Disease Detection in Apple Leaves Using Deep Convolutional Neural Network

• Published in: Agriculture (Basel) Vol. 11; no. 7; p. 617
• Main Authors: Bansal, Prakhar, Kumar, Rahul, Kumar, Somesh
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.07.2021
• Subjects: Accuracy; Agriculture; Algorithms; apple scab; Apples; Artificial neural networks; automatic detection; Automation; Classification; convolutional neural network; Crop diseases; Crops; data collection; Datasets; Deep learning; DenseNet121; Disease detection; EfficientNetB7; Farms; Fruit trees; Fruits; Leaves; Machine learning; Medical imaging; Model accuracy; Neural networks; Plant diseases; Rust fungi; Support vector machines; transfer learning
• DOI: 10.3390/agriculture11070617
• ISSN: 2077-0472

The automatic detection of diseases in plants is necessary, as it reduces the tedious work of monitoring large farms and it will detect the disease at an early stage of its occurrence to minimize further degradation of plants. Besides the decline of plant health, a country’s economy is highly affected by this scenario due to lower production. The current approach to identify diseases by an expert is slow and non-optimal for large farms. Our proposed model is an ensemble of pre-trained DenseNet121, EfficientNetB7, and EfficientNet NoisyStudent, which aims to classify leaves of apple trees into one of the following categories: healthy, apple scab, apple cedar rust, and multiple diseases, using its images. Various Image Augmentation techniques are included in this research to increase the dataset size, and subsequentially, the model’s accuracy increases. Our proposed model achieves an accuracy of 96.25% on the validation dataset. The proposed model can identify leaves with multiple diseases with 90% accuracy. Our proposed model achieved a good performance on different metrics and can be deployed in the agricultural domain to identify plant health accurately and timely.