Deep-learning-based image classification for the inspection of chicken eggs (Conference Presentation)

Tae-Gyun Rho; Se-Heon Jang; Byoung-Kwan Cho

doi:10.1117/12.2665136

13 June 2023 Deep-learning-based image classification for the inspection of chicken eggs (Conference Presentation)

Tae-Gyun Rho, Se-Heon Jang, Byoung-Kwan Cho

Author Affiliations +

Proceedings Volume PC12545, Sensing for Agriculture and Food Quality and Safety XV; PC1254504 (2023) https://doi.org/10.1117/12.2665136
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

Deep-learning models were used to evaluate egg quality based on the surface condition of the eggs. Three different deep learning image classification models (EfficientNet, Swin-transformer, YOLO v5) were used for the training, and EfficientNet showed the highest accuracy with 99.7% for assessing egg quality based on the reference with 8 conditions, such as chicken manure, yolk, spot, sandy, calcium, swelling, deformed, and normal. The result demonstrates that deep learning image classification technique can be used for automated evaluation of egg quality with good accuracy.

Conference Presentation

Citation Download Citation

Tae-Gyun Rho, Se-Heon Jang, and Byoung-Kwan Cho "Deep-learning-based image classification for the inspection of chicken eggs (Conference Presentation)", Proc. SPIE PC12545, Sensing for Agriculture and Food Quality and Safety XV, PC1254504 (13 June 2023); https://doi.org/10.1117/12.2665136

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE