An improved species based genetic algorithm and its application in multiple template matching for embroidered pattern inspection

This paper describes an improved genetic algorithm (GA) using the notion of species in order to solve an embroidery inspection problem. This inspection problem is actually a multiple template matching problem which can be formulated as a multimodal optimization problem. In many cases, the run time of the multiple template matching problem is dominated by repeating the similarity calculations and moving the templates over the source image. To cope with this problem, the proposed species based genetic algorithm (SbGA) is capable to determine its neighborhood best values for solving multimodal optimization problems. The SbGA has been statistically tested and compared with other genetic algorithms on a number of benchmark functions. After proving its effectiveness, it is integrated with multi-template matching method, namely SbGA–MTM method to solve the embroidery inspection problem. Furthermore, the notion of bounded partial correlation (BPC) is also adopted as an acceleration strategy, which enhances the overall efficiency. Experimental results indicate that the SbGA–MTM method is proven to solve the inspection problem efficiently and effectively. With the proposed method, the embroidered patterns can be identified and checked automatically.

► This paper describes an improved genetic algorithm (GA) using the notion of species in order to solve an embroidery inspection problem.
► Species based genetic algorithm (SbGA). Integrated with multi-template matching method.
► Bounded partial correlation (BPC) is also adopted as an acceleration strategy.