Texture Features and Image Texture Models
Image texture is an important phenomenon in many applications of pattern recognition and computer vision. Hence, several models for deriving texture properties have been proposed and developed. Although there is no formal definition of image texture in th
- PDF / 1,268,541 Bytes
- 36 Pages / 439.37 x 666.142 pts Page_size
- 11 Downloads / 249 Views
Texture Features and Image Texture Models
A smooth sea never made a skillful sailor. —American proverb
Image texture is an important phenomenon in many applications of pattern recognition and computer vision. Hence, several models for deriving texture properties have been proposed and developed. Although there is no formal definition of image texture in the literature, image texture is usually considered the spatial arrangement of grayscale pixels in a neighborhood on the image. In this chapter, some widely used image texture methods for measuring and extracting texture features will be introduced. These textural features can then be used for image texture classification and segmentation. Specifically, the following methods will be described: (1) the gray-level co-occurrence matrices (GLCM) which is one of the earliest methods for image texture extraction, (2) Gabor filters, (3) wavelet transform (WT) model and its extension, (4) autocorrelation function, (5) Markov random fields (MRF), (6) fractal features, (7) variogram, (8) local binary pattern (LBP), and (9) texture spectrum (TS). LBP has been frequently used for image texture measure. MRF is a statistical model which has been well studied in image texture analysis and other applications. There is one common property associated with these methods and models which use the spatial relationship for texture measurement and classification.
2.1
Introduction
Texture is used to describe a region in which textural elements are characterized in a spatial relationship. An image may consist of one or more textures. If multiple textures exist in an image, the boundary between two textures can be detected and discriminated using texture measure. Texture measure can provide important information for image segmentation, feature extraction, and image classification. Texture measure is very useful in the interpretation of images taken from satellite remote sensing, medical magnetic resonance imaging, materials science, and aerial © Springer Nature Switzerland AG 2019 C.-C. Hung et al., Image Texture Analysis, https://doi.org/10.1007/978-3-030-13773-1_2
15
16
2
Texture Features and Image Texture Models
terrain photographs. For example, the study of urban and rural land development in satellite images can benefit from using the image texture analysis. There exist many texture measures for characterizing a texture. The characterization is called texture feature. Regional properties such as coarseness, homogeneity, density, fineness, smoothness, linearity, directionality, granularity, and frequency have been frequently used as texture features. Many approaches which consist of autocorrelation functions, grayscale co-occurrence matrices, and LBP are used to describe and extract texture features in an image. All of these approaches fall in the four categories: statistical methods, structural methods, model-based methods, and transform-based methods [23–25, 63]. In most cases, texture features are represented numerically by feature vectors, which are composed of feature components de
Data Loading...