Page Number Recognition Method for Paper Jobs Based on Faster-RCNN

Abstract

The present invention belongs to the technical field of image recognition, and specifically relates to a paper job page number recognition method based on Faster-RCNN. The accuracy of page number recognition is low, and some page numbers cannot be recognized. The method of the invention includes: calculating the center coordinates of the page number in the page picture through the page number positioning method of the paper job, and using a rectangular frame to obtain the page number picture; and obtaining the corresponding page number digital category through the page number recognition model. Among them, the page number recognition model is built based on the Faster-RCNN network, and the training sample set, sample label and page number picture to be recognized are selected from the same book. The invention uses the page number of the same book as a data source to expand samples, generate sample sets with different effects for different styles of page numbers, and automatically generate labels corresponding to the samples, with high page number identification accuracy, strong robustness, and high efficiency.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and particularly relates to a method for recognizing page numbers of paper work based on Faster-RCNN. Background technique [0002] The key to page number recognition lies in the recognition of page number printed numbers. There are three main types of existing printed number recognition methods: digital recognition methods based on template matching, digital recognition methods based on feature analysis, and digital recognition methods based on artificial neural networks. [0003] Digital recognition method based on template matching: The main problem is that the amount of calculation is large, and if the template is too different from the digital font to be recognized, it cannot be recognized, so the dependence on the template is very strong, resulting in its weak robustness. Images are sensitive to noise and displacement. [0004] The method based on feature analysis: the purpose of...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the above-mentioned problems in the prior art, that is, the training set of the prior art is not rich, which leads to the low accuracy of page number recognition and the problem that such page numbers cannot be recognized because there is no training set in which the page number is combined with graphics and / or images. , the present invention provides a paper job page number recognition method based on Faster-RCNN, the page number recognition method comprising:

Images