Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis

Traditional Mongolian document layout analysis faces unique challenges due to its vertical writing system and complex structural arrangements. Existing methods often struggle with the directional nature of traditional Mongolian text and require substantial computational resources. In this paper, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenyang Zhou, Monghjaya Ha, Licheng Wu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4594
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144734663671808
author Chenyang Zhou
Monghjaya Ha
Licheng Wu
author_facet Chenyang Zhou
Monghjaya Ha
Licheng Wu
author_sort Chenyang Zhou
collection DOAJ
description Traditional Mongolian document layout analysis faces unique challenges due to its vertical writing system and complex structural arrangements. Existing methods often struggle with the directional nature of traditional Mongolian text and require substantial computational resources. In this paper, we propose a direction-aware lightweight framework that effectively addresses these challenges. Our framework introduces three key innovations: a modified MobileNetV3 backbone with asymmetric convolutions for efficient vertical feature extraction, a dynamic feature enhancement module with channel attention for adaptive multi-scale information fusion, and a direction-aware detection head with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mo form="prefix">sin</mo><mi>θ</mi><mo>,</mo><mo form="prefix">cos</mo><mi>θ</mi><mo>)</mo></mrow></semantics></math></inline-formula> vector representation for accurate orientation modeling. We evaluate our method on TMDLAD, a newly constructed traditional Mongolian document layout analysis dataset, comparing it with both heavy ResNet-50-based models and lightweight alternatives. The experimental results demonstrate that our approach achieves state-of-the-art performance, with 0.715 mAP and 92.3% direction accuracy with a mean absolute error of only 2.5°, while maintaining high efficiency at 28.6 FPS using only 8.3 M parameters. Our model outperforms the best ResNet-50-based model by 3.6% in mAP and the best lightweight model by 4.3% in mAP, while uniquely providing direction prediction capability that other lightweight models lack. The proposed framework significantly outperforms existing methods in both accuracy and efficiency, providing a practical solution for traditional Mongolian document layout analysis that can be extended to other vertical writing systems.
format Article
id doaj-art-ce403047326949fc902365909bc9a0ff
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-ce403047326949fc902365909bc9a0ff2025-08-20T02:28:16ZengMDPI AGApplied Sciences2076-34172025-04-01158459410.3390/app15084594Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout AnalysisChenyang Zhou0Monghjaya Ha1Licheng Wu2School of Chinese Ethnic Minority Languages and Literatures, Minzu University of China, Beijing 100081, ChinaCollege of Computer Science, Inner Mongolia University, Hohhot 010021, ChinaKey Laboratory of Ethnic Language Intelligent Analysis and Security Management of MOE, Minzu University of China, Beijing 100081, ChinaTraditional Mongolian document layout analysis faces unique challenges due to its vertical writing system and complex structural arrangements. Existing methods often struggle with the directional nature of traditional Mongolian text and require substantial computational resources. In this paper, we propose a direction-aware lightweight framework that effectively addresses these challenges. Our framework introduces three key innovations: a modified MobileNetV3 backbone with asymmetric convolutions for efficient vertical feature extraction, a dynamic feature enhancement module with channel attention for adaptive multi-scale information fusion, and a direction-aware detection head with <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mo>(</mo><mo form="prefix">sin</mo><mi>θ</mi><mo>,</mo><mo form="prefix">cos</mo><mi>θ</mi><mo>)</mo></mrow></semantics></math></inline-formula> vector representation for accurate orientation modeling. We evaluate our method on TMDLAD, a newly constructed traditional Mongolian document layout analysis dataset, comparing it with both heavy ResNet-50-based models and lightweight alternatives. The experimental results demonstrate that our approach achieves state-of-the-art performance, with 0.715 mAP and 92.3% direction accuracy with a mean absolute error of only 2.5°, while maintaining high efficiency at 28.6 FPS using only 8.3 M parameters. Our model outperforms the best ResNet-50-based model by 3.6% in mAP and the best lightweight model by 4.3% in mAP, while uniquely providing direction prediction capability that other lightweight models lack. The proposed framework significantly outperforms existing methods in both accuracy and efficiency, providing a practical solution for traditional Mongolian document layout analysis that can be extended to other vertical writing systems.https://www.mdpi.com/2076-3417/15/8/4594traditional Mongoliandocument layout analysisdirection-aware detectionasymmetric convolutionvector orientation representationlightweight model
spellingShingle Chenyang Zhou
Monghjaya Ha
Licheng Wu
Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis
Applied Sciences
traditional Mongolian
document layout analysis
direction-aware detection
asymmetric convolution
vector orientation representation
lightweight model
title Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis
title_full Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis
title_fullStr Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis
title_full_unstemmed Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis
title_short Direction-Aware Lightweight Framework for Traditional Mongolian Document Layout Analysis
title_sort direction aware lightweight framework for traditional mongolian document layout analysis
topic traditional Mongolian
document layout analysis
direction-aware detection
asymmetric convolution
vector orientation representation
lightweight model
url https://www.mdpi.com/2076-3417/15/8/4594
work_keys_str_mv AT chenyangzhou directionawarelightweightframeworkfortraditionalmongoliandocumentlayoutanalysis
AT monghjayaha directionawarelightweightframeworkfortraditionalmongoliandocumentlayoutanalysis
AT lichengwu directionawarelightweightframeworkfortraditionalmongoliandocumentlayoutanalysis