| Issue |
ITM Web Conf.
Volume 87, 2026
2nd International Conference on Computing Paradigms (ICCP-2026)
|
|
|---|---|---|
| Article Number | 01006 | |
| Number of page(s) | 7 | |
| DOI | https://doi.org/10.1051/itmconf/20268701006 | |
| Published online | 30 June 2026 | |
Real-Time Cocoon Quality Classification via CAE-Enhanced YOLOv8 Detection Framework
1 Dept ECE, BMS Institute of Technology and Management (Autonomous under VTU), Bengaluru, Karnataka India
2 Dept.ECE BMS Institute of Technology And Management(Autonomous under VTU) Bengaluru, India
3 Dept.ECE BMS Institute of Technology And Management(Autonomous under VTU) Bengaluru, Karnataka India
4 Dept.ECE BMS Institute of Technology And Management(Autonomous under VTU) Bengaluru, Karnataka India
5 Dept.ECE BMS Institute of Technology And Management(Autonomous under VTU) Bengaluru, Karnataka, India
6 Dept.ECE BMS Institute of Technology And Management(Autonomous under VTU) Bengaluru, Karnataka, India
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
Automated cocoon grading system gives better results in regards to silk production as it produces more predictable results, w ith many times faster than manual methods while still attaining a close to a stable silk quality. Manual grading by hand is very labor intensive since it is based on human eye inspection, with inconsistent outcomes. The research paper proposes an automated system for grading cocoon using a combined image acquisition control based system with data augmentation based on convolution auto encoder (CAE) technology and YOLOv8 framework for cocoon classification. With CAE augmentation, we generated 689 samples for the original collection of 305 cocoon images. We trained their study and manufactured YOLOv8 based on their results preprocessing parameters. The system achieved 98% classification accuracy and 97.5% mAP, showing its effectiveness in classifying cocoon quality. Your pipeline offers a scalable real, time automated cocoon inspection system.
Key words: Autoencoder / Cloud computing / Cocoon grading / Data augmentation / Deep learning / Image preprocessing / Real / time classification / YOLOv8
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.