Papers › Robust Scene Text Recognition with Automatic Rectification

Robust Scene Text Recognition with Automatic Rectification

12 Mar 2016CVPR 2016 6arXiv:1603.03915archive 2025-07-28

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Media-Smart/vedastr mentioned on GitHubpytorchApache-2.0 report
PaddlePaddle/PaddleOCR mentioned on GitHubpaddleApache-2.0 report
WarBean/tps_stn_pytorch mentioned on GitHubpytorch report
iwyoo/tf_thinplatespline mentioned on GitHubtfApache-2.0 report
mindspore-lab/mindocr mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-ready report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Optical Character Recognition (OCR)Scene Text DetectionScene Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Recognition ICDAR 2003 RARE Accuracy 90.1 #10 of 12 Archive leaderboard report
Scene Text Recognition ICDAR2013 RARE Accuracy 88.6 #36 of 38 Archive leaderboard report
Scene Text Recognition SVT RARE Accuracy 81.9 #35 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections