In this paper we present a non-causal, non-parametric, multiscale, Markov random field (MRF) texture model. The model is capable of capturing the characteristics of and synthesising a wide variety of textures, varying from the highly structured to the stochastic. We introduce a novel multiscale texture synthesis algorithm that allows us to use large neighbourhood systems to model some complex n...

A novel statistical textural distinctiveness approach for robustly detecting salient regions in natural images is proposed. Rotational-invariant neighborhood-based textural representations are extracted and used to learn a set of representative texture atoms for defining a sparse texture model for the image. Based on the learnt sparse texture model, a weighted graphical model is constructed to ...

Texture representation of ultrasound (US) images is currently considered a major issue in medical image analysis. This paper investigates the texture representation of thyroid tissue via features based on the Contourlet Transform (CT) using different types of filter banks. A variety of statistical texture features based on CT coefficients, have been considered through a selection schema. The Se...

This work presents an approach for color-texture classification of industrial products. An extension of Gray Level Co-occurrence Matrix (GLCM) to color images is proposed. Statistical features are computed from an isotropic Color Co-occurrence Matrix for classification. The following color spaces are used: RGB, HSL and La*b*. New combination schemes for texture analysis are introduced. A compar...

In this paper, we propose a novel active texture synthesis algorithm based on multi-agent, aiming at overcoming some drawbacks of existing popular patch-based methods. By defining agents’ attributes and behaviors, we dexterously convert the texture synthesis issue to an optimization problem. It can quickly achieve high-quality results for a wide variety of textures without any extra overhead fo...

This paper is concerned with the digitization and visualization of potted greenhouse tomato plants in indoor environments. For the digitization, an inexpensive and efficient commercial stereo sensor-a Microsoft Kinect-is used to separate visual information about tomato plants from background. Based on the Kinect, a 4-step approach that can automatically detect and segment stems of tomato plants...

This paper empirically compares nine image dissimilarity measures that are based on distributions of color and texture features summarizing over 1,000 CPU hours of computational experiments. Ground truth is collected via a novel random sampling scheme for color, and via an image partitioning method for texture. Quantitative performance evaluations are given for classification, image retrieval, ...

The microbial ecology of the nitrogen cycle in agricultural soils is an issue of major interest. We hypothesized a major effect by farm management systems (mineral versus organic fertilizers) and a minor influence of soil texture and plant variety on the composition and abundance of microbial nitrifiers. We explored changes in composition (16S rRNA gene) of ammonia-oxidizing archaea (AOA), bact...

To solve the issue of segmenting rich texture images, a novel detection methods based on the affine invariable principle is proposed. Considering the similarity between the texture areas, we first take the affine transform to get numerous shapes, and then utilize the KLT algorithm to verify the similarity. The transforms include rotation, proportional transformation and perspective deformation ...

This paper presents a new approach of texture image classification based on nonsubsampled contourlet transform, Local binary patterns and Support vector machines. Nonsubsampled contourlet transform and Local binary patterns are used to extract texture features of images, Support vector machines are used to classify texture images. Nonsubsampled contourlet transform has translation invariability...