In this study, two types of cotton yarn neps, viz. seed coat and fibrous neps, have been classified by means of two standard classifiers, namely support vector machine and probabilistic neural network using the features extracted from the images of neps. At first, the region of interest is located in the captured images using k -means clustering algorithm, from which six features are extracted. These extracted features are used as dataset (both training and testing) for classifiers. A K -fold cross validation technique has been applied to assess the performance of the two classifiers. The results show that the neps classification accomplished by means of image recognition through these classifiers achieves nearly 96-97% accuracy for the test data set. Experimental results show that the required time for training probabilistic neural network is significantly less as compared to that of support vector machine.
[1]
Jianhong Wu,et al.
Data clustering - theory, algorithms, and applications
,
2007
.
[2]
Jiawei Han,et al.
Data Mining: Concepts and Techniques
,
2000
.
[3]
John A. Hartigan,et al.
Clustering Algorithms
,
1975
.
[4]
Nello Cristianini,et al.
An Introduction to Support Vector Machines and Other Kernel-based Learning Methods
,
2000
.
[5]
Vladimir Vapnik,et al.
Statistical learning theory
,
1998
.
[6]
A. Atiya,et al.
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
,
2005,
IEEE Transactions on Neural Networks.