Sharif Digital Repository

Computer Aided Diagnosis (CAD) systems are widely used in different medical tasks. Radiology is a branch of medicine which takes advantage of image processing techniques to help radiologists, analyse complicated radiologic images. Among all kind of medical imagingprocedures, utilization of screening mammographyisgetting very popularin detection of breast abnormalities. A typical CAD system for mammogram analysis uses image enhancement and segmentation as pre-processing phase, and feature extraction and classification for detection phase. In this thesis, we have studied different approaches in each level of image processing required in a mammogram mass classification systems, and introduced a... 

Image registration is defined as matching two or more than two images which are taken from a same scene in different times, from various views and using different sensors. By matching, we mean finding the transformation function between the images. Image registration
has many application in medical domains such as analyzing changes in body limbs, supervision of the tumors growth, and robotic surgery. The challenges of image registration are unavailability of the transformation function, existence of the outliers in the images, changes in the images intensity, changes in the image geometry, noise, etc. Image registration consists of four steps: (i) feature extraction, (ii) choosing a... 

Nowadays, the use of MEMS sensors, due to their small size, lightweight and low cost, has been welcomed in systems such as autonomous vehicles. Although the precision of MEMS gyroscopes has been extremely improved, in some aspects, such as stability of bias, they still suffer from some big error sources, like run-to run bias, which determines the sensor price but is not negligible even inexpensive sensors. In addition to the bias, there are a lot of noises in the gyroscope outputs, where ARW is one of the most important ones, which causes failure in real-signals and produces an error in the position and attitude of mobile systems. Due to the fact that run-to-run bias and ARW are stochastic... 

Image segmentation has a huge amount of applications in machine vision, target detection, medical image processing, etc. In many medical researches such as Organ and Gland Volume Specification, Analysis of Anatomical Structures and Multimodal Image Registration, Organ
Segmentation is the first step of preprocessing.Since detection of diseases out of medical images depends on organ segmentation results,the segmentation process is done by experts which has a lot of disadvantages such as high time computation, high cost, etc. Hence, designing algorithms that can segment images with high accuracy and need minimum user interaction are desirable. So, in this thesis, a new
knowledge based... 

Image registration is one of the fundamental and essential tasks for medical imaging and remote sensing applications. One of the most common challenges in this area is the presence of complex spatially varying intensity distortion in the images. The widely used similarity metrics, such as MI (Mutual Information), CC (Correlation Coefficient), SSD (Sum of Square Difference), SAD (Sum of Absolute Difference) and CR (Correlation Ratio), are not robust against this kind of distortion; because stationarity assumption and the pixel-wise independence cannot be obeyed and captured by these metrics. In this research, we proposed a new intensity-based method for simultaneous image registration and... 

Pose and motion estimation using a set of images is a common application in photogrammetry and one of the most popular methods in doing so is Bundle adjustment. This method later got adapted to the field of computer vision and is mainly used to reconstruct a 3d scene while also estimating pose and motion of the camera. There are a variety of other methods used to estimate pose and motion. Most non-visual methods like using inertial navigation system and GPS suffer from shortcomings like accumulative error, availability problems or low accuracy. While most vision based one are computationally expensive. In this thesis two methods are proposed to increase accuracy and efficiency of one variant... 

Energy constraint is the most critical problem in wireless sensor networks (WSNs). To address this issue, clustering has been introduced as an efficient way for data aggregation and routing. However, there also exist some disadvantages associated with the clustering scheme, such as additional overheads during the cluster-head election and cluster formation process. Most available clustering algorithms do not efficiently take into consideration the geographical information of nodes in the cluster-head election. This leads to uneven distribution of cluster-heads and unbalanced cluster sizes, which brings about uneven energy dissipation in clusters. In this research, an Efficient Distributed... 

Most of current state-of-the-art methods for object tracking use adaptive tracking-by-detection. The performance of state-of-the-art methods is almost real-time with acceptable accuracy. These methods use tracking-by-detection because of its robustness. Tracking-bydetection methods use a detector as a tracker and sweep input for object of interest. They use their predictions to adapt their parameters and therefore be adaptive to appearance change in target. While suitable for cases when the object does not disappear from the scene, these methods tend to fail on occlusions. In this work, we build on a novel approach called Tracking-Learning-Detection (TLD) that overcomes this problem. In... 

In drilling oil well with respect to depth of several thousand meters, knowing the physical conditions of down-hole well such as temperature, pressure and stress have particular importance in prevention of possible injuries such as breaking the drill bit or increasing temperature. If these data can transfer from down-hole to bore-hole of the well, the operators can prevent from critical conditions such as intertangle of the drill-string. Currently, because of this lack of information, there are irreparable damages in oil industry annually. Based on researches, because of down-hole conditions of the well, these data can’t transfer with electromagnetic telemetry. Currently one of the data... 

Drilling in oil industry, is an expensive process in produce and extract oil from well. Any mistake in drilling may cause many drawbacks for industry owners. Phisic’s quantities information at downhole like tempreture, pressure and force on bit synchronously can inform user from torrid conditions and prevent undesired events by actions like evoke bit from downhole or change at rotation velocity in drilling and finally stop operations. With attention to a lot of problems in data transport from long distance more than one kilometer from downhole, scientists believe that one of the methods to do this process is converting data gathered at the bottom hole to acoustic waves and transmit them to... 

