Binary Gabor pattern feature extraction technique for hardwood species classification

Abstract

This paper presents a binary Gabor pattern (BGP) feature extraction technique to acquire significant texture features of microscopic images of hardwood species and later these feature are used to discriminate the hardwood species into 75 different categories. The usefulness of the BGP feature extraction technique has been examined with the help of three classifiers, namely, linear support vector machine (LSVM), radial basis function support vector machine (RBFSVM) and random forest (RF) classification algorithms. Further, the performance of the BGP feature extraction technique for hardwood species classification has been evaluated against several texture feature techniques. The comparison of the results obtained by the feature extraction techniques recommends that BGP feature extraction technique has been better for microscopic images of hardwood species classification than the other feature extraction techniques. © 2018 IEEE.