Real-Time Pattern Matching Using Projection Kernels
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Representing Images Using Nonorthogonal Haar-Like Bases
IEEE Transactions on Pattern Analysis and Machine Intelligence
Video block motion estimation based on gray-code kernels
IEEE Transactions on Image Processing
Fast block matching algorithm in walsh hadamard domain
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Hi-index | 0.00 |
A novel approach to pattern matching is presented, whichreduces time complexity by two orders of magnitude comparedto traditional approaches. The suggested approachuses an efficient projection scheme which bounds the distancebetween a pattern and an image window using veryfew operations. The projection framework is combined witha rejection scheme which allows rapid rejection of imagewindows that are distant from the pattern. Experimentsshow that the approach is effective even under very noisyconditions. The approach described here can also be usedin classification schemes where the projection values serveas input features that are informative and fast to extract.