Browsing by Author "Hassanpour, Reza"

Now showing 1 - 20 of 28

Citation Count: Jafari, Aref...et al. (2014). "A combined spatial and frequency based texture model for organsegmentation in computed tomography examinations" Journal Of Medical Imaging And Health Informatics, Vol.4, No.2, pp.230-236.
A combined spatial and frequency based texture model for organsegmentation in computed tomography examinations
(Amer Scientific Publishers, 2014) Jafari, Aref; Hassanpour, Reza; Shahbahrami, Asadollah; Wong, Stephan
The organ segmentation in computed tomography (CT) examination is a tedious and error prone task. The local similarity of the pixels from different organs, and the differences between the pixels of the same organ observed in different examinations are two most challenging problems affecting the segmentation process. In this study, statistical and spectral texture properties are combined with the a-priori knowledge about the human body to develop a model for reliably segmenting organs in CT examinations. The main goal of the developed model is fusing local and global statistics to support spatial-frequency analysis and to maximize the simultaneous localization of energy in both spatial and frequency domains. The feature space dimension is reduced by means of a wrapper technique applied as a pre-processing filter. The proposed classifier utilizes a linear combination (ensemble) of two support vector machines (SVM) where the first SVM classifies the input samples according to their textural information and the second one correct the results of the first classifier by searching the spatial information of those samples in a statistical atlas.
Citation Count: Yumuşak, Semih;...et.al. (2022). "A Novel Hypercube-based Approach to Overlay Design Algorithms on Topic Distribution Networks", Politeknik Dergisi, Vol.25, No.4, pp.1535-1552.
A Novel Hypercube-based Approach to Overlay Design Algorithms on Topic Distribution Networks
(2022) Yumuşak, Semih; Layazali, Sina; Öztoprak, Kasım; Hassanpour, Reza
Data communication in peer-to-peer (P2P) network requires a fine-grained optimization for memory and processing to lower the total energy consumption. When the concept of Publish/subscribe (Pub/Sub) systems were used as a communication tool in a P2P network, the network required additional optimization algorithms to reduce the complexity. The major difficulty for such networks was creating an overlay design algorithm (ODA) to define the communication patterns. Although some ODAs may perform worse on a high-scale, some may have better average/maximum node degrees. Based on the experimentation and previous works, this study designed an algorithm called the Hypercube-ODA, which reduces the average/maximum node degree for a topic connected Pub/Sub network. The Hypercube-ODA algorithm creates the overlay network by creating random cubes within the network and arranging the nodes with the cubes they belong to. In this paper, the details of the proposed Hypercube algorithm were presented and its performance was compared with the existing ODAs. Results from the experiments indicate that the proposed method outperforms other ODA methods in terms of lower average node degree (lowering the average node degree by up to 60%).
Citation Count: Saadettin, Bolat...et al. "A novel intelligent and fast question answering system for world wide web", IMSCI 2007 - International Multi-Conference on Society, Cybernetics and Informatics, Proceedings, pp. 450-455, 2007.
A novel intelligent and fast question answering system for world wide web
(2007) Saadettin, Bolat; Aşkun, Ali Rıza; Demirbulak, Dilara; Hassanpour, Reza; 56475
The World Wide Web has expanded to include on-line access to an almost unlimited number of documents. However, this enormous source of information brings with it the problem of searching the documents efficiently and easily. We have developed a Web-based Question Answering System, which primarily focuses on open domain fact-based short answer questions and also some definition questions. The most important characteristics of the system are its capability in understanding questions given in a natural language style and the effective search which avoids transferring a large amount of unnecessary data. Experimental results show the superiority of the proposed method to available similar systems in terms of accuracy.
Citation Count: Hassanpour, Reza, "A Two-Stage Matching Method for Multi-Component Shapes", Advances in Electrical and Computer Engineering, 15, No. 1, pp. 143-150, (2013).
A Two-Stage Matching Method for Multi-Component Shapes
(Univ Suceava, 2015) Hassanpour, Reza
In this paper a shape matching algorithm for multiple component objects has been proposed which aims at matching shapes by a two-stage method. The first stage extracts the similarity features of each component using a generic shape representation model. The first stage of our shape matching method normalizes the components for orientation and scaling, and neglects minor deformations. In the second stage, the extracted similarity features of the components are combined with their relative spatial characteristics for shape matching. Some important application areas for the proposed multi-component shape matching are medical image registration, content based medical image retrieval systems, and matching articulated objects which rely on the a-priori information of the model being searched. In these applications, salient features such as vertebrae or rib cage bones can be easily segmented and used. These features however, show differences from person to person on one hand and similarities at different cross-sectional images of the same examination on the other hand. The proposed method has been tested on articulated objects, and reliable registration of 3-dimensional abdominal computed tomography images.
