Hybrid fuzzy support vector machine approach for Coconut tree classification using image measurement

Abstract

Classification of trees based on morphological parameters is important for identification, taxonomy, ecological research, conservation etc. The manual measurement of these parameters is tedious, laborious, and inconsistent. Even though there are many tree classification methods based on the morphological parameters available in the literature, there is hardly any research in classification of Coconut trees based on morphological parameters. This research proposes a novel hybrid fuzzy support vector machine approach for classification of Coconut trees based on three critical morphological parameters such as height, inclination, and orientation. A fuzzy logic-based parameter measurement from image is used to estimate critical morphological parameters the from the images. An original dataset of 17000 images of Indian west coast tall Coconut trees is created to train and test the proposed method. The classification for each of the three parameters is carried out separately using fuzzy logic and support vector machine and the best classification is chosen using confidence voting method. The final classification of the Coconut trees based on all the three parameters is obtained using weight-based indexing by combining the individual outcome of confidence voting method. The results showed that the proposed architecture gives better performance than state-of-the-art classifiers, with an accuracy of 88.86%. The statistical analysis showed that the proposed architecture is stable and robust than other methods, gives least confidence interval value of ±2.5, ±3.2, ±1.9 for three different datasets other than the original dataset.