Pengenalan Penyakit pada Tanaman Pokok di Indonesia dengan Metode Convolutional Neural Network

Handy Prayoga Angjaya (Program Studi Informatika)
Kartika Gunadi (Program Studi Informatika)
Rudy Adipranata (Program Studi Informatika)

Jurnal Infra
Vol 9, No 2 (2021)

In Indonesia, the most consumed staple food is rice, the rice comes from the rice plants, besides rice, there is also cassava and corn plants. The success of harvesting these crops can affect the country's food welfare, but pest and diseases can cause crop failure. Therefore, a program was created to identify diseases in these plants to maximize crop yields. In the process of identifying the disease, the problem that often occurs is the identification of the characteristics of the disease. With the development of technology, disease recognition can be done automatically using a Neural Network. This study uses the Convolutional Neural Network (CNN) method with the Inception v3 architecture. In addition, the model used will be converted using TensorFlow Lite so that it can be used on Android-based smartphone applications. The program results from this study identified diseases in maize, potato, cassava, and rice plants. Based on the tests carried out, an average accuracy value of 90.77% was obtained in testing data test. Testing in the field actually produces an average accuracy of 65.00%.