Texture Features

Hypogene hydrothermal alteration and mineralization in porphyry Cu-Mo deposit.  Metasomatic alteration and mineralization in skarns.  Supergene sulfide blanket in PCDs.  Geochemistry of alteration and mineralization in PCDs.  Stable isotopes (O 2 , H 2 , S, and C) studies in PCDs.  Noble gases(esp., He & Ar) isotope studies in PCDs.  Alteration and mineralization in epithermal gold veins.  Alteration and mineralization and genesis of industrial rocks and minerals  Geochemistry and genesis of bauxite-laterite deposits. Finished research works 1-Studies on alteration and mineralization of precious and rare elements in Bozlokh-Gharedash area, kharvana, East-Azarbaidjan. 2-Exploration (for Ni, Co, Cr) and mineralogical, petrological, and geochemical investigations of mafic igneous rocks in Misho mountain range, Marand, East-Azarbaidjan, Iran. 3-Study of lamrophyric dikes in Eslamy island, Urumieh lake, East-Azarbaidjan, Iran. 4-Studis of calcic skarn in relation to sub-volcanic granitoidic body (hosting porphyry copper deposit) at east of Sungun-Chay, NW Ahar, East-Azarbaidjan, Iran. 5-Economic assessment and investigation of mineralogy, geochemistry, and genesis of bauxite-laterite horizons in Kanisheeteh area, east of Bukan, West-Azarbaidjan, Iran. 6-Geochemical investigations on Cambrian sandstones in SW Mashhad.

Pyrochlore-based ceramics are considered as a potential host to immobilize high-level nuclear waste in a geological repository. For this application it is essential to investigate the fundamental mechanism of the equilibration of pyrochlore in aqueous solutions. We treated cuboids of a synthetic crystalline and a natural metamict, i.e., self-irradiation-damaged Ti-based pyrochlore in 1 ml of a 1 M HCl solution containing 43.5% 18 O at 250 °C for 72 h. After the experiments the colours of the samples turned from black to almost white and their surfaces were covered by micron-sized crystallites. Both samples were mainly transformed into rutile with subordinate anatase and the reaction can be traced several tens of micrometers into the cuboids. In the case of the natural pyrochlore an additional phase (aeschynite [(REE)(Ti, Nb) 2 (O, OH) 2 ]) appeared as crystals on the surface and within an up to 100 lm thick layer at the interface between TiO 2 and the unreacted pyrochlore. 18 O is in both cases highly enriched in the reaction products with a sharp gradient (on a micrometer scale) to the unreacted pyrochlore. The replacement reaction retains even fine-scale morphological features typical for pseudomorphs. This observation along with the enrichment of 18 O in the product phases and the textural features clearly show that the dissolution of pyrochlore is spatially coupled with the precipitation of stable (metastable) TiO 2 phases at a moving front. During such a coupled process dissolution at the proceeding front is the rate controlling step. The aeschynite phase at the interface is thought to be either an intermediate alteration product or crystallized from a fluid which is located at the interface between the TiO 2 polymorphs and the unreacted pyrochlore due to changing transport properties between the interface and the fluid with increasing thickness of the TiO 2 rim. We emphasize here that our results produced under relatively extreme batch-experimental conditions show similarities with nature as well as with results derived from experiments conducted under moderate conditions rather expected in a nuclear repository.

Recently, writer identification has been studied and it has a wide variety of applications, more specifically in biometric and forensic science. This paper presents the use of texture features in identifying the writer from the handwritten document image. The texture features are extracted based on the co-occurrence histograms of wavelet decomposed images, which capture the information about relationships between each high frequency subband and that in low frequency subband of the transformed image at the corresponding level. The correlation between the subbands at the same resolution exhibits a strong relationship, indicating that this information is significant for characterizing a texture. This scheme is tested on two scripts namely, Kannada and English. The experiments are performed by considering 5, 10, 15, 20, 25 and 30 writers at a time. The experimental results demonstrate the efficacy of the texture features in identifying the writer.

Texture features extraction algorithms are key functions in various image processing applications such as medical images, remote sensing, and content-based image retrieval. The most common way to extract texture features is the use of Gray Level Co-occurrence Matrices (GLCMs). The GLCM contains the second-order statistical information of spatial relationship of the pixels of an image. Haralick texture features are extracted using these GLCMs. However, the GLCMs and Haralick texture features extraction algorithms are computationally intensive. In this paper, we apply different parallel techniques such as task-and data-level parallelism to exploit available parallelism of those applications on the Cell multi-core processor. Experimental results have shown that our parallel implementations using 16 Synergistic Processor Elements significantly reduce the computational times of the GLCMs and texture features extraction algorithms by a factor of 10× over non-parallel optimized implementations for different image sizes from 128 × 128 to 1024 × 1024.

