Abstract
This research aims to classify the types of pests on rice leaves using Tensorflow with the CNN method to make it easier for the public to know the types of pests that exist on rice plants. The research results showed that initially the accuracy was only 61% but was successfully increased to 99% through various variation tests. Accuracy is affected by the background of the object and the distance of the device. Results show this model provides accurate predictions, with an average accuracy of around 90%. In conclusion, the results of rice plant pest classification using the CNN model for detecting rice plant pests using the Android-based Tensorflow framework make it easier to classify pest types on leafy rice plants.
 
 Keywords: CNN, Padi, Tensorflow
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
