Intelligent Classification model for cashew kernel grades on the basis of Morphological, Colour and Texture features

Narendra, V G and Hareesha, K S (2015) Intelligent Classification model for cashew kernel grades on the basis of Morphological, Colour and Texture features. In: International Conference on Agriculture and Biological Sciences, July 25-28, Beijing, China.

[img] PDF
Narendra_V_G_paper_abs2015_eprint_8.pdf - Published Version
Restricted to Registered users only

Download (625kB) | Request a copy

Abstract

In this this paper, we have discussed how to build a supervised intelligent classification models for White Wholes (WW) grades of cashew kernel using different images. The morphological, colour and texture features are used to train or test different classifiers for recognition and classification. In order to achieve best prediction accuracy, the subsets of features from feature sets are selected using correlation-based feature selection (CFS) algorithm. In this study, the best prediction accuracy was obtained for the Multilayer Perceptron, Simple Logistic, Support Vector Machines, Sequential Minimal Optimization and Logistic classifiers. The percentage of classification models are correctly classified for the training or test set of WW grades was ranging from 70% to 90%, and the validation set was up to 86%. The Receiver Operating Characteristics (ROC) was used to present the studied classifiers performance of WW grades cashew kernel recognition and classification

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Classification model; White wholes cashew kernel grad; Morphological features; Colour features; Texture features
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 14 Jan 2016 10:21
Last Modified: 14 Jan 2016 10:21
URI: http://eprints.manipal.edu/id/eprint/145065

Actions (login required)

View Item View Item