INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
A Fruit Identification with Classification Fault Detection Technique using K-means clustering
Authors Name:
Gholve Sujata
, Prof. Mane Ashok
Unique Id:
IJSDR2011019
Published In:
Volume 5 Issue 11, November-2020
Abstract:
As of late, it has been exhibited that visual recognition and ML techniques can be utilized to create frameworks that keep tracks of human natural product utilization.Diseases in fruit cause devastating problem in economic losses and production in agricultural industry world wide. All the fruits were analyzed on the basis of their color (RGB space),shape and texture and then classified using different classifiers to find the classifier that gives the best accuracy.The image processing based proposed approach is composed of the first step K-Means clustering technique is used for the image segmentation, in the second step some features are extracted from the segmented image, and finally images are classified into one of the classes by using a Support Vector Machine.Our experimental results express that the proposed solution can significantly support accurate detection and automatic classification of fruit diseases. Grey Level Co-occurrence Matrix (GLCM) is used to calculate texture features.Currently we perform the analysis for Apple, Orange, Grapes, pomegranate & banana.
"A Fruit Identification with Classification Fault Detection Technique using K-means clustering", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.5, Issue 11, page no.115 - 120, November-2020, Available :http://www.ijsdr.org/papers/IJSDR2011019.pdf
Downloads:
000337074
Publication Details:
Published Paper ID: IJSDR2011019
Registration ID:192697
Published In: Volume 5 Issue 11, November-2020
DOI (Digital Object Identifier):
Page No: 115 - 120
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn