Rosetta: Large Scale System for Text Detection and Recognition in Images

被引:198
作者
Borisyuk, Fedor [1 ]
Gordo, Albert [1 ]
Sivakumar, Viswanath [1 ]
机构
[1] Facebook Inc, Menlo Pk, CA 94025 USA
来源
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING | 2018年
关键词
Optical character recognition; text detection; text recognition;
D O I
10.1145/3219819.3219861
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we present a deployed, scalable optical character recognition (OCR) system, which we call Rosetta, designed to process images uploaded daily at Facebook scale. Sharing of image content has become one of the primary ways to communicate information among internet users within social networks such as Facebook, and the understanding of such media, including its textual information, is of paramount importance to facilitate search and recommendation applications. We present modeling techniques for efficient detection and recognition of text in images and describe Rosetta's system architecture. We perform extensive evaluation of presented technologies, explain useful practical approaches to build an OCR system at scale, and provide insightful intuitions as to why and how certain components work based on the lessons learnt during the development and deployment of the system.
引用
收藏
页码:71 / 79
页数:9
相关论文
共 30 条
[21]  
[Anonymous], 20 YEARS DOCUMENT IM
[22]  
[Anonymous], 2016, CVPR
[23]  
[Anonymous], CORR
[24]  
[Anonymous], 2017, ARXIV PREPRINT ARXIV
[25]  
[Anonymous], 2014, NIPS DEEP LEARN WORK
[26]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[27]  
Iandola F., 2016, SQUEEZENET ALEXNET L
[28]  
Liu Zichuan., 2018, AAAI
[29]  
Shi Baoguang, 2016, IEEE T PATTERN ANAL
[30]  
Smith C., 2013, FACEBOOK USERS ARE U