Proceedings of the 2025 International Conference on Educational Innovation and Information Technology (EIIT 2025)

<Previous Article In Volume

Lightweight Detection for Candy Sorting with an Improved YOLOv8s

Authors
Jiarui Ma1, *, Peishan Li1, Weizhan Zhao1, Guie Zeng1
1Guangdong Baiyun University, Guangzhou, 510450, China
*Corresponding author. Email: 1261576099@qq.com
Corresponding Author
Jiarui Ma
Available Online 15 December 2025.
DOI
10.2991/978-2-38476-497-6_35How to use a DOI?
Keywords
Lightweight Object Detection; Small Object Detection; YOLOv8
Abstract

With the development of the wedding market, traditional manual sorting can no longer meet the requirements for efficiency and accuracy. This paper proposes a lightweight candy sorting method based on an improved YOLOv8s, in which a progressive downsampling module (ADown) is designed to enhance feature preservation for small objects and complex backgrounds through local average pooling and channel concatenation. Experiments on a self-constructed dataset of 22 candy categories demonstrate that the proposed method outperforms YOLOv8s in mAP metrics, achieves performance comparable to or even surpassing YOLOv8m, while significantly reducing parameters and computational complexity, making it more suitable for edge deployment. This study provides a feasible solution for automated candy sorting and offers a reference for lightweight object detection in resource-constrained scenarios.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Volume Title
Proceedings of the 2025 International Conference on Educational Innovation and Information Technology (EIIT 2025)
Series
Advances in Social Science, Education and Humanities Research
Publication Date
15 December 2025
ISBN
978-2-38476-497-6
ISSN
2352-5398
DOI
10.2991/978-2-38476-497-6_35How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Jiarui Ma
AU  - Peishan Li
AU  - Weizhan Zhao
AU  - Guie Zeng
PY  - 2025
DA  - 2025/12/15
TI  - Lightweight Detection for Candy Sorting with an Improved YOLOv8s
BT  - Proceedings of the 2025 International Conference on Educational Innovation and Information Technology (EIIT 2025)
PB  - Atlantis Press
SP  - 349
EP  - 355
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-497-6_35
DO  - 10.2991/978-2-38476-497-6_35
ID  - Ma2025
ER  -