Research on Transmission Light and Recognition Algorithms of Invoice Check Code

Invoice checking code is one of the key factors affecting invoice reimbursement, but some invoice checking codes are covered by red seal, resulting in lack of information. In order to solve the identification problem of defect invoice check code, in this paper, the color distribution in the check code region and the interaction between color and light are studied, and the scheme of invoice monochrome light reverse transmission is formulated. By analyzing the gray histogram of R, G and B three-channel images, a threechannel weighted graying method for invoice images is proposed. After locating the region by vertical horizontal projection of the check codes, the binarization of the check codes is realized by double threshold segmentation, and the single character segmentation is obtained by vertical projection. Finally, character recognition is carried out by template matching method. The experimental results show that the above method can eliminate the influence of red seals and improve the accuracy of the identification of check codes for defective invoices.