Paper job page number identification method based on Fast-RCNN

Abstract

The invention belongs to the technical field of image recognition in particular to a paper job page number recognition method based on a Faster-RCNN, and aims to solve the problems that in the prior art, a training set is not rich, and a page number training set of a graph and/or image combination style does not exist, so that the page number recognition accuracy is low, and some page numbers cannot be recognized. The method comprises the following steps: calculating a page number center coordinate in a page picture through a paper job page number positioning method, and obtaining the page number picture by using a rectangular frame; and obtaining a corresponding page number category through the page number identification model. The page number identification model is constructed based ona Faster-RCNN network, and the training sample set, the sample label and the to-be-identified page number picture are selected from the same book. The page numbers of the same book are used as the data source, sample expansion is carried out, the sample sets with different effects are generated for the page numbers of different styles, the labels corresponding to the samples are automatically generated, the page number recognition accuracy is high, the robustness is high, and the efficiency is high.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a paper job page number recognition method based on Faster-RCNN. Background technique [0002] The key to page number recognition is the recognition of printed numbers on the page. There are three main types of existing printed number recognition methods: number recognition methods based on template matching, number recognition methods based on feature analysis, and number 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 greatly different from the digital font to be recognized, it cannot be recognized, so the dependence on the template is very strong, resulting in weak robustness. The image is sensitive to noise and displacement. [0004] The method based on feature analysis: the purpose of identifying t...

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