Leaf-Based Varietal Categorization of Sweetpotato (Ipomoea batatas L. Lam.), a Potentially Healthful Vegetable, Using Image Processing and K-Means Clustering

Abstract

Sweetpotato (Ipomoea batatas Lam) leaves contain higher concentrations of phenolic compounds, flavonoids, and carotenoids that are remarkable in health promotion. However, the nutrient content in sweetpotato leaves varies from variety to variety, and leaf shape and color are the key identifying factors for the varietal classification of sweetpotatoes. So, detecting sweetpotato leaves is essential for the in-situ identification of sweetpotato varieties and for developing intelligent agricultural systems. This study aimed to create a leaf-shape-based varietal classification technique for sweetpotato using image processing techniques coupled with a K-means clustering algorithm. 38 leaf images (RGB) of two sweetpotato cultivars were collected and pre-processed to extract relevant features. A distinct difference in leaf physical characteristics, i.e., leaf area, perimeter, circularity factor, breadth, and leaf ratio, between the two varieties was observed. K-means clustering algorithm identified two sweetpotato varieties as distinct clusters with centroid values (Cluster 0: Area 695627 and Cluster 1: Area 525895). Results revealed that sweet potato leaves in cluster 0 tend to have more prominent physical characteristics than in cluster 1. This result demonstrates the prospects of using machine learning and image processing techniques for in situ varietal classification of sweetpotato. The results bridge the visual characteristics and their quantitative assessment, fostering a deeper understanding of the plant's phenotype and supporting advancements in agriculture, research, and crop improvement.