Our computer vision project aims to determine the type of disease affecting a leaf, along with its location on the leaf. To accomplish this, we have implemented both classification and segmentation algorithms.
For classification, we used transfer learning with the MobileNet model, which has been pre-trained on a large dataset and fine-tuned for our specific task. This allows us to achieve good results with relatively little data and minimal training time.
For segmentation, we used the U-Net architecture, which is well-suited for tasks involving image segmentation. The U-Net model has proven effective at identifying the boundaries of different objects in an image and assigning each pixel to a specific class.
This is our first project in the field of computer vision, and as such it is relatively simple. However, it can be improved upon in the future, as we continue to learn and explore new techniques and technologies.
We welcome feedback and contributions from anyone who is interested in this project or has expertise in computer vision. Please feel free to reach out to us if you have any suggestions or questions.
Thank you for your interest in our project!