Research Article
Identification of Abnormal Cucumber Leaves Image Based on Recurrent Residual U-Net and Support Vector Machine Techniques
@INPROCEEDINGS{10.1007/978-3-031-28816-6_7, author={Nguyen Thanh Binh and Nguyen Kim Quyen}, title={Identification of Abnormal Cucumber Leaves Image Based on Recurrent Residual U-Net and Support Vector Machine Techniques}, proceedings={Context-Aware Systems and Applications. 11th EAI International Conference, ICCASA 2022, Vinh Long, Vietnam, October 27-28, 2022, Proceedings}, proceedings_a={ICCASA}, year={2023}, month={3}, keywords={Cucumber leaf diseases Recurrent residual U-Net SVM Identify diseases}, doi={10.1007/978-3-031-28816-6_7} }- Nguyen Thanh Binh
Nguyen Kim Quyen
Year: 2023
Identification of Abnormal Cucumber Leaves Image Based on Recurrent Residual U-Net and Support Vector Machine Techniques
ICCASA
Springer
DOI: 10.1007/978-3-031-28816-6_7
Abstract
Cucumber diseases arise and spread quickly, affecting the yield and quality of cucumbers. The correct diagnosis of diseases on cucumber leaves is an important factor determining the success of control measures. To support accurate identification of cucumber leaf diseases, we proposed a machine learning method to identify powdery mildew diseases, downy mildew diseases, blight diseases, and anthracnose diseases on cucumber leaves. Most of the features of these diseases are similar. Therefore, the automatic identification of these diseases presents many challenges. The proposed method uses the recurrent residual U-Net deep learning model and the traditional support vector machine technique to identify diseases on cucumber leaves with an average accuracy of 96.33%, higher than other methods.
