Papers › STN-OCR: A single Neural Network for Text Detection and Text Recognition

STN-OCR: A single Neural Network for Text Detection and Text Recognition

27 Jul 2017arXiv:1707.08831archive 2025-07-28

Christian Bartz, Haojin Yang, Christoph Meinel

Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In re- cent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present STN-OCR, a step towards semi-supervised neural networks for scene text recognition, that can be optimized end-to-end. In contrast to most existing works that consist of multiple deep neural networks and several pre-processing steps we propose to use a single deep neural network that learns to detect and recognize text from natural images in a semi-supervised way. STN-OCR is a network that integrates and jointly learns a spatial transformer network, that can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We investigate how our model behaves on a range of different tasks (detection and recognition of characters, and lines of text). Experimental results on public benchmark datasets show the ability of our model to handle a variety of different tasks, without substantial changes in its overall network structure.

Paper PDF Code

Code

Bartzi/stn-ocr officialmentioned in papermentioned on GitHubmxnet report

Narp99/FRI_2018 mentioned on GitHubtf report

pokalaanirudh/Text-spotting-in-wild-using-YOLO. mentioned on GitHubtf 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 Detection Scene Text Recognition Text Detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Scene Text Detection	ICDAR 2013	STN-OCR	F-Measure	90.3%	#5 of 16	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.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer ReLU Residual Connection Softmax Spatial Transformer Transformer

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