Classification of Plant Leaf Using Shape and Texture Features

Abstract

Plants are mainly classified based on their characteristics of plant components such as leaves, flower, stem, root, seed, etc. Feature or characteristics is an essential fact for plant classification. A good feature extraction technique can help to extract quality features that give clear information to discriminate against each class. Computer engineers can help botanists to identify plants and their species through advanced computational techniques with the stipulated time. The proposed method gives efficient hybrid feature extraction using the PHOG, LBP, and GLCM feature extraction techniques. The fused feature vector is normalized and reduced size by Neighborhood Components Analysis (NCA). The efficient feature extraction and feature selection techniques have helped to improve the classification performance and reduced the model complexity. Two benchmark plant dataset Flavia and Swedish Leaves used to evaluate the proposed work. The primary contributions of this paper are introducing a multi-feature fusion shape and texture method for plant leaf image classification. The experimental result shows the average accuracy of the proposed method is 98.23%, and the average computational complexity is 147.98 s.