# Sequence-to-Label Script Identification for Multilingual OCR

arXiv: https://arxiv.org/abs/1708.04671 · HTML: https://mlsanity.com/paper/1708.04671/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2017.

## Built on by (most cited first, 12 of 12)

- [Rethinking Text Line Recognition Models](https://mlsanity.com/paper/2104.07787/) (2021)
- [A Multiplexed Network for End-to-End, Multilingual OCR](https://mlsanity.com/paper/2103.15992/) (2021)
- [Post-OCR Paragraph Recognition by Graph Convolutional Networks](https://mlsanity.com/paper/2101.12741/) (2021)
- [Lexically Aware Semi-Supervised Learning for OCR Post-Correction](https://mlsanity.com/paper/2111.02622/) (2021)
- [Advancing Post-OCR Correction: A Comparative Study of Synthetic Data](https://mlsanity.com/paper/2408.02253/) (2024)
- [MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition](https://mlsanity.com/paper/2305.14758/) (2023)
- [OCR Improves Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2202.13274/) (2022)
- [Weakly supervised information extraction from inscrutable handwritten document images](https://mlsanity.com/paper/2306.06823/) (2023)
- [KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark](https://mlsanity.com/paper/2410.18277/) (2024)
- [Lacuna Reconstruction: Self-supervised Pre-training for Low-Resource Historical Document Transcription](https://mlsanity.com/paper/2112.08692/) (2021)
- [On-Device Spatial Attention based Sequence Learning Approach for Scene Text Script Identification](https://mlsanity.com/paper/2112.00448/) (2021)
- [Developing a Mixed-Methods Pipeline for Community-Oriented Digitization of Kwak'wala Legacy Texts](https://mlsanity.com/paper/2506.01775/) (2025)

## Abstract (arXiv)

We describe a novel line-level script identification method. Previous work repurposed an OCR model generating per-character script codes, counted to obtain line-level script identification. This has two shortcomings. First, as a sequence-to-sequence model it is more complex than necessary for the sequence-to-label problem of line script identification. This makes it harder to train and inefficient to run. Second, the counting heuristic may be suboptimal compared to a learned model. Therefore we reframe line script identification as a sequence-to-label problem and solve it using two components, trained end-toend: Encoder and Summarizer. The encoder converts a line image into a feature sequence. The summarizer aggregates the sequence to classify the line. We test various summarizers with identical inception-style convolutional networks as encoders. Experiments on scanned books and photos containing 232 languages in 30 scripts show 16% reduction of script identification error rate compared to the baseline. This improved script identification reduces the character error rate attributable to script misidentification by 33%.