A novel hybrid genetic algorithm with Tabu search for optimizing multi-dimensional functions and point pattern recognition

Hybrid evolutionary algorithms are drawing significant attention in recent time for solving numerous real world problems. This paper presents a new hybrid evolutionary approach for optimizing mathematical functions and Point Pattern Recognition (PPR) problems. The proposed method combines a global search genetic algorithm in a course-to-fine resolution space with a local (Tabu) search algorithm. Such hybridization enhances the power of the search technique by virtue of inducing hill climbing and fast searching capabilities of Tabu search process. The approach can reach the global or near-global optimum for the functions in high dimensional space. Tests have been successfully made on several benchmark functions in up-to 100 dimensions. The performance of the proposed algorithm has been compared with other relevant algorithms using non-parametric statistical approaches like Friedman test, multiple sign-test and contrast estimation. Also, the hybrid method with grid based PPR technique has been applied for solving dot pattern shape matching and object matching represented as edge maps. The performance of proposed method compares favorably with relevant approaches reported in the article.