The large quantity of details observed at high spatial resolution imagery created many possibilities in terms of offering geo-spatial information. However, the separability of urban objects using IKONOS image remains a challenge due to the high diversity of spectral responses in urban areas and related aspects such as local texture, spatial arrangement and geometric properties. Optimizing the extraction of information and improving the processing time of the high resolution imagery imply in imagery processing techniques which need to be refined or discovered. This article uses the principal components analysis to reduce the IKONOS image dimensionality and to reduce the processing time of the image. Next, the first principal component image was submitted to the region segmentation techniques to delineate the main texture features. Bhattacharyya distance was applied as a supervised method of image classification to identify urban targets. Despite the low spectral resolution of the image used it was reasonably successful in terms of distinguishing some urban objects.

Machine vision systems play a vital role in entirely automating the evaluation of surface roughness due to the hitches in the conformist system. Machine vision systems significantly abridged the ideal time and human errors for evaluation of the surface roughness in a nondestructive way. In this work, face milling operations are performed on aluminum and a total of 60 diverse cutting experiments are conducted. Surface images of machined components are captured for the development of machine vision systems. Images captured are processed for texture features namely RGB (Red Green Blue), GLCM (Grey Level Co-occurrence Matrix) and an advanced wavelet known as curvelet transforms. Curvelet transforms are developed to study the curved textured lines present in the captured images and this module is capable to unite the discontinuous curved lines present in images. The CNC machined components consists of visible lay patterns in the curved form, so this novel machine vision technique is developed to identify the texture well over the other two extensively researched methods. Artificial Neural Network-Particle Swarm Optimization (ANN-PSO) intelligent models are developed to evaluate the surface roughness from texture features. The model average error attained using RGB, GLCM, Curvelet transform-based machine vision systems are 12.68, 7.8 and 3.57 respectively. In comparison, the results proved that computer vision system based on curvelet transforms outperformed the other two existing systems. This curvelet based machine vision system can be used for the evaluation of surface roughness. Here, image processing might be crucial in identifying certain information. One crucial issue is that, even as performance improves, cameras continue to get smaller and more affordable. The possibility for new applications in Industry 4.0 is made possible by this technological advancement and the promise of everexpanding networking.

The Julesz’s conjectures were the foundations for the development of many methods for texture discrimination as spatial arrangements of local patterns. These local patterns represent a bridge between a first conjecture that handles a purely statistical approach and the texton theory. Beyond the mathematical construction of the Local Binary Patterns (LBP) proposed by Ojala, the proposed pattern defined by a circular neighbourhood can be considered as texton. Nevertheless, the binarisation step inside the Local Binary Pattern reduced the ability to be sensitive to the details of high spatial frequencies. In addition, the colour extension of Local Binary Pattern is not straightforward. In this article, we introduce the Colour Local Patterns (CLP) as a new vector texture feature able to characterise colour texture. The Colour Local Pattern inherits from the Local Binary Pattern construction and from the psycho-physical results, starting from the third Julesz’s conjecture. By defining th...

In this study the value of magnetic resonance image (MRI) shape and texture analysis was assessed in multiple sclerosis (MS) subjects, both in differentiating between normal and abnormal tissue and in assessing disease progression. Shape and texture analysis was carried out in normal and diseased lesions in transverse sections of T2weighted magnetic resonance (MR) images acquired from 10 symptomatic untreated subjects with clinically isolated syndrome (CIS) scanned twice, with an interval of 6-12 months. All detected brain lesions were manually segmented by an experienced neurologist and confirmed by a neuro-radiologist, whilst different shape and texture features were extracted from the segmented lesions. The results showed that there was no significance difference between shape features of 0 and 6-12 months. For some texture features there was significance difference between normal tissue and MS lesions at 0 and 6-12 months and between MS lesions at 0 and 6-12 months (i.e contrast, difference variance, difference entropy, and other). Further research with more subjects is required for computing shape and texture features that may provide information for differentiating between normal tissue and MS lesions as well as for longitudinal monitoring of these lesions. In addition the proposed methodology can be used for the assessment of subjects at risk of developing future neurological events. The extracted shape and features can also offer additional information of undiagnosed lesions.

