Sharif Digital Repository

The ultimate goal of this study is to evaluate the condition of concrete structures using computer vision methods and using powerful tools such as machine learning methods based on visual information. This assessment is performed by detecting damage in these structures. With the aging of structures such as dams, bridges and tall buildings, structural health monitoring is an important task in ensuring their safety and stability. Therefore, rapid assessment of the health of structures and diagnosis of damage after destructive events is of great value in terms of providing resilience of structures. Visual inspection of structures by experts is one of the basic methods of evaluating structures.... 

Video segmentation means grouping of pixels of the video sequences into spatio-temporal regions which exhibit coherence in both appearance and motion. Due to complexity and spatio-temporal variations, dynamic texture segmentation is a one of the most challenging task in video processing. The problem of dynamic texture segmentation has received considerable attention due to the explosive growth of its applications in video analysis and surveillance systems. In this thesis, two novel approaches have been proposed. The first proposed method is based on generative Dynamic texture models (DTMs) which represent videos as a linear dynamical system. Since DTMs cannot be used for complex videos which... 

Among businesses operating under the sharing economy model, ride-sharing platforms or Internet taxis have attracted a lot of attention and have been able to encourage millions of people to use them in a few years. Meanwhile, what has been the subject of numerous researches in recent years is the motivation of people to use this type of business. Understanding what motivates users to use these businesses is important to them because it helps them allocate their resources optimally by focusing on the benefits, shortcomings, and potential disadvantages of their product, And then by improving the provided service, have more advantages and attractiveness in the eyes of customers. Accordingly, in... 

The Revenue management concept has been studied and noticed by researchers for more than forty years. Although the applications of revenue management grow in different industries continuously, airline industry which is the origin of this research area is the pioneer of developing and representing new models. In the last few years, there has been a trend to enrich traditional revenue management models. In this thesis we first, reviewed most aspects of revenue management studies especially in airline industry, then choice-based customer behavior concept is introduced. Also a case sample study in customer choice behavior has been developed with time scale considering and remodeled. According to... 

SAR image noise is a significant problem for SAR image analysis.The inherent noise of SAR images, known as speckle, seriously affects the SAR image interpretation. It also has adverse effects on the classification and segmentation of SAR images. Due to its great significance, the SAR image processing has received considerable attention in recent years and many researchers have developed techniques to reduce the inherent noise accompanying the SAR images. A survey of the literature shows that the wavelet analysis is one of the most common methods used for speckle reduction. While the power of the morphological analysis method has mostly not been recognized, we have utilized this efficient... 

Semantic segmentation is the tash of labeling each pixel of an input image. It is one of the main problems in computer vision and plays an important role in scene understanding. State of the art methods of solving it are based on Convolutional Neural Networhs (CNNs). While many real world tasks like autodriving cars and robot navigation require fast and lightweight models, CNNs inherently tend to give beter accuracy when they are deeper and bigger, and this has raised interest in designing compact networks. Knowledge distillation is one of the popular methods of training compact networhs and helps to transfer a big and powerful network’s knowledge to a small and compact one. In this research... 

For radiotherapy and removal of cancerous tissues, it is necessary to determine the location of the tumor and the vulnerable structures around the tumor before treating and irradiating the high-energy beam. To do this, the images received from the patient need to be segmented. This is usually done manually, which is not only time consuming but also very expensive.Various methods for segmenting these images are presented automatically and semi-automatically, among which methods based on machine learning and deep learning have shown much higher accuracy than other methods. Despite this superiority, these methods have problems such as high computational costs, inability to learn the shape and... 

3D face modeling is currently a popular area in Computer Graphics and Computer Vision. Many techniques have been introduced for this purpose, such as using one or more cameras, 3D scanners, and many other systems of sophisticated hardware with related software. But the main goal is to find a good balance between visual reality and the cost of the system. In this thesis, reconstruction of a 3D human face from a pair of orthogonal views, front face and side face is studied. Unlike many other systems, facial feature points are obtained automatically from two photographs with the help of an Active shape model algorithm for the frontal face and an edge detection algorithm for side view of the... 

Mobile and wireless services industry has been among the most attractive businesses recently and is progressing at a fast pace. In this huge industry various organizations and entities cooperate to deliver value to the end user. The mobile operator plays the pivotal role in this chain. Hence mobile operator’s market was chosen in this study as the representative of the industry. Market segmentation and customer satisfaction are the main topics of this study.
Market segmentation for MCI was done using data mining with two-step algorithm. Input data included the consumer behavior extracted from mobile post-paid bills. The results indicated five distinctive clusters. The next part included... 

Today, a lot of efforts have been done in order to commercialize space travels. Spacecrafts have a lot of components and producing each of them spends high costs. Components such as propellant tanks and boosters are multi segment and are released simultaneously and therefore it is economically feasible to recover them. Due to Parafoil ability in low-cost, soft (no damage to the cargo) and accurate landing, it is gradually replacing parachute. Parafoil can fly long distances after being released, so its landing point could be determined. The aim of the study is to evaluate this scenario in which some segments of launch vehicle (e.g. booster) that are equipped with Parafoil expand their... 

Despite recent advancements in deep learning methods, these methods rely on a huge amount of training data to work. Recently the problem of solving classification and recently semantic segmentation problems with a few training data have gained attention to tackle this issue. In this research, we propose a meta-learning method by combining optimization-based and prototypical approaches in which a small portion of parameters are optimized with task-specific initialization. In addition to this and designing other parts of the method, we propose a new approach to use query data as an unlabeled sample to enhance task-specific learning. Alongside the mentioned method, we propose an approach to use... 

Crack detection is a critical task in monitoring and inspection of civil engineering structures. This study proposes a deep-learning-based model for automatic crack detection on the concrete surface. The proposed model is an encoder-decoder model which uses EfficientNetB7, the state-of-the-art convolutional neural network, as encoder and the U Net’s expansion path as decoder. To minimize the training time and maximizing the accuracy, we use transfer learning in our approach. We train our model with a novel training strategy on images from an open-source dataset and achieve 96.44% F1-score for unseen test data. To compare the performance of the proposed method, we evaluate our model on CFD... 

Despite widespread applications and high performance of deep neural networks in the fields of computer vision, they have been shown to be vulnerable to adversarial examples. An adversarial example is a perturbated image that the magnitude of its difference with its corresponding natural image is small and yet given such example, the network produces incorrect output. In recent years, many approaches have been proposed to increase the robustness of DNNs against adversarial examples with adversarial training being proposed as the most effective defense measure. Approaches based on adversarial training try to increase the robustness of the network by training on the adversarial examples. One of... 

Environment Identification and recognizing surrounding objects is an exigent need in future applications. For example one of the emerging technologies in car industry is driverless cars. In driverless cars, navigation system should be able to detect and recognize pedestrians, traffic signs, roads, surrounding cars and so on. Therefore, conventional single-object recognition systems are not capable of handling the needs of advanced machine vision based applications. In recent years, designing and analyzing multi-class object detection and recognition systems have become a big challenge in machine vision. In this thesis our goal is to identify and analyze the existing problems in designing... 

In recent years, the tourism industry has become one of the most influential industries in the income generation of countries and has attracted the attention of researchers. Identifying the important features of the hotel from the users' point of view is one of the areas that have been considered, while the segmentation of hotel customers based on the extracted features has been less in the focus of researchers and the need for more research in this field has been felt by experts.Given that the desire to return to the hotel by travelers has always been one of the factors affecting the financial performance of hotels, the factors affecting it are of great importance. It can be very valuable... 

Skin cancer is a common type of cancer in the world. Melanoma is considered as the deadliest form of human skin cancer that causes approximately 75% of deaths associated with this cancer. However, melanoma is curable if diagnosed in an early stage. Due to high visual similarities and diverse characteristics of lesions, it is a challenging task to differentiate between different types of skin lesions. Therefore, it is worthwhile to develop a reliable automatic system increasing the accuracy and efficiency of pathologists. Here, we propose sparse representation and dictionary learning based methods for skin lesion segmentation and classification. First, we review the steps of a computer aided... 

Employing high-temperature superconducting (HTS) tapes, instead of copper or aluminum wires for winding in a superconducting transformer, results in a series of significant advantages; such as: smaller volume, lighter weight, higher efficieny, greatly extended overload capability, better voltage regulation, lower life cycle cost, fault current limiting capability, lower environmental pollution and lower risk potential against fire hazards.In this thesis, optimal design of flux diverter using genetic algorithm for axial short circuit force reduction in HTS transformers has been performed. Then, multilayered flux diverters have been proposed for reduction of weight and losses. The impact of... 

Due to the overall progress in the processing of imaging tissue cells, the identification and diagnosis of complex diseases using machine learning methods has become very important. Recognizing cell characteristics such as size, shape, and chromatin design is essential in determining cell type, which can be achieved through learning methods such as deep network training. Finding the nucleus or cytoplasm of cells in medical images is a small but significant part of a long process of diagnosing and treating diseases. Today, artificial intelligence has rushed to the aid of experts in this field and has increased the speed and accuracy of experts in finding these cells and their nuclei. This... 

Road transportation has long been an important form of transportation for mankind. Mass production of motorized vehicles and a growing number of people using human and goods transportation have led engineers to monitor road pavement condition and to act on accordingly in the case of degradation. Due to road networks expansion and budget restrictions, road pavement maintenance and rehabilitation projects should be prioritized based on up-to-date data. Automatic collection of data related to the pavement condition such as the number and the length of cracks, could save time and reduce cost and workforce. This research proposes a hybrid method composed of two independent techniques for... 

The goal of a speaker diarization system is to detect the number of speakers of a conversation and also assign each segment of the conversation to one of the speakers. In these types of systems it is assumed that the identity of the speakers is completely unknown. Usually speaker diarization systems operate in an offline mode. The system assumes that it does have the whole conversation at hand and then it starts processing the conversation. This method is effective for applications like spoken document retrieval, but it is not applicable to speech/speaker recognition systems which require online operating. In this dissertation, an online speaker diarization system is implemented. This...