Accelerating Pattern Matching or How Much Can You Slide?

This paper describes a method that accelerates pattern matching. The distance between a pattern and a window is usually close to the distance of the pattern to the adjacement windows due to image smoothness. We show how to exploit this fact to reduce the running time of pattern matching by adaptively sliding the window often by more than one pixel. The decision how much we can slide is based on a novel rank we define for each feature in the pattern. Implemented on a Pentium 4 3GHz processor, detection of a pattern with 7569 pixels in a 640 × 480 pixel image requires only 3.4ms.

• Type: Conference
• Year: 2007
• Where: ACCV
• Authors: Ofir Pele, Michael Werman
• Keywords: ACCV 2007, Computer Vision, Image Smoothness, Pattern Matching, Window