Citation Count: Tasel, Serdar F...et al., "A validated active contour method driven by parabolic arc model for detection and segmentation of mitochondria", Journal of Structural Biology, Vol. 194, No. 3, pp. 253-271, (2016).
A validated active contour method driven by parabolic arc model for detection and segmentation of mitochondria
(Academic Press INC Elsevier Science, 2016) Taşel, Faris Serdar; Mumcuoğlu, Erkan U.; Hassanpour, Reza; Perkins, Guy
Recent studies reveal that mitochondria take substantial responsibility in cellular functions that are closely related to aging diseases caused by degeneration of neurons. These studies emphasize that the membrane and crista morphology of a mitochondrion should receive attention in order to investigate the link between mitochondria] function and its physical structure. Electron microscope tomography (EMT) allows analysis of the inner structures of mitochondria by providing highly detailed visual data from large volumes. Computerized segmentation of mitochondria with minimum manual effort is essential to accelerate the study of mitochondrial structure/function relationships. In this work, we improved and extended our previous attempts to detect and segment mitochondria from transmission electron microcopy (TEM) images. A parabolic arc model was utilized to extract membrane structures. Then, curve energy based active contours were employed to obtain roughly outlined candidate mitochondrial regions. Finally, a validation process was applied to obtain the final segmentation data. 3D extension of the algorithm is also presented in this paper. Our method achieved an average F-score performance of 0.84. Average Dice Similarity Coefficient and boundary error were measured as 0.87 and 14 nm respectively. (C) 2016 Elsevier Inc. All rights reserved.
Citation Count: Özyer, S.T.; Hassanpour, R.,"An Rsvp Model for Opnet Simulator With An Integrated Qos Architecture", International Workshop On Modeling and Applied Simulation, Mas 2009, Held At the International Mediterranean and Latin American Modeling Multiconference, I3M 2009, pp. 67-75, (2019).
An Rsvp Model for Opnet Simulator With An Integrated Qos Architecture
(Caltek S.R.L., 2009) Özyer, Sibel T.; Hassanpour, Reza; 18980
Resource Reservation Protocol (RSVP) allows Internet real-time applications to request a specific end-to-end Quality of service (QoS) for data stream before they start transmitting data. In this paper firstly an overview of RSVP is presented. After that the different quality of services available and the relation between QoS and RSVP have been explained. The fundamentals of RSVP as a protocol is discussed. The performance issues and benchmarking for planned portion architecture at the department of Computer Engineering, Çankaya University has been given next. The experimental results and discussions conclude this paper. In this paper, OPNET network simulation tool has been used. Under given architecture and protocol, performance of quality of service implications has been carried out.
Citation Count: Tasel, Serdar F.; Hassanpour, Reza; Mumcuoglu, EU.;..et.al., "Automatic detection of mitochondria from electron microscope tomography images: a curve fitting approach" Medical Imaging 2014: Image Processing, Vol.9034, (2014).
Automatic detection of mitochondria from electron microscope tomography images: a curve fitting approach
(Spie-Int Soc Optical Engineering, 2014) Taşel, Faris Serdar; Hassanpour, Reza; Mumcuoğlu, E. U.; Perkins, Guy; Martone, Maryann
Mitochondria are sub-cellular components which are mainly responsible for synthesis of adenosine tri-phosphate (ATP) and involved in the regulation of several cellular activities such as apoptosis. The relation between some common diseases of aging and morphological structure of mitochondria is gaining strength by an increasing number of studies. Electron microscope tomography (EMT) provides high-resolution images of the 3D structure and internal arrangement of mitochondria. Studies that aim to reveal the correlation between mitochondrial structure and its function require the aid of special software tools for manual segmentation of mitochondria from EMT images. Automated detection and segmentation of mitochondria is a challenging problem due to the variety of mitochondrial structures, the presence of noise, artifacts and other sub-cellular structures. Segmentation methods reported in the literature require human interaction to initialize the algorithms. In our previous study, we focused on 2D detection and segmentation of mitochondria using an ellipse detection method. In this study, we propose a new approach for automatic detection of mitochondria from EMT images. First, a preprocessing step was applied in order to reduce the effect of non-mitochondrial sub-cellular structures. Then, a curve fitting approach was presented using a Hessian-based ridge detector to extract membrane-like structures and a curve-growing scheme Finally, an automatic algorithm was employed to detect mitochondria which are represented by a subset of the detected curves. The results show that the proposed method is more robust in detection of mitochondria in consecutive EMT slices as compared with our previous automatic method.
