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  

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... 

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... 

Partial discharge (PD) measurement is one of the best methods for condition monitoring of transformers. In this paper, we use 5 different types of defects as follows: scratch on winding insulation, bubble in oil, moisture in insulation paper, a very small free metal particle in the transformer tank, and a fixed sharp metal point on the transformer tank, for our PD-related studies. Each type of defect is implemented into 1 of the 5 identical transformer models, which had been developed in the authors' recent work. The continuous wavelet transform is applied to each related measured time-domain PD signals. This process results in an image, for each PD pulse in the time-frequency domain. Using... 

This paper presents a two layer texture modeling method to recognize architectural distortion in mammograms. We propose a method that models a Gaussian mixture on the Curvelet coefficients and the outputs of Spiculated Lesion Filters. The Curvelet transform and the Spiculated Lesion Filters have been applied to extract textural features of mammograms in literature. However the key difference between this study and the previous ones is that in our approach, a Gaussian mixture models the textural features extracted by the Curvelet transform and the Spiculated Lesion Filters. The results of the current study are shown in the form of accuracy and the area under the receiver operating... 

Suggestion and application of a set of new features for on-line Partial Discharge (PD) monitoring, where there is no information about the type of PD is a challenging task for condition assessment of power equipments, such as a power transformer. This is looked for in this paper. So far, in past various techniques have been employed to develop a comprehensive PD monitoring system, however limited success has been achieved. One of the challenging issues in this field is the discovering of proper features capable of differentiating the involvement of possible types of PD sources. In order to examine the efficiency of the method established in this paper, which is based on application of a set... 

Fingerprint is widely used in identification and verification systems. In this paper, we present a novel feature extraction method based on Gabor filter and Recursive Fisher Linear Discriminate (RFLD) algorithm, which is used for fingerprint identification. Our proposed method is assessed on images from the biolab database. Experimental results show that applying RFLD to a Gabor filter in four orientations, in comparison with Gabor filter and PCA transform, increases the identification accuracy from 85.2% to 95.2% by nearest cluster center point classifier with Leave-One-Out method. Also, it has shown that applying RFLD to a Gabor filter in four orientations, in comparison with Gabor filter... 

The Local Binary Patterns (LBP) feature extraction method is a theoretically and computationally simple and efficient methodology for texture analysis. The LBP operator is used in many applications such as facial expression recognition and face recognition. The original LBP is based on hard thresholding the neighborhood of each pixel, which makes texture representation sensitive to noise. In addition, LBP cannot distinguish between a strong and a weak pattern. In order to enhance the LBP approach, Fuzzy Local Binary Patterns (FLBP) is proposed. In FLBP, any neighborhood does not represented only by one code, but, it is represented by all existing codes with different degrees. In FLBP, any... 

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... 

Due to significant reduction in fossil fuel sources, several researches have been conducted recently to explore modern sources of renewable energy. One of the major fields in the category of renewable energy harnessing devices is parabolic trough solar collector (PTC). Several parameters have effect on the overall efficiency of the PTCs. As the effect of these parameters is coupled to each other, a comprehensive investigation is necessary. In the present study, a numerical analysis is performed to examine the efficiency of PTCs via variation of several governing parameters (e.g., wind velocity magnitude, nanoparticles volume fraction, inlet temperature, and reflector's orientation). A... 

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... 

In this paper, we propose a novel algorithm that combines color and texture information of skin with cellular learning automata to segment skin-like regions in color images. First, the presence of skin colors in an image is detected, using a committee structure, to make decision from several explicit boundary skin models. Detected skin-color regions are then fed to a color texture extractor that extracts the texture features of skin regions via their color statistical properties and maps them to a skin probability map. Cellular learning automatons use this map to make decision on skin-like regions. The proposed algorithm has demonstrated true positive rate of about 83.4% and false positive... 

Skin detection is a difficult and primary task in many image processing applications. Because of the diversity of various image processing tasks, there exists no optimum method that can perform properly for all applications. In this paper, we have proposed a novel skin detection algorithm that combines color and texture information of skin with cellular learning automata to detect skin-like regions in color images. Skin color regions are first detected, by using a committee structure, from among several explicit boundary skin models. Detected skin-color regions are then fed to a texture analyzer which extracts texture features via their color statistical properties and maps them to a skin... 

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... 

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...