Identifying plants by using the images of their leaves. Automated systems for plant recognition can be used to classify plants into appropriate taxonomies.
Project Team members
Bedikhanna Pavan Kulkarni (Mentor)
- DATE: 2022-10-20
- Team : The MATLAB team
- Domain: Computer Vision, Machine learning
In recent decades, digital image processing, image analysis and machine vision have been sharply developed, and they have become a very important part of artificial intelligence and the interface between human and machine grounded theory and applied technology. These technologies have been applied widely in industries, medicine and agriculture. Finger print recognition is well developed and face recognition is rapidly improving. As part of this project, the elaboration of such an application has been attempted. In this work, a recognition system capable of identifying plants by using the images of their leaves has been developed. Automated systems for plant recognition can be used to classify plants into appropriate taxonomies. Such information can be useful for botanists, industrialists, food engineers and physicians. Many researchers have made an attempt for plant identification. Some approaches identify the plants based on plant image colour histogram, edge features and its texture information. They also classify the plants as trees, shrubs and herbs using complication classifier algorithms. But this proposed project work makes a simple approach by just considering leaf details using simple Support Vector Machine Classifier (SVM) for image classification without many complications. Lots of researchers have proposed many methods for finding out the area of the leaf in an image. Out of these our work uses a simple and a robust area calculation by using another object as reference. Out of many edge detection techniques, this proposed work uses Sobel edge detection algorithm which extracts the boundary pattern successful. Here we are developing a GUI application which would be useful for the users to detect the leaves with ease.