Design patent image retrieval based on shape features
Wenli Yang, Zhiyuan Zeng, Yujie Bai · 2009
Based on the concrete characteristics and application background of design patent, according to the deficiengy of the present retrieval system of design patent database, this paper proposed an design patent image shape retrieval method based on the improved morphological description matrix and simulated annealing particle swarm optimization algorithm (SA-PSO), which can not only reflects the morphological characteristics of design patent image, but also has translation, rotation and scale invariances. The experimental results indicated that the proposed method can retrieve similar design patent images fast and efficiently, and improve the recall ratio and precision ratio of design patent image retrieval.