Next Article in Journal
Novel In Silico Strategies to Model the In Vivo Nerve Scarring Around Implanted Parylene C Devices
Previous Article in Journal
Evaluating Environmental Impacts of Urban Development Strategies: A Case Study of the Fontaine d’Ouche District
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Packaging Design Image Segmentation Based on Improved Full Convolutional Networks

1
College of Design and Fine Arts, Qingdao Huanghai University, 1145, Linghai Road, West Coast New District, Qingdao 266427, China
2
Department of Industrial Design, Pukyong National University, 45, Yongso-ro, Nam-Gu, Busan 48513, Republic of Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2024, 14(22), 10742; https://doi.org/10.3390/app142210742
Submission received: 6 September 2024 / Revised: 11 October 2024 / Accepted: 19 October 2024 / Published: 20 November 2024
(This article belongs to the Section Computing and Artificial Intelligence)

Abstract

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.
Keywords: image semantic segmentation; fully convolutional network; superpixel technology; knowledge distillation; packing design image semantic segmentation; fully convolutional network; superpixel technology; knowledge distillation; packing design

Share and Cite

MDPI and ACS Style

Zhang, C.; Han, M.; Jia, J.; Kim, C. Packaging Design Image Segmentation Based on Improved Full Convolutional Networks. Appl. Sci. 2024, 14, 10742. https://doi.org/10.3390/app142210742

AMA Style

Zhang C, Han M, Jia J, Kim C. Packaging Design Image Segmentation Based on Improved Full Convolutional Networks. Applied Sciences. 2024; 14(22):10742. https://doi.org/10.3390/app142210742

Chicago/Turabian Style

Zhang, Chunxiao, Mengmeng Han, Jingjing Jia, and Chulsoo Kim. 2024. "Packaging Design Image Segmentation Based on Improved Full Convolutional Networks" Applied Sciences 14, no. 22: 10742. https://doi.org/10.3390/app142210742

APA Style

Zhang, C., Han, M., Jia, J., & Kim, C. (2024). Packaging Design Image Segmentation Based on Improved Full Convolutional Networks. Applied Sciences, 14(22), 10742. https://doi.org/10.3390/app142210742

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop