AI Implementation

To start with the AI implementation of this project, I researched some similar exisiting projects until I found an open-source project on GitHub from Marko Arsenovic, that was comparing different results achieved by AI models using a plant disease dataset. This was an ideal starting point for my own project. A chart was also provided to clarify the results achieved by his project. I noticied that AlexNet achieved good results while not taking a lot of time to train as you can see in the chart below provided by Marko Arsenovic.

This project used an open-source dataset provided by the R&D unit of Penn State University called PlantVillage, to train the neural networks in plant disease identification. This dataset includes 38 classifications each represented by more than 1000 pictures and spread over 14 plant types. In order to verify that our AI model is performing correctly it is important to keep some data for validation. Thus, 80% of plant disease images was used for training and 20% for validation. The table on the right represents the distribution of classifications among plant types.

The results achieved by my own adaptation of this project by Marko Arsenovic, using the PlantVillage dataset, resulted in a top-1 accuracy of 91%, which is good enough as PoC for this project. Further improvements and expansions could be achieved by increasing the size of the dataset by finding additional labeled images, adding new plants and classifications to the dataset and using the data the user provides to increase the size of the dataset.