In this project, the final goal is to create a team consisting of a UGV and a quadrotor capable of relative tracking and coordinated landing, with focus on quadrotor control. What we mean by cooperative control in this project is control of quadrotor for the purpose of cooperation with a UGV; This should not be mistaken with another sense of cooperative control in which the control algorithms are developed for both of the robots or are based on the interactive dynamics of the robots.In order to accomplish this goal, an experimental testbed consisting of a quadrotor and a UGV capable of communication and data exchange was developed as a first step. The quadrotor was constructed using... 

New development in material fabrication resulted in functionally graded materials (FGM) with properties, can vary continuously based on the desired purpose. Vast applications of these materials attracted scientists to extend the researches in this area. One of the promising applications of these materials is in the optimized spherical and cylindrical pressure vessels. Optimization is usually based on the minimization of heat transfer and maximization of the strength of the vessel under pressure. In the present dissertation, spherical and cylindrical pressure vessels are designed and characteristics of the material distribution for certain pressure and temperature is developed. In this... 

Image classification is one of the most challenging issues in computer vision. One sort of such classifications is Scene Classification. To perform automatic classification reserchers used many aproches.The general approach used features directly extracted from the image, such as color and texture or features extracted by the SIFT algorithmetc. Another method is based on recognizing object of the Scene (espessially indoor scene). This method is based on finding of a limited number of prespecified objects. In the proposed method, first a window surrounding each objects, (regardless of the type of object) founded. Then the SIFT feature is extracted from that window. All features (corresponding... 

Regarding the numerous casualties and financial losses due to intense earthquakes, the ductility is considered of the main importance in addition to stability, stiffness, and strength criteria of the structure’s connections. In order to enhance the seismic behavior of the structures in such severe earthquakes, design codes for steel structures have suggested special types of connections. Among them, bolted end plate connection is considered a conventional type of connection used for creating ductile semi-rigid connection.In this study, in order to simulate the behavior of this joint, a 3-D finite element model is developed in Abaqus software, in which the inelastic behavior of the materials... 

Atomic force microscope (AFM) has a significant capability of imaging surface topography on an atomic scale. It is also widely used for Nanolithography in MEMS/NEMS (micro/nanoelectromechanical systems). Conventional AFMs consist of a cantilever with a sharp conical or pyramidal tip located at the free end of the cantilever that plays an important role in AFM measurements. Scanning across a surface, AFM interacts with the sample surface through its tip. Although the dynamic behavior of the AFM cantilever is complicated, the researchers have been interested in studying AFM dynamic behavior because it has a great influence on the surface imaging process. The imaging rate and contrast of... 

In addition to investigating the overall situation of healthcare information systems (HIS) in Iranian hospitals, in this thesis the goal is to determine the key elements of success and failure in the implementation of HIS. With the advent of the computer systems in Iran and due to the successful and unsuccessful experiences of organizations, the necessity of detecting the influential elements in this field is perceived even more than before. Another importance of this research is because of the essential role of the cultural and social factors in the success of these systems; this claim can be justified by observing different results founded by researchers from different countries. In this... 

Today, with the spread of various videos especially sports video and availability of them, the need for automated methods for search and retrieval of concepts from videos is strongly felt. On the other hand, summarizing video in order to making significant parts of them available is very important. One of the broadest scope that researchers have provided methods for extracting semantic concepts, is soccer videos. Often to extract high-level events, we need a definition and use of intermediate concepts. In this thesis "replay", "audio highlights" and "view type" are used to extract important events in the game. Here, two new methods are introduced for replay detection and view type... 

Gene regulatory network consists of a set of genes; interacting with each other via their protein products. Such interations lead to the regulation of the genes’ production rate. A breakdown in the regulatory process, may lead to some kinds of diseases. Therefore, understanding the gene regulatory process, is beneficial for both diagnosis and treatment. In this thesis, gene regulatory networks are modeled by the means of dynamic Bayesian networks. We have used sampling based methods, in order to learn the network structure. As these methos have a very high computational cost; we have used a correlation test to prune the search space. This way, an undirected network skeleton is obtained; for... 

With respect to the introduction of bio-material into cells (transfection) , microinjection is a highly efficient technique amongst existing methodologies. In cell injection, a manipulator injects the needle into a cellwhich is hold by a pipet mechanism. The moving range for the needle in this operation is of centimeter order and the resolution for the needle tip should be less than the cell’s diameter. In this thesis a Stewart system is used as for the manipulator. Stewart systems are used in flight simulators systems for decades, as mechanisms which are capable of providing multi-axis movements. In high accuracy positioning and multi-axis applications Stewart systems are highly reliable.... 

In accomplishment of knowledge management in real world, organization can be in different processes of awareness about importance of knowledge management and its achievements. Recognition of strength and weakness points of organization helps to logical planning and success in performance of knowledge management. For avoiding from failing in knowledge management projects, it is necessary that before stating for project performance, evaluate development level of organization from viewpoint of knowledge management, and determine some approaches for control of general problems of knowledge management, like abundance of information, work complexities, knowledge Storage.
In literature of...