Insights into Rhubarb Diversity: A Combined CNN-PCA Model for Three Class Categorization

This research introduces a new way to make it more accurate in figuring out different kinds of rhubarb. It brings together two methods: Convolutional Neural Networks (CNN) and Principal Component Analysis (PCA). Rhubarb, with many types available, is sorted in different ways based on what it naturally has. The suggested combined model plans to deal with this complexity by using the good points of CNN for getting features and PCA for reducing size. The way of doing this is by teaching a special kind of computer brain called CNN. It helps to learn details that can be seen in 6,000 pictures of rhubarb. These little and complex patterns are needed to know the differences between Victoria, Crimson Red, and Ruby types when divided up into groups by color or type. This helps show information more quickly. The mixed model combines these improved parts, giving a complete picture of different rhubarb kinds. The tests show that the new method works well. It makes rhubarb sorting more accurate at 97.25% and strong in distinguishing different types of this plant. The mix of CNN and PCA not only makes use of deep learning but also improves the feature space for better understanding. This study helps with how to sort out types of crops. It gives a good way to check rhubarb kinds right away and quickly in real-world use situations.