Novel template matching method with sub-pixel accuracy based on correlation and Fourier-Mellin transform

Template matching is the process of determining the presence and the location of a reference image or an object inside a scene image under analysis by a spatial cross-correlation. Conventional cross-correlation type algorithms are computationally expensive. Furthermore, when the object in the image is rotated, the conventional algorithms cannot be used for practical purposes. An algorithm for a rotation-invariant template matching with subpixel accuracy is proposed based on the combination of the correlation and Fourier-Mellin transformation when the fluctuating scope of the rotation angle is [−20 deg,20 deg]. The algorithm consists of two stages. In the first stage, the matching candidates are selected using a computationally low-cost improved correlation algorithm. The operation of AND is adopted to reduce the computational cost for this stage. In the second stage, rotation invariant template matching is performed only on the matching candidates using the cross-correlation algorithm after adjusting image with a Fourier-Mellin invariant (FMI) descriptor, and the matching precision is subpixel by the novel method using the Fermat point. Experimental results show that the proposed method is very robust to Gaussian noise and rotation, and it also achieves high matching accuracy and matching precision.

[1]  Ronald D. DeGroat,et al.  A correlation-based subspace tracking algorithm , 1998, IEEE Trans. Signal Process..

[2]  Shaun Quegan,et al.  Matching map features to synthetic aperture radar (SAR) images using template matching , 1992, IEEE Trans. Geosci. Remote. Sens..

[3]  Haichao Li,et al.  A new fast edge-matching algorithm based on corner constraint and edge constraint , 2006, International Symposium on Instrumentation and Control Technology.

[4]  Jian Liu,et al.  A NOVEL contour-based 3D terrain matching algorithm using wavelet transform , 2004, Pattern Recognit. Lett..

[5]  J. Carrascosa,et al.  Template location in noisy pictures , 1988 .

[6]  Ernest L. Hall,et al.  Sequential Hierarchical Scene Matching , 1978, IEEE Transactions on Computers.

[7]  Pierre-André Farine,et al.  A novel homomorphic processing of ultrasonic echoes for layer thickness measurement , 1992, IEEE Trans. Signal Process..

[8]  Amir Averbuch,et al.  FFT based image registration , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..

[10]  Luigi di Stefano,et al.  Fast template matching using bounded partial correlation , 2003, Machine Vision and Applications.

[11]  Sun Gi Kim,et al.  Fast hierarchical grayscale template matching for an arbitrarily oriented object using Zernike Moments , 1996 .

[12]  Martin Vetterli,et al.  Wavelets and filter banks: theory and design , 1992, IEEE Trans. Signal Process..

[13]  Min-Seok Choi,et al.  A novel two stage template matching method for rotation and illumination invariance , 2002, Pattern Recognit..

[14]  J.K. Aggarwal,et al.  Correspondence processes in dynamic scene analysis , 1981, Proceedings of the IEEE.

[15]  Lisa M. Brown,et al.  A survey of image registration techniques , 1992, CSUR.

[16]  Federico Tombari,et al.  ZNCC-based template matching using bounded partial correlation , 2005, Pattern Recognit. Lett..

[17]  Michel Defrise,et al.  Symmetric Phase-Only Matched Filtering of Fourier-Mellin Transforms for Image Registration and Recognition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Mandyam D. Srinath,et al.  Invariant character recognition with Zernike and orthogonal Fourier-Mellin moments , 2002, Pattern Recognit..

[19]  Ruzena Bajcsy,et al.  Adaptive Correlation Tracking of Targets With Changing Scale , 1996 .

[20]  Richard J. Prokop,et al.  A survey of moment-based techniques for unoccluded object representation and recognition , 1992, CVGIP Graph. Model. Image Process..

[21]  O. Chitsobhuk,et al.  Image registration using Hough transform and phase correlation , 2006, 2006 8th International Conference Advanced Communication Technology.

[22]  Eric L. Miller,et al.  Wavelet domain image restoration with adaptive edge-preserving regularization , 2000, IEEE Trans. Image Process..

[23]  이상우,et al.  투영법을 이용한 회전불변 템플릿 매칭 ( Rotation-Invariant Template Matching Using Projection Method ) , 1996 .

[24]  M Yanalak,et al.  Effect of Gridding Method on Digital Terrain Model Profile Data Based on Scattered Data , 2003 .

[25]  William A. Barrett,et al.  Fast registration of tabular document images using the Fourier-Mellin transform , 2004, First International Workshop on Document Image Analysis for Libraries, 2004. Proceedings..