A new Flutter project.
A mobile application has been developed, which performs classification for the detection of diseases and plant pests, for real-time use. In this way, it will be possible to classify plants taken with a mobile phone or tablet instantly. In the Flutter-based application, TensorFlow Lite library was preferred for efficient use of deep learning tools. Here TensorFlow Lite is used to convert the models into FlatBuffer files (.tflite). These converted models were then integrated into the application's folder using TensorFlow version 2.4.1.
For mobile application development, the Android Studio Graffe and Visual Studio Code environments were used, alongside Flutter 2.3.0 -a popular cross-platform framework- supported in these environments. Dart, an object-oriented programming language, was employed for coding in the Visual Studio Code environment. The code underwent thorough testing for performance and functionality on the Pixel 2 Android x86 emulator, after which an APK was generated and installed on a smartphone. Figure 5 shows the developed mobile application and the implementation of the models.
This project is a starting point for a Flutter application.
A few resources to get you started if this is your first Flutter project:
For help getting started with Flutter development, view the online documentation, which offers tutorials, samples, guidance on mobile development, and a full API reference.