ABSTRACT :
The rice leaf suffers from several bacterial, viral, or fungal diseases and these diseases reduce rice production significantly. To sustain rice demand for a vast population globally, the recognition of rice leaf diseases is crucially important. However, recognition of rice leaf diseases limited to the image backgrounds and image capture conditions. The convolutional neural network (CNN) based model is a hot research topic in the field of rice leaf disease recognition. But the existing CNN-based models drop in recognition rates severely on independent dataset and are limited to the learning of large scale network parameters. In this paper, we propose a novel CNN-based model to recognize rice leaf diseases by reducing the network parameters. Using a novel dataset of 4199 rice leaf disease images, a number of CNN-based models are trained to identify five common rice leaf diseases. The proposed model achieves the highest training accuracy of 99.78% and validation accuracy of 97.35%. The effectiveness of the proposed model is evaluated on a set of independent rice leaf disease images with the best accuracy of 97.82% with an area undercurve (AUC) of 0.99. Besides that, binary classification experiments have been carried out and our proposed model achieves recognition rates of97%, 96%, 96%, 93%, and 95% for Blast, Brown spot, Bacterial Leaf Blight, Sheath Blight and Tungro, respectively. These results demonstrate the effectiveness and superiority of our approach in comparison to the state-of-the-art CNN-based rice leaf disease recognition models.
EXISTING SYSTEM :
There exists many works for identifying and classifying the plant diseases specifically for recognizing the rice leaf diseases [23]. In [2], a CNN-based frameworks developed to identify three different rice diseases and healthy images, while in[10] a CNN-based model is used to detect various plant leaf diseases. In [6], principal component analysis (PCA) is applied to remove the redundant information and provide a vector with a reduced dimension for each rice leaf disease image. Moreover, various classifiers were used to evaluate the performances and SVM is found to achieve the best recognition rate of rice leaf diseases. In [29], diagnosis of plant disease based on CNN is achieved by extracting learned features via perturbation, gradient and reference based visualization using InceptionV3.Mixed layer is used to generate deep features like shape, diversity of colours etc. It can remove 75% of parameters without affecting the accuracy and loss. In[16], it is shown that CNN-based model is more effective than traditional feature extractors including LBPH and HaarWT for recognizing rice blast disease.
DISADVANTAGES OF EXISTING SYSTEM :
1) Less accuracy
2)low Efficiency
PROPOSED SYSTEM :
This section describes our proposed method of recognizing rice leaf diseases. The entire process is partitioned into different stages: beginning with the preparation of a novel training dataset, development of a novel CNN model, deep feature extraction for training the model and finally, classification of the rice leaf diseases.
ADVANTAGES OF PROPOSED SYSTEM :
1) High accuracy
2)High efficiency
SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10
HARDWARE REQUIREMENTS:
Processor : Core I3
RAM Capacity : 2 GB
Hard Disk : 250 GB
Monitor : 15″ Color
Mouse : 2 or 3 Button Mouse
Key Board : Windows 08/10
