Performance Analysis of Support Vector Machine in Defective and Non Defective Mangoes Classification
Neeraj Kumari1, D. Ashutosh Kr. Bhatt2, Rakesh Kr. Dwivedi3, Rajendra Belwal4

1Neeraj Kumari, Research Scholor, U.K. Technical University, Dehradun (Uttarakhand), India.
2D. Ashutosh Kr. Bhatt, Associate Professor Birla Institute, Bhimtal (Uttarakhand), India.
3Rakesh Kr. Dwivedi, Professor CCSIT, TMU, Moradabad (U.P), India.
4Rajendra Belwal, Professor Amrapali Institute Haldwani (Uttarakhand), India.

Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 1563-1571 | Volume-8 Issue-4, April 2019 | Retrieval Number: D6669048419/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Automation in agriculture field is the latest topic among researchers. In automated quality testing and grading of food and food products, non-destructive computer vision techniques are playing the vital role for customer satisfaction related to product quality. In machine learning algorithms support vector machine (SVM) has been used in various fields like image classification, information retrieving, text classification/character learning. In this paper we are introducing SVM for the classification of defected and non defected Indian mangoes. In surface defect detection K-Mean clustering and FCM algorithm are used. Performance of K-Means clustering is measured well as compared to FCM. For classification linear SVM is used. SVM achieves a substantial improvement over a variety of different machine learning algorithms. These algorithms are fully automatic that eliminates the need of manual parameter tuning. SVM results of data classification are satisfactory and getting 92% accuracy in Classification.
Keywords: SVM, K-Mean, Automation, Classification, Machine Learning, Non-Destructive, Computer Vision, Food Quality

Scope of the Article: Classification