Citation Count: Hassanpour, Reza; Atalay, V. (20049. "Camera Auto-calibration Using a Sequence of 2D Images with Small Rotations", Pattern Recognition Letters, Vol. 9, No. 2, pp. 989-997.
Camera Auto-calibration Using a Sequence of 2D Images with Small Rotations
(2004) Hassanpour, Reza; Atalay, V.
In this study, we describe an auto-calibration algorithm with fixed but unknown camera parameters. We have modified Triggs' algorithm to incorporate known aspect ratio and skew values to make it applicable for small rotation around a single axis. The algorithm despite being a quadratic one is easy to solve. We have applied the algorithm to some artificial objects with known size and dimensions for evaluation purposes. In addition, the accuracy of the algorithm has been verified using synthetic data. The described method is particularly suitable for three dimensional human head modeling. © 2004 Elsevier B.V. All rights reserved.
Citation Count: Mumcuoğlu, E.U...et al. (2012). Computerized detection and segmentation of mitochondria on electron microscope images. Journal Of Microscopy, 246(3), 248-265. http://dx.doi.org/10.1111/j.1365-2818.2012.03614.x
Computerized detection and segmentation of mitochondria on electron microscope images
(Wiley-Blackwell, 2012) Mumcuoğlu, E. U.; Hassanpour, Reza; Taşel, Faris Serdar; Perkins, G.; Martone, M. E.; Gürcan, M. N.; 55346
Mitochondrial function plays an important role in the regulation of cellular life and death, including disease states. Disturbance in mitochondrial function and distribution can be accompanied by significant morphological alterations. Electron microscopy tomography (EMT) is a powerful technique to study the 3D structure of mitochondria, but the automatic detection and segmentation of mitochondria in EMT volumes has been challenging due to the presence of subcellular structures and imaging artifacts. Therefore, the interpretation, measurement and analysis of mitochondrial distribution and features have been time consuming, and development of specialized software tools is very important for high-throughput analyses needed to expedite the myriad studies on cellular events. Typically, mitochondrial EMT volumes are segmented manually using special software tools. Automatic contour extraction on large images with multiple mitochondria and many other subcellular structures is still an unaddressed problem. The purpose of this work is to develop computer algorithms to detect and segment both fully and partially seen mitochondria on electron microscopy images. The detection method relies on mitochondria's approximately elliptical shape and double membrane boundary. Initial detection results are first refined using active contours. Then, our seed point selection method automatically selects reliable seed points along the contour, and segmentation is finalized by automatically incorporating a live-wire graph search algorithm between these seed points. In our evaluations on four images containing multiple mitochondria, 52 ellipses are detected among which 42 are true and 10 are false detections. After false ellipses are eliminated manually, 14 out of 15 fully seen mitochondria and 4 out of 7 partially seen mitochondria are successfully detected. When compared with the segmentation of a trained reader, 91% Dice similarity coefficient was achieved with an average 4.9 nm boundary error.
Citation Count: Hassanpour, R.,; Atalay, V., "Delaunay Triangulation Based 3D Human Face Modeling From Uncalibrated İmages", IEEE Computer Society Conference On Computer Vision and Pattern Recognition Workshops, (2004).
Delaunay Triangulation Based 3D Human Face Modeling From Uncalibrated İmages
(IEEE Computer Society, 2004) Hassanpour, Reza; Atalay, Volkan; 48646
In this paper, we describe an algorithm for generating three dimensional models of human faces from uncalibrated images. Input images are taken by a camera generally with a small rotation around a single axis which may cause degenerate solutions during auto-calibration. We describe a solution to this problem by a priori assumptions on the camera. To generate a specific person's head, a generic human head model is deformed according to the 3D coordinates of points obtained by reconstructing the scene using images calibrated with our algorithm. The deformation process is based on a physical based massless spring model and it requires local re-triangulation in the area with high curvatures. This is achieved by locally applying Delaunay traingulation method. However, there may occur degeneracies in Delaunay triangulation such as encroaching of edges. We describe an algorithm for removing the degeneracies during triangulation by modifying the definition of the Delaunay cavity. This algorithm has also the effect of preserving the curavature in the face area. We have compared the models generated with our algorithm with the models obtained using cyberscanners. The RMS geometric error in these comparisons are less than 1.8 x 10-2.
