After the training process, a Keras inference graph was generated indicating the predictions made by the model. This graph was then saved and frozen as a “.pb” graph thereby changing the graph to a Tensorflow graph which can be interpreted by Android Studio.
The MwogoNet application currently runs on an Android operating system and has been tested on Android version 7.
The Interfaces for the application are explained below;
Home Screen
When the user clicks the "MwogoNet icon" on the home screen,the MwogoNet home page will then be displayed as illustrated below
Home Page
On the home page, different icons are displayed which include; the Camera icon, gallery icon, manual icon and report icon.
Diagnosed Image
On clicking the camera icon, the user will be prompted to take a picture of the cassava leaf.An alternative to capturing an image using a camera is loading an image from the gallery.This can be done by clicking the gallery icon on the home page.
The diagnosis results will then be displayed on the screen as shown below
Report Page
The Report page includes details about the various cassava diseases such as Cassava Mosaic Disease, Cassava Brown Streak Disease, Cassava Green Mite and Cassava Bacterial Blight. The details in the report include the causes, symptoms and ways of prevent the disease. The Report page can be illustrated below;
