Neural coding for texture features of visual objects was investigated in monkey inferior temporal cortex by inactivating intrinsic GABAergic inhibition. The inactivation enabled a substantial number of cells to respond to originally ineffective texture pattern that had a particular feature distinct from the originally effective pattern, or to ineffective texture and non-texture stimuli that pos...

Residential areas show plenty of texture information on high resolution remotely sensed imagery. Appropriate description about this texture information for discriminating residential class and its background is a key problem for improving the classification results. Method for selecting proper texture parameters is presented in this paper. Based on the analysis of residential texture, grey leve...

Projective texture mapping is used to project a texture map onto scene geometry. It has been used in many applications, since it eliminates the assignment of fixed texture coordinates and provides a good method of representing synthetic images or photographs in image-based rendering. But conventional projective texture mapping has limitations in the field of view and the degree of navigation be...

computer graphics, transformations, texture mapping In a 3D graphics application, a common operation is the binding of a 2D texture onto a triangle in a 3D positional space. For light-dependent or view-dependent texture mapping, a need may arise in the graphics pipeline to transform the light or view direction vector into texture space. The affine transformation is unique within the plane of th...

Color texture classification is an important step in image segmentation and recognition. The color information is especially important in textures of natural scenes. In this paper, we propose a novel approach based on the 2D and semi 3D texture feature coding method (TFCM) for color texture classification. While 2D TFCM features are extracted on gray scale converted color texture images, the se...

Most Content-Based Image Retrieval (CBIR) systems employ color as primary feature with texture and shape as secondary features. Very few systems exploit spatial features. None of the available systems combines all three visual features, texture, shape and location, for organization and retrieval. Moreover relatively few systems use Gabor filters in texture extraction, despite the widely acclaim...

Texture segmentation is a process of segmenting an image into differently textured regions. This paper is aimed at the segmentation of multitextured images by using Optimized Local Ternary Patterns (OLTP), a new texture model which is recently proposed for texture analysis. This paper uses unsupervised texture segmentation method with the application of optimized local ternary patterns for find...

A novel method of texture modelling based on discrete distribution mixtures is discussed. The statistical properties of textures are modelled by a discrete distribution mixture of product components. A natural colour texture is spectrally factorized and discrete mixtures models are learned and used to synthesize single orthogonal monospectral components. Texture synthesis is based on easy compu...

As a special class of images, texture can represent the surface characteristics of one object, e.g. terrain, vegetation, mineral and fur, etc. This paper combines perceptual texture features and wavelet features for texture image classification. Three new texture features which are proved to be in accordance with human visual perception are introduced. These features include directionality, con...

In this paper, a novel unsupervised segmentation framework for texture image queries is presented. The proposed framework consists of an unsupervised segmentation method for texture images, and a multi-filter query strategy. By applying the unsupervised segmentation method on each texture image, a set of texture feature parameters for that texture image can be extracted automatically. Based upo...