Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements

The layout analysis of elements is indispensable in graphic design, as effective layout design not only facilitates the delivery of visual information but also enhances the overall esthetic appeal to the audience. The combination of deep learning and graphic design has gradually turned into a popula...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunfei Zhong, Yumei Pu, Xiaoxuan Li, Wenxuan Zhou, Hongjian He, Yuyang Chen, Lang Zhong, Danfei Liu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7797
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246744003477504
author Yunfei Zhong
Yumei Pu
Xiaoxuan Li
Wenxuan Zhou
Hongjian He
Yuyang Chen
Lang Zhong
Danfei Liu
author_facet Yunfei Zhong
Yumei Pu
Xiaoxuan Li
Wenxuan Zhou
Hongjian He
Yuyang Chen
Lang Zhong
Danfei Liu
author_sort Yunfei Zhong
collection DOAJ
description The layout analysis of elements is indispensable in graphic design, as effective layout design not only facilitates the delivery of visual information but also enhances the overall esthetic appeal to the audience. The combination of deep learning and graphic design has gradually turned into a popular research direction in graphic design in recent years. However, in the era of rapid development of artificial intelligence, the analysis of layout still requires manual participation. To address this problem, this paper proposes a method for analyzing the layout of complex layout image elements based on the improved DeepLabv3++ model. The method reduces the number of model parameters and training time by replacing the backbone network. To improve the effect of multi-scale semantic feature extraction, the null rate of ASPP is fine-tuned, and the model is trained by self-constructed movie poster dataset. The experimental results show that the improved DeepLabv3+ model achieves a better segmentation effect on the self-constructed poster dataset, with MIoU reaching 75.60%. Compared with the classical models such as FCN, PSPNet, and DeepLabv3, the improved model in this paper effectively reduces the number of model parameters and training time while also ensuring the accuracy of the model.
format Article
id doaj-art-751dcc3b6c4f46ea921e5e6d3b7aa743
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-751dcc3b6c4f46ea921e5e6d3b7aa7432025-08-20T03:58:25ZengMDPI AGApplied Sciences2076-34172025-07-011514779710.3390/app15147797Deep Learning-Based Layout Analysis Method for Complex Layout Image ElementsYunfei Zhong0Yumei Pu1Xiaoxuan Li2Wenxuan Zhou3Hongjian He4Yuyang Chen5Lang Zhong6Danfei Liu7School of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaSchool of Packaging Engineering, Hunan University of Technology, Zhuzhou 412007, ChinaThe layout analysis of elements is indispensable in graphic design, as effective layout design not only facilitates the delivery of visual information but also enhances the overall esthetic appeal to the audience. The combination of deep learning and graphic design has gradually turned into a popular research direction in graphic design in recent years. However, in the era of rapid development of artificial intelligence, the analysis of layout still requires manual participation. To address this problem, this paper proposes a method for analyzing the layout of complex layout image elements based on the improved DeepLabv3++ model. The method reduces the number of model parameters and training time by replacing the backbone network. To improve the effect of multi-scale semantic feature extraction, the null rate of ASPP is fine-tuned, and the model is trained by self-constructed movie poster dataset. The experimental results show that the improved DeepLabv3+ model achieves a better segmentation effect on the self-constructed poster dataset, with MIoU reaching 75.60%. Compared with the classical models such as FCN, PSPNet, and DeepLabv3, the improved model in this paper effectively reduces the number of model parameters and training time while also ensuring the accuracy of the model.https://www.mdpi.com/2076-3417/15/14/7797DeepLabv3+image segmentationposter layout analysisdeep learning
spellingShingle Yunfei Zhong
Yumei Pu
Xiaoxuan Li
Wenxuan Zhou
Hongjian He
Yuyang Chen
Lang Zhong
Danfei Liu
Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
Applied Sciences
DeepLabv3+
image segmentation
poster layout analysis
deep learning
title Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
title_full Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
title_fullStr Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
title_full_unstemmed Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
title_short Deep Learning-Based Layout Analysis Method for Complex Layout Image Elements
title_sort deep learning based layout analysis method for complex layout image elements
topic DeepLabv3+
image segmentation
poster layout analysis
deep learning
url https://www.mdpi.com/2076-3417/15/14/7797
work_keys_str_mv AT yunfeizhong deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT yumeipu deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT xiaoxuanli deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT wenxuanzhou deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT hongjianhe deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT yuyangchen deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT langzhong deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements
AT danfeiliu deeplearningbasedlayoutanalysismethodforcomplexlayoutimageelements