Title: Detection of various categories of fruits and vegetables through various descriptors using machine learning techniques
Authors: Mukesh Kumar Tripathi; Dhananjay D. Maktedar
Addresses: Department of Computer Science and Engineering, Guru Nanak Dev Engineering College Bidar, Affiliated to VTU, Belagavi, Karnataka, India ' Department of Computer Science and Engineering, Guru Nanak Dev Engineering College Bidar, Affiliated to VTU, Belagavi, Karnataka, India
Abstract: An accurate and efficient recognition system for fruits and vegetables is one major challenge. To solve this challenge, we have examined various feature descriptors based on colour and texture such as RGB, CMH, CCV, CDH, LBP, CSLBP and SEH. All process of proposed framework consists three phase: 1) background subtraction; 2) feature extraction; 3) training and classification. In this paper, Otsu's thresholding is used for background subtraction. Further all segmented image is used in the feature extraction phase. Finally, C4.5 and KNN is used for training and classification. The various performances metric such as CA, precision, recall, F-measure, MCC, PRC and FPR are used to evaluate the proposed system for recognition problem. We also analysed the performance accuracy of both classifiers. In that C4.5 and KNN classifier produce CA values of 94.63% and 90.25%, respectively.
Keywords: detection; fruits; vegetables; descriptor; performance metric; C4.5; k-nearest neighbour; KNN; SVM.
International Journal of Computational Intelligence Studies, 2021 Vol.10 No.1, pp.36 - 73
Received: 27 Nov 2019
Accepted: 04 Apr 2020
Published online: 18 Mar 2021 *