Color-Ciratefi: A color-based RST-invariant template matching algorithm

Template matching is a technique widely used for finding patterns in digital images. An efficient template matching algorithm should be able to detect template instances that have undergone geometric transformations. Similarly, a color template matching should be able to deal with color constancy problem. Recently we have proposed a new grayscale template matching algorithm named Ciratefi, invariant to rotation, scale, translation, brightness and contrast. In this paper we introduce the Color-Ciratefi that takes into account the color information. We use a new similarity metric in the CIELAB space to obtain invariance to brightness and contrast changes. Experiments show that Color-Ciratefi is more accurate than C-color-SIFT, the well-known SIFT algorithm that uses a set of color invariants. In conventional computers, Color-Ciratefi is slower than C-color-SIFT. However Color-Ciratefi is more suitable than C-color-SIFT to be implemented in highly parallel architectures like FPGA, because it repeats exactly the same set of operations for each pixel.

[1]  Hae Yong Kim,et al.  Grayscale Template-Matching Invariant to Rotation, Scale, Translation, Brightness and Contrast , 2007, PSIVT.

[2]  Vincent Lemaire,et al.  Illumination-Invariant Color Image Correction , 2006, IWICPAS.

[3]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Theo Gevers,et al.  A Perceptual Comparison of Distance Measures for Color Constancy Algorithms , 2008, ECCV.

[5]  Hae Yong Kim,et al.  Automatic VHDL generation for solving rotation and scale-invariant template matching in FPGA , 2009, 2009 5th Southern Conference on Programmable Logic (SPL).

[6]  Hans-Peter Seidel,et al.  Scale Invariant Feature Transform with Irregular Orientation Histogram Binning , 2009, ICIAR.

[7]  Du-Ming Tsai,et al.  Rotation-invariant pattern matching with color ring-projection , 2002, Pattern Recognit..

[8]  George A. Constantinides,et al.  A Parallel Hardware Architecture for Scale and Rotation Invariant Feature Detection , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[9]  Hae Yong Kim.  Rotation-discriminating template matching based on Fourier coefficients of radial projections with robustness to scaling and partial occlusion , 2010, Pattern Recognit..

[10]  Arnold W. M. Smeulders,et al.  Color Invariance , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  P. Bekaert,et al.  SIFT-CCH: Increasing the SIFT distinctness by Color Co-occurrence Histograms , 2007, 2007 5th International Symposium on Image and Signal Processing and Analysis.

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

[13]  Cordelia Schmid,et al.  A Performance Evaluation of Local Descriptors , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Frédéric Jurie,et al.  Learned color constancy from local correspondences , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[15]  Aly A. Farag,et al.  CSIFT: A SIFT Descriptor with Color Invariant Characteristics , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Gertjan J. Burghouts,et al.  Performance evaluation of local colour invariants , 2009, Comput. Vis. Image Underst..