Interval weighted multi-template matching for accurate measurement

Abstract

This paper employs the interval weighted multi-template matching approach for accurate measurement. Generally, a vernier caliper is used as the subject to capture the analyzing image. However, the vernier caliper has many similar regions which all effect the measure accuracy. The traditional template matching with only one template is not suitable, as the matching region may only stands for one local region. To reduce this effect, the multi-template matching is employed to get different matching regions with different templates. Then the interval which the matching result belongs to is weighted, and the final measure accuracy is obtained based on the weighted average approach. Compared with the true value, the final result is just sub-pixel error which shows that the interval weighted multi-template matching method is efficient for accurate measurement and it's simple to implement.