A Speed-up Way of Template Matching Using Normalized Cross-correlation
One classic algorithm used in template matching is normalized cross correlation method.It often achieves high precision.But it does not meet speed requirements for time-critical applications.To solve that issue,a speed-up way of template matching is proposed.The fast matching way bases on pyramid hierarchical searching algorithm.It adopts two template matching methods to match images,which base on rough matching proceeds local matching precision.Firstly,the coarse matching is performed based on gray-scale projection algorithm.Secondly,the precise matching is made based on several small block matching.The new way is compared to conventional approach without pyramid hierarchical searching by experiments.Experimental result demonstrates that the proposed way efficiently improves the speed of template matching and the precision is unchanged.
template matching normalized cross correlation pyramid hierarchical searching algorithm
Fang Chen Cunji Zhang Binwen Zhao Jinfei Shi
Department of Mechanical Engineering,Southeast University,Nanjing,211189,China Department of Mechanical Engineering,Nanjing Institute of Technology,Nanjing,China
国际会议
济南
英文
1188-1191
2012-12-29（万方平台首次上网日期，不代表论文的发表时间）