Research on printing registration recognition method

摘要

A genetic algorithm (GA) optimization support vector machine (SVM) method was proposed to solve the problem of printing registration recognition. The printing marks images were collected and the image feature parameters of Gray Level Co-occurrence Matrix (GLCM) were extracted. SVM model with radial basis function was established. GA was used to optimize the parameters of SVM, thus completing the recognition. Results show that the proposed method can effectively recognize the printing registration and meet industrial demand.