Today almost all of the data in the radiology department is already in digital form because it is one of the hospital departments that use many computerized systems. The data contains information that is essential for the development of health care. Data warehouse (DW) development has been widely used in business, but it also can be used in health care. The objective of this study is design a model of data warehouse that can be implemented in radiology department so it can be a source of knowledge of radiology science. The research method used on this study are 1) data collection through literature review, forum group discussion with radiologist, and observations; 2) design method of data warehouse using the fourth stages of data warehouse design methodology Kimball and Ross (2013). Through this research we will design a radiology data warehouse so the radiologist or researcher can analyze report requirement from case study of patient historical record and assess the accuracy of dia...

Abstract. We demonstrate Teardrop–a rapid reef mosaicing tool that can make fast and frequent surveys of shallow reefs at low cost. The hardware component is a hollow, teardrop-shaped wing that holds a waterproof digital camera in video mode while being towed by a boat or a swimmer over reefs. Captured video are parsed into images and stitched using Microsoft Image Composite Editor (ICE), a free panorama stitching software. Using this tool, we have shortened the time to make a composite image of the reef floor from one week to ...

In this study we propose a Computer Aided Detection and Diagnosis System to detect breast cancer based on characteristics of individual microcalcifications (main indicators of an early breast cancer) by scanning breast tissue with micro-CT, a high resolution 3D imaging modality. By integrating supervised machine learning techniques with feature extraction and feature selection methods, we are able to classify MCs as benign or malignant with 75.88% accuracy, 62.13% sensitivity and 86.39% specificity, outperforming the state of the art.

This study introduces a new approach based on Bidimensional Empirical Mode Decomposition (BEMD) to extract texture features at multiple scales or spatial frequencies. Moreover, it can resolve the intrawave frequency modulation provided the frequency modulation. This decomposition, obtained by the bidimensional sifting process, plays an important role in the characterization of regions in textured images. The sifting process is realized using morphological operators to analyze the spatial frequencies and thanks to radial basis functions (RBF) for surface interpolation. We modified the original sifting algorithm to permit a pseudo bandpass decomposition of images by inserting scale criterion. Its effectiveness is demonstrated on synthetic and natural textures. In particular, we show that many different elements in textures can be extracted through the bidimensional empirical mode decomposition, which is fully unsupervised.

In the past, the plants have been studied for various reasons whether it is for medicine or diseases classification. A plant can be classified on the basis of its flowers, size and shape of the leaves including color, barks etc. The role of leaves in taxonomic classification of plants is very essential. This paper studies the effect of leaf image quality improvement by sharpening and enhancing contrast of the image on the classification accuracy of texture based features. For classification purpose, K-Nearest Neighbor (KNN), J48, Classification and Regression Tree (CART), and Random Forest(RF) algorithms have been used. This study has observed pixels from one pixel distance to five pixel distance in the Co-occurrence matrix for finding the improvement in classification accuracy. Keywords— Image quality, texture features, classification accuracy, leaf images, GLCM.

We propose a general image and video editing method based on a Bayesian segmentation framework. In the first stage, classes are established from scribbles made by a user on the image. These scribbles can be considered as a multimap (multilabel map) that defines the boundary conditions of a probability measure field to be computed for each pixel. In the second stage, the global minima of a positive definite quadratic cost function with linear constraints, is calculated to find the probability measure field. The components of such a probability measure field express the degree of each pixel belonging to spatially smooth classes. Finally, the computed probabilities (memberships) are used for defining the weights of a linear combination of user provided colors or effects associated to each class. The proposed method allows the application of different operators, selected interactively by the user, over part or the whole image without needing to recompute the memberships. We present applications to colorization, recolorization, editing and photomontage tasks.

Feature extraction is an important component of a pattern recognition system. A well-defined feature extraction algorithm makes the identification process more effective and efficient. Quality checking is one of the most prominent steps in many applications using Feature extraction. Several techniques exist for the quality checking of wooden materials. However, image based quality checking of wooden materials still remains a challenging task. Although trivial quality checking methods are available, they do not give useful results in most situations. This paper addresses the issue of quality checking of wooden materials using feature extraction techniques with high accuracy and reliability. Experiments conducted under the proposed conditions showing significant results are presented.

