# Edit Probability for Scene Text Recognition

arXiv: https://arxiv.org/abs/1805.03384 · HTML: https://mlsanity.com/paper/1805.03384/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 May 2018.

## Built on by (most cited first, 19 of 19)

- [Benchmarking Chinese Text Recognition: Datasets, Baselines, and an Empirical Study](https://mlsanity.com/paper/2112.15093/) (2021)
- [Primitive Representation Learning for Scene Text Recognition](https://mlsanity.com/paper/2105.04286/) (2021)
- [Self-supervised Implicit Glyph Attention for Text Recognition](https://mlsanity.com/paper/2203.03382/) (2022)
- [Joint Visual Semantic Reasoning: Multi-Stage Decoder for Text Recognition](https://mlsanity.com/paper/2107.12090/) (2021)
- [Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation](https://mlsanity.com/paper/2107.12087/) (2021)
- [Seq-UPS: Sequential Uncertainty-aware Pseudo-label Selection for Semi-Supervised Text Recognition](https://mlsanity.com/paper/2209.00641/) (2022)
- [Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2106.06960/) (2021)
- [I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition](https://mlsanity.com/paper/2105.08383/) (2021)
- [Searching a High-Performance Feature Extractor for Text Recognition Network](https://mlsanity.com/paper/2209.13139/) (2022)
- [Parallel Scale-wise Attention Network for Effective Scene Text Recognition](https://mlsanity.com/paper/2104.12076/) (2021)
- [E^2VTS: Energy-Efficient Video Text Spotting from Unmanned Aerial Vehicles](https://mlsanity.com/paper/2206.02281/) (2022)
- [Natural Scene Text Editing Based on AI](https://mlsanity.com/paper/2111.15475/) (2021)
- [SAFL: A Self-Attention Scene Text Recognizer with Focal Loss](https://mlsanity.com/paper/2201.00132/) (2022)
- [Training Protocol Matters: Towards Accurate Scene Text Recognition via Training Protocol Searching](https://mlsanity.com/paper/2203.06696/) (2022)
- [HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution](https://mlsanity.com/paper/2307.16410/) (2023)
- [Towards Detecting, Recognizing, and Parsing the Address Information from Bangla Signboard: A Deep Learning-based Approach](https://mlsanity.com/paper/2311.13222/) (2023)
- [One Model for Two Tasks: Cooperatively Recognizing and Recovering Low-Resolution Scene Text Images by Iterative Mutual Guidance](https://mlsanity.com/paper/2409.14483/) (2024)
- [A Lightweight Multi-Module Fusion Approach for Korean Character Recognition](https://mlsanity.com/paper/2504.05770/) (2025)
- [OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognition](https://mlsanity.com/paper/2511.08133/) (2025)

## Abstract (arXiv)

We consider the scene text recognition problem under the attention-based encoder-decoder framework, which is the state of the art. The existing methods usually employ a frame-wise maximal likelihood loss to optimize the models. When we train the model, the misalignment between the ground truth strings and the attention's output sequences of probability distribution, which is caused by missing or superfluous characters, will confuse and mislead the training process, and consequently make the training costly and degrade the recognition accuracy. To handle this problem, we propose a novel method called edit probability (EP) for scene text recognition. EP tries to effectively estimate the probability of generating a string from the output sequence of probability distribution conditioned on the input image, while considering the possible occurrences of missing/superfluous characters. The advantage lies in that the training process can focus on the missing, superfluous and unrecognized characters, and thus the impact of the misalignment problem can be alleviated or even overcome. We conduct extensive experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets. Experimental results show that the EP can substantially boost scene text recognition performance.