Real-Time Pattern Matching using Projection Kernels

Abstract:  This technique suggests a novel approach to pattern matching which reduces time complexity by two orders of magnitude compared to traditional approaches. The approach uses an efficient projection scheme which bounds the distance between a pattern and an image window using very few operations. The projection framework is combined with a rejection scheme which allows rapid rejection of image windows that are distant from the pattern. The approach was shown to be effective even under very noisy conditions.

-       Y. Hel-Or and H. Hel-Or:  Real Time Pattern Matching using Projection Kernels,  PAMI, Sept 2005.

-       Power Point presentation.


-       README

-       Source code in C 




The Gray-Code Filter Kernels

Abstract:   We introduce a family of filter kernels—the Gray-Code Kernels (GCK) and demonstrate their use in image analysis. Filtering an image with a sequence of Gray-Code Kernels is highly efficient and requires only two operations per pixel for each filter kernel, independent of the size or dimension of the kernel. We show that the family of kernels is large and includes the Walsh-Hadamard kernels, among others. The GCK can be used to approximate any desired kernel and, as such forms, a complete representation. The efficiency of computation using a sequence of GCK filters can be exploited for various real-time applications, such as, pattern detection, feature extraction, texture analysis, texture synthesis, and more.

-       G. Ben-Artzi, H. Hel-Or, and Y. Hel-Or  The Gray-Code Filter Kernels

IEEE Trans. Pattern Analysis and Machine Intelligence, Vol 29, No. 3, March 2007


-    C code written by Josh Allmann



Fast Template Matching in Non-Linear Tone-Mapped Images

Abstract:  We propose a fast pattern matching scheme termed Matching by Tone Mapping (MTM) which allows matching under non-linear tone mappings. We show that when tone mapping is approximates by a piecewise constant function fast computational scheme is possible requiring computational time similar to the fast implementation of Normalized Cross Correlation (NCC). In fact, the MTM measure can be viewed as a generalization of the NCC for non-linear mappings and actually reduces to NCC when mappings are restricted to be linear. The MTM is shown to be invariant to non-linear tone mappings, and is empirically shown to be highly discriminative and robust to noise.

-       Y. Hel-Or and H. Hel-Or:  Matching by Tone Mapping: Photometric Invariant Template Matching, PAMI 2013.


-       Source code in Matlab