Citation Count: Babagholami-Mohamadabadi, Behnam; Bagheri-Khaligh, Ali; Hassanpour, Reza,"Digital Video Stabilization Using Radon Transform", 2012 International Conference On Digital Image Computing Techniques and Applications (Dicta), (2012)
Digital Video Stabilization Using Radon Transform
(IEEE, 2012) Babagholami-Mohamadabadi, Behnam; Bagheri-Khaligh, Ali; Hassanpour, Reza; 163907
Digital video stabilization is a category of techniques used to reduce the impact of unintentional camera motion such as jitter, jiggle, and other unsteady motions. These unintentional shakings degrade visual quality of videos and reduce the performance of subsequent processes such as video compression. Digital video stabilization which is performed by post processing the acquired frames, suffers from inaccuracy of motion estimation which is mostly due to the local motions of internal moving objects included in videos, and long processing time which prohibits them from being used in real time applications. In this paper we propose a fast and accurate transform based motion estimation method which is robust to internal moving objects. Our experimental results with real and synthesized data indicate efficacy of our proposed method.
Citation Count: Hassanpour, R., Atalay, V., (2006). Experimental study on the sensitivity of autocalibration to projective camera model parameters. Optical Engineering, 45(4). http://dx.doi.org/10.1117/1.2189292
Experimental study on the sensitivity of autocalibration to projective camera model parameters
(Spie-Int Society Optical Engineering, 2006) Hassanpour, Reza; Atalay, Volkan; 48646
Existing methods of 3-D object modeling and recovering 3-D data from uncalibrated 2-D images are subject to errors introduced by assumptions about camera parameters and mismatches in finding point pairs in the images. In this study, we experimentally evaluate the effect of each of these assumptions together with the inaccuracy in the measurements in the images. Sensitivity of reconstruction errors to inaccuracies in the estimation of camera parameters and mismatches due to noise in input data is measured using a linear and two nonlinear autocalibration methods for a projective camera. Our experimental results show that some assumptions such as a vanishing skew can be safely made; however, other parameters such as principal point location are quite sensitive to wrong assumptions. (c) 2006 Society of Photo-Optical Instrumentation Engineers. Keywords
Citation Count: Hassanpour, Reza; Atalay, Volkan. "Head Modeling with Camera Auto-calibration and Deformation", 2002.
Head Modeling with Camera Auto-calibration and Deformation
(2002) Hassanpour, Reza; Atalay, Volkan
A 3D head modeling method from a sequence of 2D images is described. The views from which the input images are acquired are not calibrated. Therefore, an auto-calibration method for a sequence of images with small rotations and translation is developed. For this purpose, we have modified an already existing auto-calibration algorithm to incorporate known aspect ratio and skew values to make it applicable for small rotation around a single axis. We apply this auto-calibration technique to head (face) modeling. Three dimensional positions of known facial features computed from two dimensional images are used to deform a generic head model by using a spring based energy minimization method.
Citation Count: Hassanpour, Reza; Atalay, Mehmet Volkan (2002). "Head Modeling with Camera Autocalibration and Deformation", Proceedings of the Vision, Modeling, and Visualization Conference 2002 (VMV 2002), Erlangen, Germany, November 20-22, 2002.
Head Modeling with Camera Autocalibration and Deformation.
(2002) Hassanpour, Reza; Atalay, Mehmet Volkan
Citation Count: Karaömeroǧlu, Betül; Hassanpour, Reza (2005). "Human face identification using M-PCA augmented with Gabor Wavelet", WSEAS Transactions on Information Science and Applications, Vol. 2, No. 11, pp. 2021-2030.
Human face identification using M-PCA augmented with Gabor Wavelet
(2005) Karaömeroǧlu, Betül; Hassanpour, Reza
In this paper, a specialized version of PCA augmented with Gabor Wavelet Transform is proposed for face identification. Firstly, to cope with the variations due to illumination and facial expression changes 2D Gabor Wavelet Transform is applied; then for reducing a large set of correlated variables to a small number of uncorrelated components the PCA approach is used with some modifications. Based on the effect of the illumination, facial expression and occluding objects such as eye glasses and facial hair, performance of the proposed algorithm is compared with the other algorithms.
Citation Count: Sahin, S.; Tolun, M. R.; Hassanpour, R. "Hybrid expert systems: A survey of current approaches and applications", Expert Systems With Applications, Vol. 39, No. 4, pp. 4609-4617, (2012)
Hybrid Expert Systems: A Survey of Current Approaches and Applications
(Expert Systems With Applications, 2012) Şahin, S.; Tolun, Mehmet R.; Hassanpour, Reza; 1863
This paper is a statistical analysis of hybrid expert system approaches and their applications but more specifically connectionist and neuro-fuzzy system oriented articles are considered. The current survey of hybrid expert systems is based on the classification of articles from 1988 to 2010. Present analysis includes 91 articles from related academic journals, conference proceedings and literature reviews. Our results show an increase in the number of recent publications which is an indication of gaining popularity on the part of hybrid expert systems. This increase in the articles is mainly in neuro-fuzzy and rough neural expert systems' areas. We also observe that many new industrial applications are developed using hybrid expert systems recently. (C) 2011 Elsevier Ltd. All rights reserved.
