基于快速RCNN的场景文本识别算法

2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS) Pub Date : 2017-06-03 DOI:10.1109/EIIS.2017.8298720

Boya Wang, Jianqing Xu, Junbao Li, Cong Hu, Jeng-Shyang Pan

{"title":"基于快速RCNN的场景文本识别算法","authors":"Boya Wang, Jianqing Xu, Junbao Li, Cong Hu, Jeng-Shyang Pan","doi":"10.1109/EIIS.2017.8298720","DOIUrl":null,"url":null,"abstract":"Industrial session of the natural scene in the text recognition technology has a great demand. The traditional optical character recognition technology (OCR) requires the text neat layout and neatness and background clean, and industrial production often fail to meet such standards. In this paper, a new text recognition algorithm based on deep learning is proposed for the existing problems of OCR technology. In this paper, a new method based on convolution neural network (Faster RCNN) is proposed to improve the correctness of text recognition. Compared with the conventional detection method, the correct rate of recognition based on Faster RCNN model can reach 90.4%, and the correctness rate is 88.9%. Experiments show that the recognition method in this paper is effective.","PeriodicalId":434246,"journal":{"name":"2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Scene text recognition algorithm based on faster RCNN\",\"authors\":\"Boya Wang, Jianqing Xu, Junbao Li, Cong Hu, Jeng-Shyang Pan\",\"doi\":\"10.1109/EIIS.2017.8298720\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Industrial session of the natural scene in the text recognition technology has a great demand. The traditional optical character recognition technology (OCR) requires the text neat layout and neatness and background clean, and industrial production often fail to meet such standards. In this paper, a new text recognition algorithm based on deep learning is proposed for the existing problems of OCR technology. In this paper, a new method based on convolution neural network (Faster RCNN) is proposed to improve the correctness of text recognition. Compared with the conventional detection method, the correct rate of recognition based on Faster RCNN model can reach 90.4%, and the correctness rate is 88.9%. Experiments show that the recognition method in this paper is effective.\",\"PeriodicalId\":434246,\"journal\":{\"name\":\"2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS)\",\"volume\":\"5 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-06-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/EIIS.2017.8298720\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EIIS.2017.8298720","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 11

摘要

工业会议对自然场景中的文本识别技术有很大的需求。传统的光学字符识别技术(OCR)要求文字排版整齐、背景干净，工业生产往往达不到这样的标准。针对OCR技术存在的问题，提出了一种新的基于深度学习的文本识别算法。本文提出了一种基于卷积神经网络(Faster RCNN)的文本识别方法来提高文本识别的正确率。与传统检测方法相比，基于Faster RCNN模型的识别正确率可达90.4%，正确率为88.9%。实验表明，本文提出的识别方法是有效的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Scene text recognition algorithm based on faster RCNN

Industrial session of the natural scene in the text recognition technology has a great demand. The traditional optical character recognition technology (OCR) requires the text neat layout and neatness and background clean, and industrial production often fail to meet such standards. In this paper, a new text recognition algorithm based on deep learning is proposed for the existing problems of OCR technology. In this paper, a new method based on convolution neural network (Faster RCNN) is proposed to improve the correctness of text recognition. Compared with the conventional detection method, the correct rate of recognition based on Faster RCNN model can reach 90.4%, and the correctness rate is 88.9%. Experiments show that the recognition method in this paper is effective.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2017 First International Conference on Electronics Instrumentation & Information Systems (EIIS)

自引率

0.00%

发文量