recognit..

[6]  Miroslaw Bober,et al.  Curvature Scale Space Representation: Theory, Applications, and MPEG-7 Standardization , 2011, Computational Imaging and Vision.

[7]  Farzin Mokhtarian,et al.  Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Mark H. Singer,et al.  Reduced resolution and scale space for dominant feature detection in contours , 2001, Pattern Recognit..

[9]  Roland T. Chin,et al.  Scale-Based Detection of Corners of Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Nasser Khalili,et al.  Multi-scale free-form 3D object recognition using 3D models , 2001, Image Vis. Comput..

[11]  Farzin Mokhtarian,et al.  Silhouette-based occluded object recognition through curvature scale space , 1997, Machine Vision and Applications.

[12]  George Papadourakis,et al.  Curvature scale-space-driven object recognition with an indexing scheme based on artificial neural networks , 1999, Pattern Recognit..