paper-with-me

Papers

Robust Scene Text Recognition with Automatic Rectification

2016-03-12 · CVPR 2016 6 · Baoguang Shi, Xinggang Wang, Pengyuan Lyu, Cong Yao, Xiang Bai

Recognizing text in natural images is a challenging task with many unsolved problems. Different from those in documents, words in natural images often possess irregular shapes, which are caused by perspective distortion, curved character placement, etc. We propose RARE (Robust text recognizer with Automatic REctification), a recognition model that is robust to irregular text. RARE is a specially-designed deep neural network, which consists of a Spatial Transformer Network (STN) and a Sequence Recognition Network (SRN). In testing, an image is firstly rectified via a predicted Thin-Plate-Spline (TPS) transformation, into a more "readable" image for the following SRN, which recognizes text through a sequence recognition approach. We show that the model is able to recognize several types of irregular text, including perspective text and curved text. RARE is end-to-end trainable, requiring only images and associated text labels, making it convenient to train and deploy the model in practical systems. State-of-the-art or highly-competitive performance achieved on several benchmarks well demonstrates the effectiveness of the proposed model.

📄 PDF Abstract BibTeX arXiv:1603.03915

Code (5)

Media-Smart/vedastr pytorch
PaddlePaddle/PaddleOCR paddle
WarBean/tps_stn_pytorch pytorch
iwyoo/tf_thinplatespline tf
mindspore-lab/mindocr mindspore

Tasks

Optical Character Recognition (OCR)Scene Text DetectionScene Text Recognition

Similar Papers 제목 키워드 기반

Scene Text Recognition With Finer Grid Rectification

2020-01-26 · Gang Wang

Scene Text Recognition is a challenging problem because of irregular styles and various distortions. This paper proposed an end-to-end trainable model consists of a finer rectification module and a bidirectional attentio…

DecoderScene Text Recognition

ESIR: End-to-end Scene Text Recognition via Iterative Image Rectification

2018-12-14 · CVPR 2019 6 · Fangneng Zhan, Shijian Lu

Automated recognition of texts in scenes has been a research challenge for years, largely due to the arbitrary variation of text appearances in perspective distortion, text line curvature, text styles and different types…

Scene Text Recognition

A Multi-Object Rectified Attention Network for Scene Text Recognition

2019-01-10 · Canjie Luo, Lianwen Jin, Zenghui Sun

Irregular text is widely used. However, it is considerably difficult to recognize because of its various shapes and distorted patterns. In this paper, we thus propose a multi-object rectified attention network (MORAN) fo…

DecoderObjectOptical Character Recognition (OCR)Scene Text Recognition

Portmanteauing Features for Scene Text Recognition

2022-11-09 · Yew Lee Tan, Ernest Yu Kai Chew, Adams Wai-Kin Kong, Jung-jae Kim 외

Scene text images have different shapes and are subjected to various distortions, e.g. perspective distortions. To handle these challenges, the state-of-the-art methods rely on a rectification network, which is connected…

Scene Text Recognition

Symmetry-constrained Rectification Network for Scene Text Recognition

2019-08-06 · ICCV 2019 10 · MingKun Yang, Yushuo Guan, Minghui Liao, Xin He 외

Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes. Recently, the community has paid increasing attention to the problem of recognizing text in…

DiversityScene Text Recognition