Citation Count: Hassanpour, Reza, "Illicit Material Detection using Dual-Energy X-Ray Images", International Arab Journal of Information Technology, Vol. 13, No. 4, pp. 409-416, (2016).
Illicit Material Detection using Dual-Energy X-Ray Images
(Zarka Private Univ, 2016) Hassanpour, Reza
Dual energy X-ray inspection systems are widely used in security and controlling systems. The performance of these systems however, degrades with the poor performance of human operators. Computer vision based systems are of vital importance in improving the detection rate of illicit materials, while keeping false alarms at a reasonably low level. In this study, a novel method is proposed for detecting material overlapping and reconstructing multiple images by alleviating these overlaps. Evaluation tests were conducted on images taken from luggage inspection X-ray screening devices used in shopping centres. The experimental results indicate that the reconstructed images are much easier to inspect by human operators than the unprocessed original images.
Citation Count: Yumusak, Semih;...et.al. (2021). "Low-diameter topic-based pub/sub overlay Network Construction with minimum–maximum node Degree", PeerJ Computer Science, Vol.7, pp.1-26.
Low-diameter topic-based pub/sub overlay Network Construction with minimum–maximum node Degree
(2021) Yumusak, Semih; Layazali, Sina; Öztoprak, Kasım; Hassanpour, Reza
In the construction of effective and scalable overlay networks, publish/subscribe (pub/sub) network designers prefer to keep the diameter and maximum node degree of the network low. However, existing algorithms are not capable of simultaneously decreasing the maximum node degree and the network diameter. To address this issue in an overlay network with various topics, we present herein a heuristic algorithm, called the constant-diameter minimum–maximum degree (CD-MAX), which decreases the maximum node degree and maintains the diameter of the overlay network at two as the highest. The proposed algorithm based on the greedy merge algorithm selects the node with the minimum number of neighbors. The output of the CD-MAX algorithm is enhanced by applying a refinement stage through the CD-MAX-Ref algorithm, which further improves the maximum node degrees. The numerical results of the algorithm simulation indicate that the CD-MAX and CD-MAX-Ref algorithms improve the maximum node-degree by up to 64% and run up to four times faster than similar algorithms.
Citation Count: Yildirim, Pinar...et al. "Mining Medline for the Treatment of Osteoporosis", Journal of Medical Systems, Vol. 36, No. 4, pp. 2339-2347, (2012)
Mining Medlıne for the Treatment of Osteoporosis
(Springer, 2012) Yıldırım, Pınar; Çeken, Çınar; Hassanpour, Reza; Esmelioğlu, Sadık; Tolun, Mehmet R.; 101956
In this paper, we consider the importance of osteoporosis disease in terms of medical research and pharmaceutical industry and we introduce a knowledge discovery approach regarding the treatment of osteoporosis from a historical perspective. Osteoporosis is a systemic skeletal disease in which osteoporotic fractures are associated with substantial morbidity and mortality and impaired quality of life. Osteoporosis has also higher costs, for example, longer hospital stays than many other diseases such as diabetes and heart attack and it is an attractive market for pharmaceutical companies. We use a freely available biomedical search engine leveraging text-mining technology to extract the drug names used in the treatment of osteoporosis from MEDLINE articles. We conclude that alendronate (Fosamax) and raloxifene (Evista) have the highest number of articles in MEDLINE and seem the dominating drugs for the treatment of osteoporosis in the last decade.
Phishing e-mail detection by using deep learning algorithms
(2018) Hassanpour, Reza; Doğdu, Erdoğan; Choupani, Roya; Göker, Onur; 21259
Phishing e-mails are considered as spam e-mails, which aim to collect sensitive personal information about the users via network. Since the main purpose of this behavior is mostly to harm users financially, it is vital to detect these phishing or spam e-mails immediately to prevent unauthorized access to users’ vital information. To detect phishing e-mails, using a quicker and robust classification method is important. Considering the billions of e-mails on the Internet, this classification process is supposed to be done in a limited time to analyze the results. In this work, we present some of the early results on the classification of spam email using deep learning and machine methods. We utilize word2vec to represent emails instead of using the popular keyword or other rule-based methods. Vector representations are then fed into a neural network to create a learning model. We have tested our method on an open dataset and found over 96% accuracy levels with the deep learning classification methods in comparison to the standard machine learning algorithms.