Hardwood species classification with DWT based hybrid texture feature extraction techniques

Abstract

In this work, discrete wavelet transform (DWT) based hybrid texture feature extraction techniques have been used to categorize the microscopic images of hardwood species into 75 different classes. Initially, the DWT has been employed to decompose the image up to 7 levels using Daubechies (db3) wavelet as decomposition filter. Further, first-order statistics (FOS) and four variants of local binary pattern (LBP) descriptors are used to acquire distinct features of these images at various levels. The linear support vector machine (SVM), radial basis function (RBF) kernel SVM and random forest classifiers have been employed for classification. The classification accuracy obtained with state-of-the-art and DWT based hybrid texture features using various classifiers are compared. The DWT based FOS-uniform local binary pattern (DWTFOSLBP u2) texture features at the 4 th level of image decomposition have produced best classification accuracy of 97.67 ± 0.79% and 98.40 ± 064% for grayscale and RGB images, respectively, using linear SVM classifier. Reduction in feature dataset by minimal redundancy maximal relevance (mRMR) feature selection method is achieved and the best classification accuracy of 99.00 ± 0.79% and 99.20 ± 0.42% have been obtained for DWT based FOS-LBP histogram Fourier features (DWTFOSLBP-HF) technique at the 5 th and 6 th levels of image decomposition for grayscale and RGB images, respectively, using linear SVM classifier. The DWTFOSLBP-HF features selected with mRMR method has also established superiority amongst the DWT based hybrid texture feature extraction techniques for randomly divided database into different proportions of training and test datasets.

Wood identification of Cyclobalanopsis (Endl.) Oerst based on microscopic features and CTGAN-enhanced explainable machine learning models

“…However, advances in artificial intelligence (AI) technology have led to the emergence of new ideas to facilitate rapid and accurate identification at the ßpecies" level (Tou et al, 2007;Yuliastuti et al, 2013;Mohan et al, 2014). Machine learning forms the core of AI, withdeep learning constituting a large-scale machine learning approach often employing multilayer convolutional neural networks and deep, fully connected neural networks to construct models (Yadav et al, 2015a;Hwang and Sugiyama, 2021). These models rely on vast amounts of input data and significant computing power to gain a deeper understanding of knowledge.…”

A Novel Method for Classifying Liver and Brain Tumors Using Convolutional Neural Networks, Discrete Wavelet Transform and Long Short-Term Memory Networks

“…Khatami et al [18] increased the performance of deep belief networks by using wavelet transform in radiological image classification. Yadav et al [19] used DWT-based texture feature extraction techniques to categorize the microscopic images of the hardwood species into 75 different classes.…”