A leaf disease deep learning classification method using EfficientNet

HeSheng Liu

doi:10.1117/12.2658825

20 October 2022 A leaf disease deep learning classification method using EfficientNet

HeSheng Liu

Proceedings Volume 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022); 1245154 (2022) https://doi.org/10.1117/12.2658825
Event: 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 2022, Chongqing, China

Abstract

The planting of crops is related to the national movement and people's livelihood, and the production of crops is directly related to our country's social development and economical construction. With the rapid development of deep learning, researchers can use deep learning for disease and insect pest detection in plant leaves. In our paper, we utilized EfficientNet for crop disease classification. The Kaggle platform provides our dataset. In order to improve the performance of the model, we adopt data augmentation. Furthermore, the result shows that our EfficientNet method owns the lowest accuracy, 0.901. In contrast, the other methods like ResNext50, ResNet151 and ResNet50’s accuracy are 0.89, 0.869, 0.832 respectively.

Citation Download Citation

HeSheng Liu "A leaf disease deep learning classification method using EfficientNet", Proc. SPIE 12451, 5th International Conference on Computer Information Science and Application Technology (CISAT 2022), 1245154 (20 October 2022); https://doi.org/10.1117/12.2658825

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

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Performance modeling

3D modeling

Resistance

Convolutional neural networks

Data modeling

Feature extraction

Show All Keywords

Keywords/Phrases

Search In:

Publication Years