具有旋转不变性的异形模板匹配方法

针对工业自动装配产品过程中异形工件出现旋转后的定位问题，提出一种新的异形目标识别方法，设计基于目标轮廓的同心等势线异形模板，并结合圆投影方法，能快速有效地实现计算机对异形目标的自动识别与定位。研究结果表明，该方法可以准确地实现不规则目标的旋转变化识别，同时可以有效地解决存在亮度变化、对比度变化、噪声干扰等情况下的异形目标的匹配问题。

Matching Method of Irregular Shaped Template with Rotation Invariance

Aiming at positioning irregular parts rotated in the process of automated assembling of products in the industry, a new non-standard shaped target identification method is put forward. Design of irregular template based on the concentric equipotential line of target contour, combined with the projection, can quicly and efficiently realize automatic identification and position of irregular images by the computer. Results show that the method not only can accurately realize identification of irregular objection rotation change, but also can effectively solve matching problem under the circumstance of brightness changes, contrast changes or noise interferences .