Packaging Design Image Segmentation Based on Improved Full Convolutional Networks

Packaging design plays a critical role in brand recognition and cultural dissemination, yet the traditional design process is time-consuming and dependent on the designer’s technical skills, making it difficult to quickly respond to market changes and consumer demands. In recent years, advancements...

Full description

Saved in:
Bibliographic Details
Main Authors: Chunxiao Zhang, Mengmeng Han, Jingjing Jia, Chulsoo Kim
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10742
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154383717302272
author Chunxiao Zhang
Mengmeng Han
Jingjing Jia
Chulsoo Kim
author_facet Chunxiao Zhang
Mengmeng Han
Jingjing Jia
Chulsoo Kim
author_sort Chunxiao Zhang
collection DOAJ
description Packaging design plays a critical role in brand recognition and cultural dissemination, yet the traditional design process is time-consuming and dependent on the designer’s technical skills, making it difficult to quickly respond to market changes and consumer demands. In recent years, advancements in machine learning, particularly in the field of natural language processing (NLP), have paved the way for novel methods in other areas, such as image processing and packaging design. This study draws inspiration from advanced NLP techniques and proposes an improved fully convolutional network (FCN) model for image semantic segmentation, which is applied to packaging design. The model integrates superpixel technology, multi-branch networks, dual-attention mechanisms, and edge knowledge distillation in a manner analogous to the approach taken by NLP models in the context of semantic segmentation and context understanding. The experimental results showed that the model achieved significant improvements in accuracy, inference efficiency, and memory usage, with an average accuracy of 96.84% and a false-alarm rate of only 2.78%. Compared to traditional methods, the proposed model achieved over 96% accuracy across 50 packaging design images, with an average segmentation error rate of only 1.42%. By incorporating machine learning techniques from NLP into image processing, this study enhances the overall quality and efficiency of packaging design and provides new directions for the application of advanced technologies across different fields.
format Article
id doaj-art-3dff03a0a2744d1bad5cc2c4605a566b
institution Kabale University
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-3dff03a0a2744d1bad5cc2c4605a566b2024-11-26T17:49:59ZengMDPI AGApplied Sciences2076-34172024-11-0114221074210.3390/app142210742Packaging Design Image Segmentation Based on Improved Full Convolutional NetworksChunxiao Zhang0Mengmeng Han1Jingjing Jia2Chulsoo Kim3College of Design and Fine Arts, Qingdao Huanghai University, 1145, Linghai Road, West Coast New District, Qingdao 266427, ChinaDepartment of Industrial Design, Pukyong National University, 45, Yongso-ro, Nam-Gu, Busan 48513, Republic of KoreaDepartment of Industrial Design, Pukyong National University, 45, Yongso-ro, Nam-Gu, Busan 48513, Republic of KoreaDepartment of Industrial Design, Pukyong National University, 45, Yongso-ro, Nam-Gu, Busan 48513, Republic of KoreaPackaging design plays a critical role in brand recognition and cultural dissemination, yet the traditional design process is time-consuming and dependent on the designer’s technical skills, making it difficult to quickly respond to market changes and consumer demands. In recent years, advancements in machine learning, particularly in the field of natural language processing (NLP), have paved the way for novel methods in other areas, such as image processing and packaging design. This study draws inspiration from advanced NLP techniques and proposes an improved fully convolutional network (FCN) model for image semantic segmentation, which is applied to packaging design. The model integrates superpixel technology, multi-branch networks, dual-attention mechanisms, and edge knowledge distillation in a manner analogous to the approach taken by NLP models in the context of semantic segmentation and context understanding. The experimental results showed that the model achieved significant improvements in accuracy, inference efficiency, and memory usage, with an average accuracy of 96.84% and a false-alarm rate of only 2.78%. Compared to traditional methods, the proposed model achieved over 96% accuracy across 50 packaging design images, with an average segmentation error rate of only 1.42%. By incorporating machine learning techniques from NLP into image processing, this study enhances the overall quality and efficiency of packaging design and provides new directions for the application of advanced technologies across different fields.https://www.mdpi.com/2076-3417/14/22/10742image semantic segmentationfully convolutional networksuperpixel technologyknowledge distillationpacking design
spellingShingle Chunxiao Zhang
Mengmeng Han
Jingjing Jia
Chulsoo Kim
Packaging Design Image Segmentation Based on Improved Full Convolutional Networks
Applied Sciences
image semantic segmentation
fully convolutional network
superpixel technology
knowledge distillation
packing design
title Packaging Design Image Segmentation Based on Improved Full Convolutional Networks
title_full Packaging Design Image Segmentation Based on Improved Full Convolutional Networks
title_fullStr Packaging Design Image Segmentation Based on Improved Full Convolutional Networks
title_full_unstemmed Packaging Design Image Segmentation Based on Improved Full Convolutional Networks
title_short Packaging Design Image Segmentation Based on Improved Full Convolutional Networks
title_sort packaging design image segmentation based on improved full convolutional networks
topic image semantic segmentation
fully convolutional network
superpixel technology
knowledge distillation
packing design
url https://www.mdpi.com/2076-3417/14/22/10742
work_keys_str_mv AT chunxiaozhang packagingdesignimagesegmentationbasedonimprovedfullconvolutionalnetworks
AT mengmenghan packagingdesignimagesegmentationbasedonimprovedfullconvolutionalnetworks
AT jingjingjia packagingdesignimagesegmentationbasedonimprovedfullconvolutionalnetworks
AT chulsookim packagingdesignimagesegmentationbasedonimprovedfullconvolutionalnetworks