A New Model-Based Rotation and Scaling-Invariant Projection Algorithm for Industrial Automation Application

摘要

This paper describes a simple approach for model-based template matching, which is robust to undergo rotation and scaling variations. An efficient image warping scheme spiral aggregation image (SAI), which has been utilized in this paper, provides a method for generating projection profiles for matching. In addition, it determines the rotation angle and is invariant to scale changes. The proposed spiral projection algorithm (SPA) for template matching enables the simultaneous representation for each value of projection profile, obtained through SAI, and provides structural and statistical information on the template. The experimental evaluation shows that the proposed SPA achieves very attractive results for template matching in the industrial automation application.