Medical information composed of clinical data, images, videos & other physiological signals, has become an essential part of patients care during screening, diagnostic and treatment phases. Today, a wide range of different image modalities can be found in medical imaging like Ultrasound (US), Computed Tomography (CT), Magnetic Resonance (MRI) and Positron Emission Tomography (PET). Amongst all Ultrasound is a widely used technique as it is non-invasive, non-ionizing, portable, free of radiation risk, gives real time acquisition of internal structure such as heart, kidney, liver, uterus and spleen and relatively inexpensive when compared with other imaging modalities such as MRI and CT

Background: Extracting features from the colonoscopic images is essential for getting the features, which characterizes the properties of the colon. The features are employed in the computer-assisted diagnosis of colonoscopic images to assist the physician in detecting the colon status. Methods: Endoscopic images contain rich texture and color information. Novel schemes are developed to extract new texture features from the texture spectra in the chromatic and achromatic domains, and color features for a selected region of interest from each color component histogram of the colonoscopic images. These features are reduced in size using Principal Component Analysis (PCA) and are evaluated using Backpropagation Neural Network (BPNN). Results : Features extracted from endoscopic images were tested to classify the colon status as either normal or abnormal. The classification results obtained show the features' capability for classifying the colon's status. The average classification accuracy, which is using hybrid of the texture and color features with PCA (τ = 1%), is 97.72%. It is higher than the average classification accuracy using only texture (96.96%, τ = 1%) or color (90.52%, τ = 1%) features. Conclusion: In conclusion, novel methods for extracting new texture-and color-based features from the colonoscopic images to classify the colon status have been proposed. A new approach using PCA in conjunction with BPNN for evaluating the features has also been proposed. The preliminary test results support the feasibility of the proposed method.

Stroke is the third leading cause of death in the western world and the major cause of disability in adults. The type and stenosis of extracranial carotid artery disease is often responsible for ischemic strokes, transient ischemic attacks (TIAs) or amaurosis fugax (AF). The identification and grading of stenosis can be done using gray scale ultrasound scans. The appearance of B-scan pictures containing various granular structures makes the use of texture analysis techniques suitable for computer assisted tissue characterization purposes. The objective of this study is to investigate the usefulness of variogram analysis in the assessment of ultrasound plague morphology. The variogram estimates the variance of random fields, from arbitrary samples in space. We explore stationary random field models based on the variogram, which can be applied in ultrasound plaque imaging leading to a Computer Aided Diagnosis (CAD) system for the early detection of symptomatic atherosclerotic plaques. Non-parametric tests on the variogram coefficients show that the coefficients coming from symptomatic versus asymptomatic plaques come from distinct distributions. Furthermore, we show significant improvement in class separation, when a log point-transformation is applied to the images, prior to variogram estimation. Model fitting using least squares is explored for anisotropic variograms along specific directions. Comparative classification results, show that variogram coefficients can be used for the early detection of symptomatic cases, and also exhibit the largest class distances between symptomatic and asymptomatic plaque images, as compared to over 60 other texture features, used in the literature.

We address the problem of developing discriminative, yet invariant, features for texture classification. Texture variations due to changes in scale are amongst the hardest to handle. One of the most successful methods of dealing with such variations is based on choosing interest points and selecting their characteristic scales [Lazebnik et al. PAMI 2005]. However, selecting a characteristic scale can be unstable for many textures. Furthermore, the reliance on an interest point detector and the inability to evaluate features densely can be serious limitations. Fractals present a mathematically well founded alternative to dealing with the problem of scale. However, they have not become popular as texture features due to their lack of discriminative power. This is primarily because: (a) fractal based classification methods have avoided statistical characterisations of textures (which is essential for accurate analysis) by using global features; and (b) fractal dimension features are unable to distinguish between key texture primitives such as edges, corners and uniform regions. In this paper, we overcome these drawbacks and develop local fractal features that are evaluated densely. The features are robust as they do not depend on choosing interest points or characteristic scales. Furthermore, it is shown that the local fractal dimension is invariant to local bi-Lipschitz transformations whereas its extension is able to correctly distinguish between fundamental texture primitives. Textures are characterised statistically by modelling the full joint PDF of these features. This allows us to develop a texture classification framework which is discriminative, robust and achieves state-of-the-art performance as compared to affine invariant and fractal based methods.

With the inter-and multidisciplinary collaboration of the medical community with technologists in conjunction with a disproportionately alarming doctor-patient ratio, it has now become a matter of concern for researchers to enhance patient care with advanced technology along with the reduction of burden on medical professionals. Artificial Intelligence (AI) has now been accepted willingly in the healthcare sector, which has led to a tremendous increase in computational power and large data handling capabilities and is widely used in gastrointestinal endoscopy. The objective of this review is to explore the state of current literature on different AI-based methods applied in intestinal endoscopy for the detection of colonic polyps. A detailed non-systematic literature review was conducted to identify all relevant studies using PubMed/MEDLINE, Scopus, EMBASE, and Google Scholar databases. The technique of AI systems, model building steps, and diagnostic measuring techniques are also discussed. In the automated diagnosis of polyps, AI-based platforms have achieved clinically acceptable diagnostic efficiency. AI-based methods can be of clinical importance in gastroenterology, and as computing strength and algorithms enhance, the application is likely to grow and expand in the field.

This paper proposes two color texture descriptors based on the introduction of a fuzzy color symilarity function: the spatial color similarity pattern and the spatial color symmetry spread index. Both descriptors embed information on the spatial color distribution within a rstorder statistical distribution. Experiments show t h a t the proposed descriptors can be successfully used for color texture recognition and retrieval.

Breast cancer is among the most infectious ailments impacting early part women in countries like India. The severe booster algorithm "Maximize the effectiveness" classifier was used in the proposed solution to automate the medical sector in order to produce an efficient breast cancer detector. Traditional methods for machine learning have all produced models with serious bias or little variance. As a result, the suggested technique used a variety of evaluation markers to evaluate the model. Optimization has a significant impact on machine learning. The devised approach used hierarchical models throughout the svm classifier to address this issue. Then, the suggested framework is contrasted with current models. The early identification of breast cancer is the main goal of the proposed theory.

Objective. This trial examined the use of 4-hydroxyphenyl-retinamide (4-HPR), demonstrated to be a potent inhibitor of carcinogenesis in vitro and in animal models, in patients with cervical intraepithelial neoplasia (CIN) grades 2 to 3. Quantitative pathology and chromosome 9 polysomy were used to understand the biology and quantify the clinical histopathologic changes observed. Methods. Patients were randomized to 4-HPR or placebo for 6 months and followed for six more months. Cervical biopsies were obtained at baseline, 6 months, and 12 months; the biopsies were read blinded three times by the study pathologist. Feulgen-stained sections were also obtained and analyzed using computer-assisted image cytometry. Chromosome 9 polysomy was performed on tissue slices using in situ hybridization and measured quantitatively. Statistical analyses were carried out in S-Plus (Insightful Corporation, Seattle, WA) and R. Results. The interim analysis, planned for 40 patients, was carried out on 39. The 6-and 12-month analyses showed a statistically significant difference between the two study arms. When code was broken, the 4-HPR-treatment arm was found to have fared less well than placebo. Analyses of Feulgen-stained sections provided a quantitative measure of the increase of DNA content and texture features. Chromosome 9 polysomy was also measured using image analysis. The changes observed were consistent with those of cells displaying cancerous changes, indicating a lack of response. Conclusion. 4-HPR is not active at 200 mg/day. The interim analysis was helpful in directing the study; and, in this case, ending it. The intermediate endpoint biomarkers of quantitative histomorphometry and chromosome 9 polysomy yielded quantitative and repeatable results consistent with the findings of the clinical pathologist.

This paper uses theory, simulation and laboratory experiment to investigate the directional filter on Kube and Pentland's linear reflectance model which presents the image directionality as a product of the illuminant direction and surface directionality. As a result, a surface rotation is not equivalent to an image rotation if the illuminant is not rotated. It can be seen that the directional filter characteristics of an image are described by the term of cosine function. The non-linear and shadowing effects neglected by the model are also investigated. Finally surface orientations estimated from this model using photometric stereo are examined, and experimental results verify the theoretical predictions.

A new texture feature extraction method proposed in this paper called Median Gray Level Value method. It is an effective texture classification method due to its high discrimination capability and low computational complexity. The MGLV method divides the image into 3˟3 region and compares the pixel intensity value with median value of region. It extracts various local texture features from image. These are median features (MF), Symmetric Intensity Difference (SID) features, features. All these features are robust to rotation invariant and illumination invariant texture classification. The MGLV method use K-Nearest Neighbors (KNN) and Naïve Bayes (NB) classifier for texture classification. Experiment result show that, the proposed MGLV method outperform for classification of normal texture image. It gives 92.00% result using Kylberg texture database. This indicate that MGLV method extract more detail texture information of image. Experiment result also shows more distinctive performance for rotation invariant and illumination invariant texture classification. It gives 89.74% result for rotation invariant texture classification using Brodatz texture database and 41.25% result for illumination invariant texture classification using Kth-Tips texture database.

A new texture feature extraction method proposed in this paper called Median Gray Level Value method. It is an effective texture classification method due to its high discrimination capability and low computational complexity. The MGLV method divides the image into 3˟3 region and compares the pixel intensity value with median value of region. It extracts various local texture features from image. These are median features (MF), Symmetric Intensity Difference (SID) features, features. All these features are robust to rotation invariant and illumination invariant texture classification. The MGLV method use K-Nearest Neighbors (KNN) and Naïve Bayes (NB) classifier for texture classification. Experiment result show that, the proposed MGLV method outperform for classification of normal texture image. It gives 92.00% result using Kylberg texture database. This indicate that MGLV method extract more detail texture information of image. Experiment result also shows more distinctive performance for rotation invariant and illumination invariant texture classification. It gives 89.74% result for rotation invariant texture classification using Brodatz texture database and 41.25% result for illumination invariant texture classification using Kth-Tips texture database.

Considering the analogy between image segmentation and cluster analysis, the aim of this paper is to adapt statistical texture measures to describe the spatial distribution of multidimensional observations. The main idea is to consider the cluster cores as domains characterized by their specific textures in the data space. The distribution of the data points is first described as a multidimensional histogram defined on a multidimensional regular array of sampling points. In order to evaluate locally a multidimensional texture, a co-occurrence matrix is introduced, which characterizes the local distribution of the data points in the multidimensional data space. Several local texture features can be computed from this co-occurrence matrix, which accumulates spatial and statistical information on the data distribution in the neighborhoods of the sampling points. Texture features are selected according to their ability to discriminate different distributions of data points. The sampling points where the local underlying texture is evaluated are categorized into different texture classes. The points assigned to these classes tend to form connected components in the data space, which are considered as the cores of the clusters.

Image classification plays an important part in the fields of Remote sensing, Image analysis and Pattern recognition. Digital image classification is the process of sorting all the pixels in an image into a finite number of individual classes. The conventional statistical approaches for land cover classification use only the gray values. However, they lead to misclassification due to strictly convex boundaries. Textural features can be included for better classification but are inconvenient for conventional methods. Artificial neural networks can handle non-convex decisions. The uses of textural features help to resolve misclassification. This paper describes the design and development of a hierarchical network by incorporating textural features. The effect of inclusion of textual features on classification is also studied.

Spongillite from João Pinheiro, Minas Gerais, Brazil is mainly known for its use in brick production and in the refractory industry. Very few studies have focused on its geological context. Spongillite-rich deposits occur in shallow ponds on a karstic planation surface developed on rocks of the Neoproterozoic São Francisco Supergroup. Cenozoic siliciclastic sediments are related to this surface. A field study of these deposits and analysis of multispectral images showed a SE-NW preferential drainage system at SE, suggesting that Mesozoic Areado Group sandstones were the source area of the spongillite-hosting sediments. Mineralogical and textural characterization by optical microscopic analysis, X-ray diffraction (XRD), differential and gravimetric thermal analysis (DTA-GTA), infrared spectroscopy (IR) and scanning electron microscopy (SEM) of seven open-pit spongillite-rich deposits (Avião, Carvoeiro, Vânio, Preguiça, Divisa, Severino, Feijão) showed a sedimentological similarity between the deposits. They are lens-shaped and are characterized at the bottom by sand facies, in the middle by spicules-rich muddy-sand facies and at the top by organic matter-rich muddy-sand facies. Petrographically, the spongillite-hosting sediments and the siliclastic sediments of the Areado Group show detrital phases with similar mineralogical and textural features, such as the presence of well-sorted quartz grains and surface features of abrasion typical of aeolian reworking that occurred in the depositional environment in which the sandstones of the Areado Group were formed. Detrital heavy minerals, such as staurolite, zircon, tourmaline, and clay minerals, such as kaolinite, low amounts of illite, scarce chlorite and mixed-layer chlorite/smectite and illite/smectite occur in the spongillite-hosting sediments and in sandstones from the Areado Group. In both formations, staurolite has similar chemical composition. These mineralogical and textural features show that the sediments of the Areado Group constitute the main source of the pond sediments that host spongillite.

In this paper, we will show how non-photorealistic rendering (NPR) can take a new role in content-based image retrieval (CBIR). We propose a content-based image retrieval method. The novelty is that it is based on the painting representation of images, obtained by Stochastic Paintbrush Transformation (SPT), which automatically simulates a painting process. The painting representation is a stroke sequence. Stroke parameters include color and structure (size, orientation, and position) information. We have compared our method with Global Histogram Intersection (GHI) and Oracle's CBIR functions on a database of 1,017 images. The results show that our method has a better performance.

Research studies have shown that advances in computed tomography (CT) technology allow better detection of pulmonary nodules by generating higher-resolution images. However, the new technology also generates many more individual transversal reconstructions, which as a result may affect the efficiency and accuracy of the radiologists interpreting these images. The goal of our research study is to build a content-based image retrieval (CBIR) system for pulmonary CT nodules. Currently, texture is used to quantify the image content, but any other image feature could be incorporated into the proposed system. Unfortunately, there is no texture model or similarity measure known to work best for encoding nodule texture properties or retrieving most similar nodules. Therefore, we investigated and evaluated several texture models and similarity measures with respect to nodule size, number of retrieved nodules, and radiologist agreement on the nodules' texture characteristic. The results were generated on 90 thoracic CT scans collected by the Lung Image Database Consortium (LIDC). Every case was annotated by up to four radiologists marking the contour of nodules and assigning nine characteristics (including texture) to each identified nodule. We found that Gabor texture descriptors produce the best retrieval results regardless of the nodule size, number of retrieved items or similarity metric. Furthermore, when analyzing the radiologists' agreement on the texture characteristic, we found that when just two radiologists agreed, the average precision increased from 88% to 96% for both Gabor and Markov texture features. Moreover, once three or four radiologists agreed the precision increased to nearly 100%.

In this paper we present an efficient computer aided mass classification method in digitized mammograms using Artificial Neural Network (ANN), which performs benign-malignant classification on region of interest (ROI) that contains mass. One of the major mammographic characteristics for mass classification is texture. ANN exploits this important factor to classify the mass into benign or malignant. The statistical textural features used in characterizing the masses are mean, standard deviation, entropy, skewness, kurtosis and uniformity. The main aim of the method is to increase the effectiveness and efficiency of the classification process in an objective manner to reduce the numbers of false-positive of malignancies. Three layers artificial neural network (ANN) with seven features was proposed for classifying the marked regions into benign and malignant and 90.91% sensitivity and 83.87% specificity is achieved that is very much promising compare to the radiologist's sensitivity 75%.

Histopathological assessment is one of the examinations that allows the classification of breast cancer based on its level. Histopathological assessment factors are based on tubule formation, nuclear pleomorphism, and the mitotic count. This study only focused on tubule formation. The tubule formation was represented by a lumen surrounded a  nucleus. The segmentation of tubule histopathology of breast cancer method was using a combination of k-means clustering and graph cut. The image data used in this study were 15 images of breast cancer histopathology preparations using 5 variations in the number of clusters (k) in the k-means clustering method. The best results of tubule formation segmentation using k = 4, with an average value of balanced accuracy was 81.08% and the most optimal balanced accuracy results was 94.34%.

A new, computationally inexpensive, approach to texture recognition and segmentation is proposed based on a discriminating quantity called the texture energy tensor (TET). The TET is defined as the sum over a window of the products of pixel pairs at fixed vector displacement. For mathematical textures the TET gives easy to interpret results. Texture classification and segmentation using Laws masks or "tuned masks" and "texture energy" is shown to be a special case of a TET approach.

This paper describes the parallel extension of the mask tuning scheme for texture feature extraction. Unlike other parallel systems in which specific parallel computer archi- tectures are required, our parallel solution to increase pro- cessing speed is examined by introducing the concept of remote procedure call(RPC) in distributed systems for Io- cal or remote interprocess communication. Based on our previous

