Rice grain disease identification using dual phase convolutional neural network based system aimed at small dataset
This work addresses rice grain disease identification for agricultural applications, but it is incremental as it adapts existing methods (Faster RCNN and CNN) to a small dataset.
The paper tackled the problem of plant disease detection with limited data by proposing a dual-phase CNN method that first crops rice grains from images to remove background heterogeneity, then classifies diseases on the simplified samples, achieving 88.07% accuracy in 5-fold cross-validation.
Although Convolutional neural networks (CNNs) are widely used for plant disease detection, they require a large number of training samples when dealing with wide variety of heterogeneous background. In this work, a CNN based dual phase method has been proposed which can work effectively on small rice grain disease dataset with heterogeneity. At the first phase, Faster RCNN method is applied for cropping out the significant portion (rice grain) from the image. This initial phase results in a secondary dataset of rice grains devoid of heterogeneous background. Disease classification is performed on such derived and simplified samples using CNN architecture. Comparison of the dual phase approach with straight forward application of CNN on the small grain dataset shows the effectiveness of the proposed method which provides a 5 fold cross validation accuracy of 88.07%.