Hybrid tree-fuzzy-rough set decision support for determining plant growth using vision-based descriptors

• Main Authors: Loresco, Pocholo James M., Tan, Gerhard P., Dadios, Elmer Jose P.
• Format: text
• Published: Animo Repository 2019
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/790; https://animorepository.dlsu.edu.ph/context/faculty_research/article/1789/type/native/viewcontent
• Institution: De La Salle University

© 2019 IEEE. Correct identification of the growth stage of crops contributes largely to the proper allocation and control of environmental factors for optimized harvestable products. Machine vision approaches for lettuce growth stage prediction has issues such as feature extraction, feature selection and dimensionality reduction for optimum classification accuracy, and robust framework for the prediction system. This paper presented a methodology of classifying lettuce growth stage using a Hybrid Decision Tree-Fuzzy- Rough Set. Vision features are extracted and subjected to dimensionality reduction using Decision Tree. The reduced inputs are used to design the Mamdani Fuzzy Inference system. Rough Set Theory is then applied to the Fuzzy Logic model to simplify the rules. Experimental results show a high performance in determining the growth stage of test lettuce images.