Multi-Threshold Corner Detection and Region Matching Algorithm Based on Texture Classification

In order to address the unreasonable distributed corners in single threshold Harris detection and expensive computation cost incurred from image region matching performed by normalized cross correlation (NCC) algorithm, multi-threshold corner detection and region matching algorithm based on texture classification are proposed. Firstly, the input image is split into sub-blocks which are classified into four different categories based on the specific texture: flat, weak, middle texture and strong regions. Subsequently, an algorithm is suggested to decide threshold values for different texture type, and interval calculation for the sub-blocks is performed to improve operation efficiency in the algorithm implementation. Finally, based on different texture characteristics, Census, interval-sampled NCC, and complete NCC are employed to perform image matching. As demonstrated by the experimental results, corner detection based on texture classification is capable to obtain a reasonable corner number as well as a more uniform spatial distribution, when compared to the traditional Harris algorithm. If combined with the interval classification, speedup for texture classification is approximately 30%. In addition, the matching algorithm based on texture classification is capable to improve the speed of 26.9%~29.9% while maintaining the comparable accuracy of NCC. In general, for better splicing quality, the overall stitching speed is increased by 14.1%~18.4%. Alternatively, for faster speed consideration, the weak texture region which accounts for a large proportion of an image and provides less effective information can be ignored, for which 23.9%~28.4% speedup can be achieved at the cost of a 1.9%~3.9% reduction in corner points. Therefore, the proposed algorithm is made potentially suited to uniformly distributed corner point calculation and high computation efficiency requirement scenarios.