Version 1
: Received: 21 June 2024 / Approved: 4 July 2024 / Online: 4 July 2024 (06:43:42 CEST)
How to cite:
Fan, W.; Huang, Y.; Zhang, J.; Zhang, X.; Wang, Q.; Cheng, Y. Robust Detection of Cracked Eggs Using a Multi-Domain
Training Method with NSFE-MMD for Practical Egg Production. Preprints2024, 2024070400. https://doi.org/10.20944/preprints202407.0400.v1
Fan, W.; Huang, Y.; Zhang, J.; Zhang, X.; Wang, Q.; Cheng, Y. Robust Detection of Cracked Eggs Using a Multi-Domain
Training Method with NSFE-MMD for Practical Egg Production. Preprints 2024, 2024070400. https://doi.org/10.20944/preprints202407.0400.v1
Fan, W.; Huang, Y.; Zhang, J.; Zhang, X.; Wang, Q.; Cheng, Y. Robust Detection of Cracked Eggs Using a Multi-Domain
Training Method with NSFE-MMD for Practical Egg Production. Preprints2024, 2024070400. https://doi.org/10.20944/preprints202407.0400.v1
APA Style
Fan, W., Huang, Y., Zhang, J., Zhang, X., Wang, Q., & Cheng, Y. (2024). Robust Detection of Cracked Eggs Using a Multi-Domain
Training Method with NSFE-MMD for Practical Egg Production. Preprints. https://doi.org/10.20944/preprints202407.0400.v1
Chicago/Turabian Style
Fan, W., Qiaohua Wang and Yuxuan Cheng. 2024 "Robust Detection of Cracked Eggs Using a Multi-Domain
Training Method with NSFE-MMD for Practical Egg Production" Preprints. https://doi.org/10.20944/preprints202407.0400.v1
Abstract
The presence of cracks reduces egg quality and safety, which are easy to cause food safety hazards to consumers. Machine vision-based methods for crack egg detection have made significant success on in-domain egg data. However, the performance of deep learning models usually decreases under practical industrial scenarios, such as the different egg varieties, origins, and environmental changes. Existing researches which rely on improving network structures or increasing training data volumes, can not effectively solve the problem of model performance decline on unknown egg testing data in practical egg production. To address these challenges, a novel and robust detection method is proposed to extract max domain-invariant features to enhance the model performance on unknown testing egg data. Firstly, multi-domain egg data is built on different egg origins and acquisition devices. Then, a multi-domain trained strategy is established by using Maximum Mean Discrepancy with Normalized Squared Feature Estimation (NSFE-MMD) to obtain the optimal matching egg training domain. With the NSFE-MMD method, the original deep learning model can be applied without network structure improvements, which reduces the extremely complex tuning process and hyperparameter adjustments. Finally, robust crack egg detection experiments are carried out on several unknown testing egg domains. The YOLOV5 model trained by proposed multi-domain trained method with NSFE-MMD has a detection mAP of 86.6\% on the unknown test domain 4, and the YOLOV8 model has a detection mAP of 88.8\% on domain 4, which is an increase of 8\% and 4.4\% compared to the best performance of models trained on a single domain, and an increase of 4.7\% and 3.7\% compared to models trained on all domains. In addition, the YOLOV5 model trained by the proposed multi-domain trained method has a detection mAP of 87.9\% on egg data of the unknown testing domain 5. The experimental results demonstrate the robustness and effectiveness of the proposed multi-domain trained method, which can be more suitable for the large quantity and variety of egg detection production.
Keywords
Cracked egg; unknown egg test domain; multi-domain training; MMD; robust and efficient
Subject
Engineering, Bioengineering
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
