A Review of Recent Texture Classification: Methods.

Abstract

Texture classification is used in various pattern recognition applications that possess feature-liked Appearance. This paper aims to compile the recent trends on the usage of feature extraction and classification methods used in the research of texture classification as well as the texture datasets used for the experiments. The study shows that the signal processing methods, such as Gabor filters and wavelets are gaining popularity but old methods such as GLCM are still used but are improved with new calculations or combined with other methods. For the classifiers, nearest neighbor algorithms are still fairly popular despite being simple and SVM has become a major classifier used in texture classification. For the datasets, DynTex, Brodatz texture dataset is the most popularly used dataset despite it being old and with limited samples, other datasets are less used. I. Introduction Texture classification is the process to classify different textures from the given images. Although the classification of textures itself often seems to be meaningless in its own sense, texture classification can however be implemented a large variety of real world problems involving specific textures of different objects [1]. Some of the real world applications that involve textured objects of surfaces include rock classification [2], wood species recognition [3], face Detection [4], fabric classification [5], geographical landscape segmentation [6] and etc. All these applications allowed the target subjects to be viewed as a specific type of texture and hence they can be solved using texture classification techniques. Texture classification techniques are grouped up in five main groups in general, namely 1) structural; 2) statistical; 3) signal processing; 4) model-based stochastic [1], and; 5) morphology-based methods [7]. Out of the five groups, statistical and signal processing methods are the most widely used because they can be directly applied onto any type of texture. The rest are not as widely used because the structural methods need to implemented on structured textures which are naturally rare, the model based stochastic methods are not easily implemented due to the complexity to estimate the parameters and morphology-based methods are relatively new and the process are very simple, they may not promise very good textural features. The main objective of this paper is to compile the recent trends in texture classification in terms of feature extraction and classification methods used as well as the texture datasets used in the training and testing process within the last five years. Section 2 shows the feature extraction methods used in the recent years. Section 3 shows the classification methods used in the recent years. Section 4 shows the popularly