Fractal dimension has been found not suitable to be used solely in classifying natural earth terrain. This is due to the fact that surfaces with different texture may portray similar fractal dimensions. Evertsz and Mandelbrot [Evertsz, et. al. 1992] suggested that multifractal dimension may be a more appropriate parameter than fractal dimension in describing geometrical properties of a fractal ...

Road infrastructure developments in rural Papua New Guinea (PNG) have not picked up pace due to mountainous and difficult geographical landscape. Hence road accessibility Salt Nomane Karimui (SNK) District of Simbu province is emerged as a serious concern particularly with regard impact poor mobility on agricultural produce ability access public amenities. Governing agencies plans place for con...

The paper presents a genetic algorithm based methodology for learning a set offeature detectors for texture discrimination. This methodology is implemented inJo a vision system that learns to classify noisy examples of different texture classes by evolving populations of simple and texture-specific local spatial feature detectors.

We propose an algorithm for texture segmentation based on a divide-and-conquer strategy of statistical modeling. Selected sets of Gaussian clusters, estimated via Expectation Maximization on the texture features, are grouped together to form composite texture classes. Our cluster grouping technique exploits the inherent local spatial correlation among posterior distributions of clusters belongi...

This paper conducts an empirical evaluation of the MPEG-7 texture descriptors and the LBP (Local Binary Pattern) operator. The experiment involves 319 textures from the Outex texture database, which makes it one of the largest experiments found in the literature, if not the largest, in terms of the number of texture classes. The descriptors are evaluated with respect to retrieval performance an...

in the present study, five log-normal models, normal model (n), and two four- parameter models namely gompertz (g) and fredlund (fr) were tested on 71 psd data from 10 soil textural classes. the jaky (j) and fr models had the smallest and largest r2 values for all of the soils, respectively. the results of comparing the n and simple log-normal (sl) models showed that the accuracy of the n model...

soil moisture retention curve (smrc) is an important soil property which expresses reaction between matric potential and moisture of soil. direct measurement of soil matric potential and moisture is labour- and time-consuming. in order to prevail this problem, indirect methods are used for smrc prediction. pedotransfer functions (ptfs) are one of these indirect methods. this study was carried o...

The paper reports on experimental analysis of the spatial statistics (texture), as measured by wavelet frames in Lband SAR observations of tropical forest. Signatures are used to characterize the dependences of the texture measures on scale and polarization state. For detected data, experiments performed using a full resolution (12.5 m) JERS-1 image confirm that textural features provide good s...

We combine both amplitude and texture statistics of the Synthetic Aperture Radar (SAR) images for classification purpose. We use Nakagami density to model the class amplitudes and a non-Gaussian Markov Random Field (MRF) texture model with t-distributed regression error to model the textures of the classes. A non-stationary Multinomial Logistic (MnL) latent class label model is used as a mixtur...

Pigeons are known to be able to categorize a wide variety of visual stimulus classes. However, it remains unclear which are the characteristics of the perceptually relevant features employed to reach such good performance. Here, we investigate the relative contributions of texture and shape information to categorization decisions about complex natural classes. We trained three groups of pigeons...