Context Perception Parallel Decoder for Scene Text Recognition Article Swipe

MAKE IMPACT

Yongkun Du , Zhineng Chen , Caiyan Jia , Xiaoting Yin , Chenxia Li , Yuning Du , Yu–Gang Jiang · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2307.12270

Scene text recognition (STR) methods have struggled to attain high accuracy and fast inference speed. Autoregressive (AR)-based models implement the recognition in a character-by-character manner, showing superiority in accuracy but with slow inference speed. Alternatively, parallel decoding (PD)-based models infer all characters in a single decoding pass, offering faster inference speed but generally worse accuracy. We first present an empirical study of AR decoding in STR, and discover that the AR decoder not only models linguistic context, but also provides guidance on visual context perception. Consequently, we propose Context Perception Parallel Decoder (CPPD) to predict the character sequence in a PD pass. CPPD devises a character counting module to infer the occurrence count of each character, and a character ordering module to deduce the content-free reading order and placeholders. Meanwhile, the character prediction task associates the placeholders with characters. They together build a comprehensive recognition context. We construct a series of CPPD models and also plug the proposed modules into existing STR decoders. Experiments on both English and Chinese benchmarks demonstrate that the CPPD models achieve highly competitive accuracy while running approximately 8x faster than their AR-based counterparts. Moreover, the plugged models achieve significant accuracy improvements. Code is at \href{https://github.com/PaddlePaddle/PaddleOCR/blob/dygraph/doc/doc_en/algorithm_rec_cppd_en.md}{this https URL}.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2307.12270

PDF

https://arxiv.org/pdf/2307.12270

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4385261455

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4385261455

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2307.12270

Digital Object Identifier

Title

Context Perception Parallel Decoder for Scene Text Recognition

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-07-23

Full publication date if available

Authors

Yongkun Du, Zhineng Chen, Caiyan Jia, Xiaoting Yin, Chenxia Li, Yuning Du, Yu–Gang Jiang

List of authors in order

Landing page

https://arxiv.org/abs/2307.12270

Publisher landing page

PDF URL

https://arxiv.org/pdf/2307.12270

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2307.12270

Direct OA link when available

Concepts

Computer science, Inference, Context (archaeology), Decoding methods, Character (mathematics), Speech recognition, Perception, Code (set theory), Autoregressive model, Artificial intelligence, Construct (python library), Task (project management), Pattern recognition (psychology), Natural language processing, Algorithm, Psychology, Programming language, Set (abstract data type), Management, Geometry, Paleontology, Mathematics, Economics, Neuroscience, Econometrics, Biology

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2024: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload