China
Africa
Explore chapters and articles related to this topic
Image Descriptors and Features
Published in Manas Kamal Bhuyan, Computer Vision and Image Processing, 2019
Texture can be used as a feature for the description of a region. Texture analysis Texture analysis is one of the fundamental aspects of human vision by which humans can discriminate between surfaces and objects. The same concept may be applied to computer vision in which computer vision algorithms can take the advantages of the cues provided by surface texture to distinguish and recognize objects. In computer vision, texture analysis may be used alone or in combination with other sensed features (e.g., colour, shape, or motion) to recognize different objects in the scene. One important application of image texture (feature) is the recognition of image regions using texture distribution/properties. Many common low-level computer vision algorithms (such as edge detection algorithms) behave erratically when applied to images having textured surfaces. It is therefore very important to efficiently process different types of textures for image/object recognition.
Computer Vision for Microstructural Image Representation: Methods and Applications
Published in Jeffrey P. Simmons, Lawrence F. Drummy, Charles A. Bouman, Marc De Graef, Statistical Methods for Materials Science, 2019
Brian L. DeCost, Elizabeth A. Holm
The concept of texture in this context takes the same meaning as in the visual arts, as opposed to the crystallographic texture that the materials scientist will be familiar with. Image texture describes the spatial distribution of pixel-level intensity values within a region, without regard to the global shape of the region. Common image texture tasks include identifying macroscopic material surfaces [177], extracting geospatial information from satellite imagery [178], medical screening and diagnosis using 2D and 3D imaging techniques [221, 384], and various process monitoring systems in the minerals industry and surface inspection [90, 1162, 17]. Microstructure is similar in the relative unimportance of global geometry, but often the features of interest span a greater breadth of length scales than in traditional image textures. For example, a lamellar structure such as pearlite represents an image texture with a particular pixel intensity distribution; a lath martensite would evince a different distribution, and thus a different texture. However, a representative hypereutectoid steel microstructure might have multiple pearlite colonies interspersed with primary cementite particles, with potentially differing morphology depending on processing conditions.
Principal Component Analysis
Published in N.C. Basantia, Leo M.L. Nollet, Mohammed Kamruzzaman, Hyperspectral Imaging Analysis and Applications for Food Quality, 2018
Cristina Malegori, Paolo Oliveri
Image texture algorithms are traditionally conceived for gray-scale images and their basic steps include the definition of a neighborhood around the pixel of interest and the calculation of statistics for that neighborhood. The most famous algorithms applied for image texture purposes are: Gray Level Co-occurrence Matrix (GLCM) (Haralick et al., 1973; Malegori et al., 2016) and Angle Measure Technique (AMT) (Andrle, 1994; Fongaro & Kvaal, 2013). Such methods could also be applied on hypercubes, either on a derived image at a single channel or on the total intensity image; in this way, a huge amount of information would be lost.
An Optimal Multi-Level Backward Feature Subset Selection for Object Recognition
Published in IETE Journal of Research, 2019
Image texture features describe the visual patterns of the image. The texture features are extracted from the regions using grey-level co-occurrence matrix. The second-order statistics of an image can be obtained from gray level co-occurrence matrix (GLCM) based on the spatial inter-dependency or co-occurrence of two pixels at specific relative positions. Co-occurrence matrices are calculated for the directions of 0, 45, 90, and 135 degree. The Haralick statistics are calculated from co-occurrence matrices generated and features can be extracted from each of the grey-tone spatial-dependence matrices.
Classification of Deep-SAT Images under Label Noise
Published in Applied Artificial Intelligence, 2021
Mohammad Minhazul Alam, Md Gazuruddin, Nahian Ahmed, Abdul Motaleb, Masud Rana, Romman Riyadh Shishir, Sabrina Yeasmin, Rashedur M. Rahman
The suitable texture features to be used for an image dataset may depend on the image type and application domain. Usually image texture means some visual randomness, repeated patterns, and some statistical characteristics. Extracting texture information from an image is important because it gives us an insight of the image (or certain part of an image) as a quantifiable number. As such, the spatial information of the pixel values are preserved here.
Cognitive framework and learning paradigms of plant leaf classification using artificial neural network and support vector machine
Published in Journal of Experimental & Theoretical Artificial Intelligence, 2022
Gajanand Sharma, Ashutosh Kumar, Nidhi Gour, Ashok Kumar Saini, Aditya Upadhyay, Ankit Kumar
An image texture is a group of image processing metrics designed to quantify an image’s perceived texture. Image texture provides information on colour or intensities of the spatial arrangement in an image or the selected image region (Wang & Wang, 2019). Following are the methods used for feature extractions: