Sharif Digital Repository

Segmentation of aerial images has been a challenging task in recent years. This paper introduces a simple and efficient method for segmentation and classification of aerial images based on a pixel-level classification. To this end, we use the Gabor texture features in HSV color space as our best experienced features for aerial images segmentation and classification. We test different classifiers including KNN, SVM and a classifier based on sparse representation. Comparison of our proposed method with a sample of segmentation pre-process based classification methods shows that our pixel-wise approach results in higher accuracy results with lower computation time  

Nematic shells of liquid crystals have been provided in microscales. Defect structures in the shells are very essential in the electro-optical applications of such colloidal objects. We have numerically minimized the free energy of symmetric and asymmetric spherical shells of the nematic liquid crystal. Considering degenerate planar anchoring on the surfaces and isotropic nematic elasticity, a variety of defect structures are observed by controlling or varying the thicknesses of the shell and its degree of asymmetry. In symmetric shells, our calculations show that boojums (bipolar) defects appear in thick shells and tetrahedral (baseball) defects in thin shells. In asymmetric shells, while... 

Retained austenite as a key constituent in final microstructure plays an important role in TRansformation Induced Plasticity (TRIP) steels. The volume fraction, carbon concentration, size, and morphology of this phase are the well-known parameters which effects on the rate of transformation of retained austenite to martensite and the properties of steel, are studied by many researchers. Of the transformation of retained austenite to martensite under strain in a TRIP steel is studied in this paper. The experimental results show that the transformation rate of retained, austenite with similar characteristics, to martensite in differently processed TRIP steel samples, exhibits an anisotropic... 

Breast cancer is considered as the most important cause of death among women. Architectural distortions are very important signs of breast cancer and early detection of them is a rewarding work. In this paper we propose a method to recognize architectural distortion from normal parenchyma. In our proposed method, appropriate features are extracted by the analysis of oriented textures with the application of orientation component of recent the state-of-the-art local texture descriptor called Monogenic Binary Coding (MBC). In addition, we transform Region of Interests (ROIs) to polar coordinates in order to highlight some specific patterns in mammograms. Various classifiers are used over a set... 

This study attempts to find an optimum combination of the welding tool rotation rate (ω) and traveling speed (υ), concerning the corrosion and mechanical properties of Friction Stir Welded (FSWed) AA5052 Aluminum alloy. The effect of the tool speeds on the FSWed AA5052 are investigated via potentiodynamic polarization, open circuit potential (OCP) monitoring, test of the susceptibility to intergranular corrosion, weight loss, tension and micro-hardness tests. Optical microscope and Scanning Electron Microscopy (SEM) were employed for studying the morphology and analyzing the probable intergranular attacks. It was found that by increasing υ up to 200. mm/min at ω=400 rpm, the microstructural... 

Simultaneous effects of thickness and texture on the anisotropy of mechanical properties and fracture behaviors of commercially pure titanium thin sheets were studied. The activation of different deformation systems, due to the split distribution of basal texture, led to mechanical properties anisotropy. The crack initiation and propagation energies, when the loading direction was parallel to the initial rolling direction, decreased with increasing thickness ranges from 0.25 to 1 mm. The changes of size, shape and distribution of dimples with increasing thickness confirmed the restriction of deformation systems and the development of triaxial stress state and plane-strain condition at the... 

Content-based image retrieval (CBIR) has been one of the most active areas of research. The retrieval principle of CBIR systems is based on visual features such as colour, texture and shape or the semantic meaning of the images. A CBIR system can be used to locate medical images in large databases. This paper presents a CBIR system for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the support vector machine (SVM) learning method. This system can retrieve similar images from the database in two groups: normal and tumoural. This research uses the knowledge of the CBIR approach to the application of medical decision support and discrimination... 

We present a modified examplar-based inpainting method in the framework of patch sparsity. In the examplar-based algorithms, the unknown blocks of target region are inpainted by the most similar blocks extracted from the source region, with the available information. Defining a priority term to decide the filling order of missing pixels ensures the connectivity of object boundaries. In the exemplar-based patch sparsity approaches, a sparse representation of missing pixels was considered to define a new priority term. Here, we modify this representation of the priority term and take measures to compute the similarities between fill-front and candidate patches. Comparative reconstructed test... 

Processing time and segmentation quality are two main factors in evaluation of image segmentation methods. Oversegmentation is one of the most challenging problems that significantly degrade the segmentation quality. This paper presents a framework for decreasing the oversegmentation rate and improving the processing time. Significant variations in both color and texture spaces are the main reasons that lead to oversegmentation. We exploit Affine Invariant Region Detectors to mark regions with high variations in both color and texture spaces. The results are then utilized to reduce the oversegmentation rate of image segmentation algorithms. The performance of the proposed framework is... 

Identification of different flow regimes in industrial systems operating under two-phase flow conditions is necessary in order to safely design and optimize their performance. In the present work, experiments on two-phase flow have been performed in a large scale test facility with the length of 6 m and diameter of 5 cm. Four main flow regimes have been observed in vertical air-water two-phase flow at moderate superficial velocities of gas and water namely: Bubbly, Slug, Churn, and Annular. An image processing technique was used to extract information from each picture. This information includes the number of bubbles or objects, area, perimeter, as well as the height and width of objects... 

The effect of high-energy ball milling on the textural evolution of alumina nanopowders (compaction response, sinter-ability, grain growth and the degree of agglomeration) during post sintering process is studied. The applied pressure required for the breakage of the agglomerates (P y) during milling was estimated and the key elements of compressibility (i.e. critical pressure (P cr) and compressibility (b)) were calculated. Based on the results, the fracture point of the agglomerates decreased from 150 to 75 MPa with prolonged milling time from 3 to 60 min. Furthermore, the powders were formed by different shaping methods such as cold isostatic press (CIP) and uniaxial press (UP) to better... 

In this study Al2O3-SiC micro/nanocomposites have been fabricated by mixing alumina nanopowders and silicon carbide micro/nanopowders, followed by hot pressing at 1550, 1600, 1650 and 1700°C. The density, mechanical properties and fracture mode of Al2O3-SiC composites containing different volume fractions (2.5%, 5%, 7.5%, 10% and 15%) of micro/nanoscale SiC particles were investigated and compared with those of alumina. The relative density of composites could reach values very close to theoretical density, especially after sintering at 1700°C. However, relative density declined by increasing the SiC fraction at the same sintering temperature. The flexural strength of composites was best for... 

Crystallographic texture is one of the most sensitive parameters for controlling the microstructure of electrodeposited layers. In this work, we study the crystallographic texture of electrodeposited nickel-silicon carbide coatings. The nickel coatings containing SiC nanoparticles and microparticles were electrodeposited from an additive-free sulfate bath containing nickel ions and SiC particles. The effect of current density on the codeposited Ni/SiC was studied. The coatings were analyzed with scanning electron microscopy and X-ray diffraction. Pole figure studies were done to characterize the evolved crystallographic texture. The X-ray scans followed by Rietveld analysis using the... 

Content-based image retrieval (CBIR) has turned into an important and active potential research field with the advance of multimedia and imaging technology. It makes use of image features, such as color, texture and shape, to index images with minimal human intervention. A CBIR system can be used to locate medical images in large databases. In this paper we propose a CBIR system which describes the methodology for retrieving digital human brain magnetic resonance images (MRI) based on textural features and the Adaptive neuro-fuzzy inference system (ANFIS) learning to retrieve similar images from database in two categories: normal and tumoral. A fuzzy classifier has been used, because of the... 

In this paper, Ti-6Al-4V/TiC composite was fabricated by VIM furnace and graphite crucible. X-ray diffraction analysis and EDS techniques were used to identify the phases in the material. Microstructure characteristics of the Ti-6Al-4V/TiC composite were evaluated by means of optical microscopy. The tensile test was performed at room temperature after hot-rolling of the samples in the beta phase field. The results revealed that at different melting times, three kinds of precipitates are formed in the microstructure including grain boundary, eutectic and transgranular precipitates. The size of transgranular precipitates was significantly larger than that of the other two types of carbides and... 

The newly developed multiphase transformation-induced plasticity (TRIP) steels are of interest for industrial applications because of their excellent combination of high strength and ductility. Their performance can be successfully controlled by designing an optimum balance in the volume fractions of ferrite, bainite and retained austenite. The characteristics of the retained austenite are considered to be the main key to achieving the desired final properties. Against this background, the effects of retained austenite characteristics, such as volume fraction, carbon concentration, size and shape, on the behaviour of TRIP steels have been studied. The crystallographic orientation of the... 

A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as the group of database images labeled with a common semantic label. It is shown that, by establishing this one-to-one correspondence between semantic labels and semantic classes, a minimum probability of error annotation and retrieval are feasible with algorithms that are 1) conceptually simple and 2) computationally efficient. In this article, a content-based image retrieval and annotation architecture is proposed. Its attitude is decreasing the semantic gap by partitioning the image to its semantic regions and using... 

ZnO tetrapods and rods were grown on silicon and thermally oxidized porous silicon substrates with and without Au catalyst layer by carbothermal reduction of ZnO powder through chemical vapor transport and condensation method (CVTC). Porous silicon was fabricated by electrochemical etching of silicon in HF solution. The effect of substrates on morphology, structure and photoluminescence spectra of ZnO nanostructures has been studied. The texture coefficient (TC) of each sample was calculated from XRD data that demonstrated random orientation of ZnO nanostructures on the oxidized porous silicon substrate. Moreover, TC indicates the effect of Au catalyst layer on formation of more highly... 

In order to safe design and optimize performance of industrial systems which work under two phase flow conditions, it's often needed to categorize flow into different regimes. In present work the experiments of two phase flow were done in a large scale test facility with length of 6m and 5cm diameter. Four main flow regimes were observed in vertical air-water two phase flows at moderate superficial velocities of gas and water: Bubbly, Slug, Churn and Annular. Some image processing techniques were used to extract information from each picture. This information include number of bubbles or objects, area, perimeter, height and width of objects (second phase).Also a texture feature extraction... 

Detection of skin pixels in arbitrary images is addressed in this paper. We have combined texture and color information to segment skin regions. First, a pixel-based boosted skin detection method is used to locate skin pixels. To further improve the detect performance, skin region texture features are employed using the nonsubsampled contourlet coefficients. For the candidate skin pixels, the set of 8×8 patches around that pixel in all subimages are selected and the feature vector of each patch is extracted. Multilayer perceptron is then utilized to learn features and classify any given input sample. The proposed algorithm has achieved true positive rate of about 82.8% and false positive...