Optimal correlation filters are widely used in signal processing and pattern recognition applications. Correlation filters are a set of synthesized spatial filters that produce controlled response with sharp peaks. Wh...
详细信息
ISBN:
(纸本)9781450340809
Optimal correlation filters are widely used in signal processing and pattern recognition applications. Correlation filters are a set of synthesized spatial filters that produce controlled response with sharp peaks. While providing excellent discrimination capabilities correlation filters offer shift, rotation and scale invariance for 2D images. Correlation filters are optimized to enhance the recognition of consistent parts while suppressing the varying patterns. Synthesizing the correlation filters for pattern recognition applications involves several complex mathematical operations and requires high computation resources especially for high resolution images and videos. In this paper, we show that near real time performance can be achieved for the design of the OTCHF filter with help of optimization and parallelization on multicore GPUs and CPUs.
暂无评论