Abstract
This paper presents a robust and economically efficient method for the discrimination of four mung-beans varieties on the basis of quantitative parameters, which is otherwise a challenging task due to their similar physical and morphological features, such as color, shape and size etc. Digital images of the bulk samples have been used as input data are acquired in an absolute natural environment. A total number of 230 first-order and second-order Gray Level Co-Occurrence Matrices (GLCM) textural parameters are extracted from different size of regions of interest (ROIs), the most relevant 10 features are selected by Fisher’s Co-efficient and classification capability of the selected features is verified by Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), whereas, a feed-forward ANN classifier has been employed for training and testing purpose. The best results are achieved with an average accuracy of 98.17% and 94.35% during training and testing respectively, when the data of 10 selected features from ROI (64*64) is deployed to the classifier.
Muhammad Shahid, Mehwish Bari, Muti ullah. (2019) TEXTURE FEATURES-BASED QUANTITATIVE ANALYSIS OF MUNG-BEAN VARIETIES USING MACHINE VISION APPROACH, Pakistan Journal of Engineering and Applied Sciences, VOLUME 24, Issue 1.
-
Views
2046 -
Downloads
210
Article Details
Volume
Issue
Type
Language