This paper presents a novel and non-destructive approach to the appearance characterization and classification of commercial pork, turkey and chicken ham slices. Ham slice images were modelled using directional fractal (DF 0 ;45 ;90 ;135) dimensions and a minimum distance classifier was adopted to perform the classification task. Also, the role of different colour spaces and the resolution level of the images on DF analysis were investigated. This approach was applied to 480 wafer thin ham slices from four types of hams (120 slices per type): i.e., pork (cooked and smoked), turkey (smoked) and chicken (roasted). DF features were extracted from digitalized intensity images in greyscale, and R, G, B, L * , a * , b * , H, S, and V colour components for three image resolution levels (100%, 50%, and 25%). Simulation results show that in spite of the complexity and high variability in colour and texture appearance, the modelling of ham slice images with DF dimensions allows the capture of differentiating textural features between the four commercial ham types. Independent DF features entail better discrimination than that using the average of four directions. However, DF dimensions reveal a high sensitivity to colour channel, orientation and image resolution for the fractal analysis. The classification accuracy using six DF dimension features (a à 90 ; a à 135 ; H 0 ; H 45 ; S 0 ; H 90) was 93.9% for training data and 82.2% for testing data.

Breast density has been shown to be one of the most significant risks for developing breast cancer. The Breast Imaging Reporting and Data System (BI-RADS) has a four category classification scheme that describes the different breast densities. Yet, there is great interand intraobserver variability for density classification. This work presents a novel texture classification method and its application for the development of a completely automated breast density classification system. Textons can be thought of as the building block of texture. A new algorithm is proposed that captures the mammographic appearance of the different density patterns by evaluating the texton spatial dependence matrix (TDSM) for the breast region’s corresponding texton map. The TSDM is a new texture model that captures both statistical and structural/spatial texture characteristics. The TSDMs are evaluated for different density classes and corresponding texture models are established. Classification is achi...

The Bouvet Triple Junction is located where the Antarctic, south American and African plates meet in the south Atlantic. Two oceanographic expeditions were carried out in this region in 1994 and 1996 by the Institute of Marine Geology, CNR (Bologna), and the Geology Institute of the Russian Academy of Science (Moscow) under the sponsorship of the Italian Antarctic Research Program (PNRA). The main objectives of these expeditions were to define the structural, morphological and petrographical differences of the three divergent margins that meet in the Bouvet region, and to clarify the evolution in space and time of the geometry of the Triple Junction. Single and multichannel seismic reflection, gravimetric and magnetometric profiles were obtained during the first cruise, with the R/V Akademik Strakhov, in addition to medium resolution multibeam bathymetry of the Bouvet island area and in the southem portion of the Mid Atlantic Ridge. The second cruise, carried out with the R/V Gelendzhik, completed the bathymetric survey of the entire Triple Junction region using an high resolution multi-beam system. Seafloor sampling was carried out by dredging in both cruises. Some of the data obtained during these two expeditions are reported in this paper.

Identification of writer has great scope in emerging technology due to its usage in various types of applications in biometric and forensic science. Our aim in this work to identify the writer from script which is handwritten and obtained as scanned images. Features of textures will be elicited from wavelet decomposed images based on cooccurrence histograms. These will get the information about the relations among the sub bands of less frequency and that in sub bands of higher frequency at the particular level of the transformed image. If the co-relation between the sub bands has the same resolution then that indicates a stronger resolution. The relationship will indicate as information was essential considered to differentiating the textures. The proposed methodology will be executed with kannada handwritten document images by considering 5,10,15,20,25,30 writers. Ability of features from texture in identifying writers is indicated through outcome achieved in experimentation.

It has been proposed that molecular changes in breast cancer (BC) may be accompanied by corresponding changes in phenotype. One such phenotype is the presence of lymphocytic infiltration (LI), a form of immune response seen often in high grade BC. The presence of LI in BC histology has been shown to correlate with prognosis and course of treatment. The advent of digitized histopathology has made tissue slides amenable to computer aided diagnosis (CAD). While texture-based features have recently been shown to successfully distinguish between tissue classes in histopathology, the similarity in appearance of BC nuclei and LI suggests that texture features alone may be insufficient. In this paper, we present a methodology that integrates manifold learning with graph-based features to distinguish high grade BC histology specimens based on the presence or absence of LI. Lymphocytes are first automatically detected via a segmentation scheme comprising a Bayesian classifier and template matching. For a total of 41 samples, the graphbased features, in conjunction with a Support Vector Machine classifier, achieve a classification accuracy of 89.50%. Our method is also compared against the popular Varma-Zisserman (VZ) texton-based classifier, which achieves a maximum accuracy of 62.50%. Visualization of the low dimensional manifold of the LI complex via Graph Embedding shows the presence of three distinct stages of LI.