Papers › Revisiting Classification Perspective on Scene Text Recognition

Revisiting Classification Perspective on Scene Text Recognition

22 Feb 2021arXiv:2102.10884archive 2025-07-28

Hongxiang Cai, Jun Sun, Yichao Xiong

The prevalent perspectives of scene text recognition are from sequence to sequence (seq2seq) and segmentation. Nevertheless, the former is composed of many components which makes implementation and deployment complicated, while the latter requires character level annotations that is expensive. In this paper, we revisit classification perspective that models scene text recognition as an image classification problem. Classification perspective has a simple pipeline and only needs word level annotations. We revive classification perspective by devising a scene text recognition model named as CSTR, which performs as well as methods from other perspectives. The CSTR model consists of CPNet (classification perspective network) and SPPN (separated conv with global average pooling prediction network). CSTR is as simple as image classification model like ResNet \cite{he2016deep} which makes it easy to implement and deploy. We demonstrate the effectiveness of the classification perspective on scene text recognition with extensive experiments. Futhermore, CSTR achieves nearly state-of-the-art performance on six public benchmarks including regular text, irregular text. The code will be available at https://github.com/Media-Smart/vedastr.

Paper PDF Code

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

Media-Smart/vedastr officialmentioned in paperpytorchApache-2.0 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

Classification General Classification Image Classification Multi-class Classification Scene Text Recognition image-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Scene Text Recognition	ICDAR 2003	CSTR	Accuracy	94.8	#6 of 12	Archive leaderboard	report
Scene Text Recognition	ICDAR2013	CSTR	Accuracy	93.2	#26 of 38	Archive leaderboard	report
Scene Text Recognition	ICDAR2015	CSTR	Accuracy	81.6	#16 of 27	Archive leaderboard	report
Scene Text Recognition	SVT	CSTR	Accuracy	90.6	#24 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.

Methods

1x1 Convolution Average Pooling Batch Normalization Bottleneck Residual Block Convolution Global Average Pooling Kaiming Initialization Max Pooling ReLU Residual Block Residual Connection

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