Loading...
Search for:
segmentation
0.008 seconds
Total 331 records
Weak visibility queries of line segments in simple polygons and polygonal domains
, Article International Journal of Computer Mathematics ; Volume 95, Issue 4 , 2018 , Pages 721-738 ; 00207160 (ISSN) ; Ghodsi, M ; Sharif University of Technology
Taylor and Francis Ltd
2018
Abstract
In this paper we consider the problem of computing the weak visibility polygon of a query line segment pq (or WVP(pq)) inside a given polygon P. Our first algorithm runs in simple polygons and needs O(n3 log n) time and O(n3) space in the preprocessing phase to report WVP(pq) of any query line segment pq in time O(log n + |WVP(pq)|).. We also give an algorithm to compute the weak visibility polygon of a query line segment in a non-simple polygon with h ≥ 1 pairwise-disjoint polygonal obstacles with a total of n vertices. Our algorithm needs O(n2 log n) time and O(n2) space in the preprocessing phase and WVP(pq) in query time of O(nh’ log n + k), in which h’ is an output sensitive parameter...
Persian/arabic text font estimation using dots
, Article 6th IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2006, Vancouver, BC, 27 August 2006 through 30 August 2006 ; 2006 , Pages 420-425 ; 0780397541 (ISBN); 9780780397545 (ISBN) ; Shirali Shahreza, S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2006
Abstract
Nowadays, computer is being used in many aspects of human life. A consequence of computer is electronic documents. Computers can't understand written documents. So, we need to convert written documents to electronic documents in order to be able to process them with computers. One of the common methods for converting written texts to electronic text is Optical Character Recognition (OCR). A lot of work has been done on English OCR, but Persian/Arabic OCR is still under development. A phase which commonly used in recognition part of an OCR system is estimating font size of text. Usually when the font size of text is found, the pen width is calculated. The pen width can be used for character...
Multi-class segmentation of skin lesions via joint dictionary learning
, Article Biomedical Signal Processing and Control ; Volume 68 , 2021 ; 17468094 (ISSN) ; Mahdavi Amiri, N ; Sharif University of Technology
Elsevier Ltd
2021
Abstract
Melanoma is the deadliest type of human skin cancer. However, it is curable if diagnosed in an early stage. Recently, computer aided diagnosis (CAD) systems have drawn much interests. Segmentation is a crucial step of a CAD system. There are different types of skin lesions having high similarities in terms of color, shape, size and appearance. Most available works focus on a binary segmentation. Due to the huge variety of skin lesions and high similarities between different types of lesions, multi-class segmentation is still a challenging task. Here, we propose a method based on joint dictionary learning for multi-class segmentation of dermoscopic images. The key idea is based on combining...
A robust page segmentation method for Persian/Arabic documents
, Article WSEAS Transactions on Computers ; Volume 4, Issue 11 , 2005 , Pages 1692-1698 ; 11092750 (ISSN) ; Shirali Shahreza, S ; Sharif University of Technology
2005
Abstract
Optical Character Recognition (OCR) softwares are widely used in the office automation systems. One of the first steps in the recognition of the documents is to segment the input image. Various methods have been offered for the English language. For the Persian/Arabic Language, however, no complete method has been found yet. In this paper we present a new page segmentation method for Persian/Arabic printed texts. This method has been inspired by the effect of the spreading of ink on paper. One of the most important characteristics of this method is its non-sensitivity to rotation
Evaluation and Diagnosis of Intraosseos Lesions in Panoramic Radiographs
, M.Sc. Thesis Sharif University of Technology ; Kasaie, Shohre (Supervisor)
Abstract
Panoramic radiography is known to be one of the preliminary means in diagnoses of maxillofacial intraosseos lesions, which has a big role in increasing the prognosis of such patients. Considering the fact that nowadays most health-care centers are equipped with digital radiography systems, we can rely on image processing techniques to recognize such lesions automatically.In this study, we try to segment mandible (lower jaw) out of panoramic image by means of some innovative algorithms based on edge detection and edge following, and some atlas-based methods. Then by extracting some features such as intensity, homogeneity, local energy and local gradient and with the help of SVM classifier we...
