A leaf-based rice diseases recognition system using convolutional neural network | |
| Author | Cagadas, Dominic Olango |
| Call Number | AIT Thesis no.ISE-20-16 |
| Subject(s) | Deep learning (Machine learning) Neural network (Computer science) |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Microelectronics and Embedded Systems |
| Publisher | Asian Institute of Technology |
| Abstract | Timely detection of diseases and infection of rice plants would help farmers especially living in remote areas in treating rice plants and hopefully can increase yield in agricultural production. Developments in deep convolutional neural network has become the state-of-the-art solution for visual recognitions. As CNN has successfully waved in image classification problems, this study detects and recognizes the diseases or infection from the leaves of rice plants. Diseases under test are Bacterial Leaf Blight caused by Bacterial Infection, Rice Blast from Fungal Infection, Rice Tungro Disease from Viral Infection and Healthy Rice. Pretrained CNN models, Naïve Model, Resnet50, VGG16, VGG19 and Inception V3 are used as feature extractor and classifier. Experimental results show that amongst all models used for classification, VGG19 model has achieved an accuracy of 91.0% under less parameters and less time for training which makes the system novel, robust and efficient. |
| Year | 2020 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Industrial Systems Engineering (DISE) |
| Academic Program/FoS | Industrial Systems Engineering (ISE) |
| Chairperson(s) | Mongkol Ekpanyapong |
| Examination Committee(s) | Dailey, Matthew N.;Atthaphongse Taparugssanagorn |
| Scholarship Donor(s) | University of Science and Technology of Southern Philippines – Cagayan de Oro (USTP-CDO);Asian Institute of Technology Fellowship |
| Degree | Thesis (M. Eng.) -- Asian Institute of Technology, 2020 |