Synthesis of Dithiocarbamate by Markonikov Addition Reaction
, M.Sc. Thesis Sharif University of Technology ; Mahmoodi Hashemi, Mohammad (Supervisor) ; Ziyaei Halimehjani, Azim (Supervisor)
Abstract
Development of strategically important processes which are environmentally benign with simple methodology and work-up by low toxic material is currently reciving considerable attention.In recent years, dithiocarbamates (DTCs) and their synthesis with a green procedure have received many attention because of their undeniable applications.These synthetic compounds play important roles either in academia and industry. Here a simple, efficient and regiospecific method for synthesis of dithiocarbamates is described by one-pot three-component reaction of an amine, CS2 and alkyl vinyl ether via Markovnikov addition reaction in poly ethylene glycol (PEG) under a mild and green procedure with...
Simulation of Chip Segmentation in Metal Cutting Using ALE Finite Element Method
, M.Sc. Thesis Sharif University of Technology ; Movahhedy, Mohammad Reza (Supervisor)
Abstract
Since it is important to obtain the suitable cutting conditions for machining and investigate the effect of various parameters on this process, the simulation of this process has been developed extensively by using the finite element method in recent years. Due to very large plastic deformation and also continuous chip flow, one of the most appropriate techniques in modeling chip formation is the arbitrary Lagrangian-Eulerian (ALE) finite element method which has been used in several papers using some traditional codes like ABAQUS or personal codes in recent years. However, one of the limitations in this method is the use of a continuous mesh retains with no change in connectivities which is...
A new homologous series of linear aliphatic unsaturated hydroxypolyesters a polyol soft segments for polyurethanes: Synthesis and characterization [electronic resource]
, Article Journal of Applied Polymer Science ; Volume 68, Issue 2, pages 173–183, 11 April 1998 ; Rezai, Nasrin ; Zohurian, M. J ; Sharif University of Technology
Abstract
Synthesis and characterization of a new series of low molecular weight (MW = 500–3000) OH-terminated linear aliphatic unsaturated polyesters based on cis-2-butene-1,4-diol and oxalic to sebacic acid were investigated. Direct polycondensation and transesterification methods were used for the syntheses. The latter was recognized to be the preferable method due to its lower reaction temperature and time, lower diol/diacid ratio, absence of decarboxylation, and formation of a product with low polydispersity (Mw/Mn = 1.3–2.7). Elemental analysis, GPC, FTIR, 1H-NMR, DSC, and WAXD were used for the investigations. A segmented polyurethane based on poly (cis-2-butylene adipate) glycol was also...
Robust zero watermarking for still and similar images using a learning based contour detection
, Article Communications in Computer and Information Science ; Vol. 427, issue , Sep , 2014 , p. 13-22 ; Jamzad, M ; Sharif University of Technology
Abstract
Digital watermarking is an efficacious technique to protect the copyright and ownership of digital information. Traditional image watermarking algorithms embed a logo in the image that reduces its visual quality. A new approach in watermarking called zero watermarking doesn’t need to embed a logo in the image. In this algorithm we find a feature from the main image and combine it with a logo to obtain a key. This key is securely kept by a trusted authority. In this paper we show that we can increase the robustness of digital zero watermarking by a new counter detection method in comparison to Canny Edge detection and morphological dilatation that is mostly used by related works. Experimental...
Progressive sparse image sensing using Iterative Methods
, Article 2012 6th International Symposium on Telecommunications, IST 2012 ; 2012 , Pages 897-901 ; 9781467320733 (ISBN) ; Marvasti, F ; Sharif University of Technology
2012
Abstract
Progressive image transmission enables the receivers to reconstruct a transmitted image at various bit rates. Most of the works in this field are based on the conventional Shannon-Nyquist sampling theory. In the present work, progressive image transmission is investigated using sparse recovery of random samples. The sparse recovery methods such as Iterative Method with Adaptive Thresholding (IMAT) and Iterative IKMAX Thresholding (IKMAX) are exploited in this framework since they have the ability for successive reconstruction. The simulation results indicate that the proposed method performs well in progressive recovery. The IKMAX has better final reconstruction than IMAT at the cost of...
Weak visibility queries in simple polygons
, Article Proceedings of the 23rd Annual Canadian Conference on Computational Geometry, CCCG 2011 ; 2011 ; Ghodsi, M ; Sharif University of Technology
Abstract
In this paper, we consider the problem of computing the weak visibility (WV ) of a query line segment in- side a simple polygon. Our algorithm first preprocesses the polygon and creates data structures from which any WV query is answered efficiently in an output sensitive manner. In our solution, the preprocessing is performed in time O(n3 log n) and the size of the constructed data structure is O(n3). It is then possible to report the WV polygon of any query line segment in time O(log n+k), where k is the size of the output. Our algorithm im- proves the current results for this problem
A new MCMC sampling based segment model for radar target recognition
, Article Radioengineering ; Volume 24, Issue 1 , 2015 , Pages 280-287 ; 12102512 (ISSN) ; Radmard, M ; Nayebi, M ; Sharif University of Technology
Czech Technical University
2015
Abstract
One of the main tools in radar target recognition is high resolution range profile (HRRP). However, it is very sensitive to the aspect angle. One solution to this problem is to assume the consecutive samples of HRRP identically independently distributed (IID) in small frames of aspect angles, an assumption which is not true in reality. However, based on this assumption, some models have been developed to characterize the sequential information contained in the multi-aspect radar echoes. Therefore, they only consider the short dependency between consecutive samples. Here, we propose an alternative model, the segment model, to address the shortcomings of these assumptions. In addition, using a...
Visibility maintenance of a moving segment observer inside polygons with holes
, Article Proceedings of the 22nd Annual Canadian Conference on Computational Geometry, CCCG 2010, 9 August 2010 through 11 August 2010, Winnipeg, MB ; 2010 , Pages 117-120 ; Ghodsi, M ; Sharif University of Technology
2010
Abstract
We analyze how to efficiently maintain and update the visibility polygons for a segment observer moving in a polygonal domain. The space and time requirements for preprocessing are O(n2) and after preprocessing, visibil- ity change events for weak and strong visibility can be handled in O(log VP) and O(log(VP1 + VP2)) re- spectively, or O(log n) in which VP is the size of the line segment's visibility polygon and VP 1 and VP2 represent the number of vertices in the visibility poly- gons of the line segment endpoints
Tourism market segmentation in Iran
, Article International Journal of Tourism Research ; Volume 12, Issue 5 , 2010 , Pages 497-509 ; 10992340 (ISSN) ; Sharbatoghlie, A ; Jafarieh, A ; Sharif University of Technology
Abstract
This study was a prototype segmentation of Iran's inbound tourism market with a concentration on culture. The focus of this paper was to introduce a step by step description of the methodology used to segment Iran's inbound tourism market. In the first phase, cluster analysis was employed to segment the entire market based on two dimensions of tourists' expenditure and cultural traits. In the second phase, the resulting clusters were divided into further subgroups using a common sense approach. Additional variables were utilised to profile the segments, and finally, the segmentation process was verified through outcome analysis
A multispectral image segmentation method using size-weighted fuzzy clustering and membership connectedness
, Article IEEE Geoscience and Remote Sensing Letters ; Volume 7, Issue 3 , March , 2010 , Pages 520-524 ; 1545598X (ISSN) ; Kasaei, S ; Sharif University of Technology
2010
Abstract
Clustering-based image segmentation is a well-known multispectral image segmentation method. However, as it inherently does not account for the spatial relation among image pixels, it often results in inhomogeneous segmented regions. The recently proposed membership-connectedness (MC)-based segmentation method considers the local and global spatial relations besides the fuzzy clustering stage to improve segmentation accuracy. However, the inherent spatial and intraclass redundancies in multispectral images might decrease the accuracy and efficiency of the method. This letter addresses these two problems and proposes a segmentation method that is based on the MC method, watershed transform,...
Visibility of a moving segment
, Article Proceedings of the 2009 International Conference on Computational Science and Its Applications, ICCSA 2009, 29 June 2009 through 2 July 2009, Yongin ; 2009 , Pages 169-176 ; 9780769537016 (ISBN) ; Ghodsi, M ; Sharif University of Technology
2009
Abstract
In this paper we define topological segment visibility, and show how to compute and maintain it as the observer moves in the plane. There are n non-intersecting line segment objects in the plane, and we have a segment observer among them. As the topological visibility of a line segment has not been studied before, we first consider static case of the problem, in which the observer and objects are static, and then we study dynamic case of the problem, in which the observer can move among obstacles
3D numerical investigation of the effects of driving of the new mechanized tunnel on existing segmental linings and ground surface settlements - a case study: Shiraz metro line 2
, Article International Journal of Geotechnical Engineering ; 2020 ; Shivaei, S ; Sadaghiani, M. H ; Nikooee, E ; Sharif University of Technology
Taylor and Francis Ltd
2020
Abstract
Subway metro systems are one of the most efficient modes of mass transportation, especially in heavily populated areas. A series of 3D Finite Element Analysis (FEA) has been carried out to investigate the interaction between mechanized twin tunnels excavated beneath the highly congested streets of Shiraz (Iran). Firstly, the reference numerical model has been verified using the measured data of surface settlement control pins. The effects of driving of the new closed shield tunnel on the evolution of stress fields in the existing segmental lining as well as the ground surface settlements in the reference numerical model have been then quantified. Lastly, the effects of influencing factors...
A new approach for touching cells segmentation
, Article BioMedical Engineering and Informatics: New Development and the Future - 1st International Conference on BioMedical Engineering and Informatics, BMEI 2008, Sanya, Hainan, 27 May 2008 through 30 May 2008 ; Volume 1 , 2008 , Pages 816-820 ; 9780769531182 (ISBN) ; Mirsafian, A ; Masoudi Nejad, A ; Sharif University of Technology
2008
Abstract
Automatic cell segmentation has various applications in different parts of science. The development of automated methods for cell segmentation, remains challenging in situations where there are touching cells. In this paper we propose a new method for separating touching cells. As the first step, we use a combination of graph segmentation algorithm and thresholding for segmenting foreground objects and producing a binary image. Next, boundary points of separation zone are selected by using a corner detection algorithm. Finally, the marker controller watershed transform is applied to separate touching cells at selected points. © 2008 IEEE
WLFS: Weighted label fusion learning framework for glioma tumor segmentation in brain MRI
, Article Biomedical Signal Processing and Control ; Volume 68 , 2021 ; 17468094 (ISSN) ; Jamzad, M ; Sharif University of Technology
Elsevier Ltd
2021
Abstract
Glioma is a common type of tumor that develops in the brain. Due to many differences in the shape and appearance, accurate segmentation of glioma for identifying all parts of the tumor and its surrounding tissues in cancer detection is a challenging task in cancer detection. In recent researches, the combination of atlas-based segmentation and machine learning methods have presented superior performance over other automatic brain MRI segmentation algorithms. To overcome the side effects of limited existing information on atlas-based segmentation, and the long training and the time consuming phase of learning methods, we proposed a semi-supervised learning framework by introducing a...
3D Image Segmentation with Sparse Annotation by Self-Training and Internal Registration
, Article IEEE Journal of Biomedical and Health Informatics ; Volume 25, Issue 7 , 2021 , Pages 2665-2672 ; 21682194 (ISSN) ; Nikdan, M ; Baghshah, M. S ; Sharif University of Technology
Institute of Electrical and Electronics Engineers Inc
2021
Abstract
Anatomical image segmentation is one of the foundations for medical planning. Recently, convolutional neural networks (CNN) have achieved much success in segmenting volumetric (3D) images when a large number of fully annotated 3D samples are available. However, rarely a volumetric medical image dataset containing a sufficient number of segmented 3D images is accessible since providing manual segmentation masks is monotonous and time-consuming. Thus, to alleviate the burden of manual annotation, we attempt to effectively train a 3D CNN using a sparse annotation where ground truth on just one 2D slice of the axial axis of each training 3D image is available. To tackle this problem, we propose...