Browsing by Author "Hassanpour, Reza"

Now showing 1 - 20 of 27

Human Face Identification Using M-Pca Augmented With Gabor Wavelet
(2005) Karaömeroǧlu, B.; Hassanpour, Reza; Hassanpour, R.; Yazılım Mühendisliği
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 - WoS: 6
Citation - Scopus: 7
Illicit Material Detection Using Dual-Energy X-Ray Images
(Zarka Private Univ, 2016) Hassanpour, Reza; Hassanpour, Reza; Yazılım Mühendisliği
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 - WoS: 2
Citation - Scopus: 6
Region Based Hand Gesture Recognition
(Union Agency Science Press, 2008) Birdal, Ahmet; Hassanpour, Reza; Hassanpour, Reza; Yazılım Mühendisliği
Evolution of user interfaces shapes the change in the human-computer interaction. With rapid emerge of three-dimensional (3-D) applications, the need for a new type of interaction device arises since traditional devices such as mouse, keyboard, and joystick become inefficient for interaction within these virtual environments. A better interaction in virtual environments requires a natural and suitable device. "Hand Gesture" concept in human computer interaction which has become popular in recent years can be used to develop such an interaction device. This study reports the development of a real-time, low cost, vision based hand gesture recognition system that works precisely on a relatively small restricted gesture space for single user robot control and human-computer interaction in such an environment that the lighting is relatively stable and the background is not complex.
Citation - WoS: 7
Citation - Scopus: 10
Prediction of Similarities Among Rheumatic Diseases
(Springer, 2012) Ceken, Cinar; Hassanpour, Reza; Tolun, Mehmet Resit; Yildirim, Pinar
We introduce a method for extracting hidden patterns seen in rheumatic diseases by using articles from the widely used biomedical database MEDLINE. Rheumatic diseases affect hundreds of millions of people worldwide and lead to substantial loss of functioning and mobility. Diagnosing rheumatic diseases can be difficult because some symptoms are common to many of them. We use Facta system as a biomedical text mining tool for finding symptoms and then create a dataset with the frequencies of symptoms for each disease and apply hierarchical clustering analysis to find similarities between diseases. Clustering analysis yields four distinct types or groups of rheumatic diseases. Although our results cannot remove all the uncertainty for the diagnosis of rheumatic diseases, we believe they can contribute to the diagnosis of rheumatic diseases to a certain extent. We hope that some similarities exposed can provide additional information at the stage of decision-making.
Citation - WoS: 7
Phishing E-Mail Detection by Using Deep Learning Algorithms
(Assoc Computing Machinery, 2018) Hassanpour, Reza; Dogdu, Erdogan; Choupani, Roya; Goker, Onur; Nazli, Nazli
Spam Mail Filtering Using Bayesian Classifier and Heuristics
(2006) Eş, Sinan; Eş, S.; Aşkun, A.R.; Hassanpour, Reza; Hassanpour, R.; Bilgisayar Mühendisliği; Yazılım Mühendisliği
Commercials and virus infected files transferred by electronic mails (e-mail) have been a main source of time and resource loss during the past decade and email filtering as a binary text classification problem has attracted the attention of many researchers recently. In this study, we have tried to find a filtering solution which is able to automatically classify emails into spam and legitimate categories. In order to automatically and efficiently classify emails as spam or legitimate we took advantage of some Bayesian stochastic algorithms and machine learning based heuristic methods. Our approach includes some novel ideas from Information Retrieval.
A Two-Stage Matching Method for Multi-Component Shapes
(Univ Suceava, Fac Electrical Eng, 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.
A Novel Intelligent and Fast Question Answering System for World Wide Web
(int inst informatics & Systemics, 2007) Aşkun, Ali Rıza; Bolat, Saadettin; Demirbulak, Dilara; Askun, Ali Riza; Dernirbulak, Dilara; Hassanpour, Reza; Bolat, Saadettin; Hassanpour, Reza; Ortak Dersler Bölümü; İngiliz Dili ve Edebiyatı; Yazılım Mühendisliği; Bilgisayar Mühendisliği
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.
An Rsvp Model for Opnet Simulator With an Integrated Qos Architecture
(Caltek s.r.l., 2009) Özyer, S.T.; Hassanpour, Reza; Hassanpour, R.; Özyer, Sibel; Yazılım Mühendisliği; Bilgisayar Mühendisliği
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 - WoS: 8
Citation - Scopus: 9
Power Aware Routing Protocols in Wireless Sensor Network
(Ieice-inst Electronics information Communications Eng, 2016) Oztoprak, Kasim; Hassanpour, Reza; Alsultan, Mohammed
Wireless Sensor Networks (WSNs) have gained importance with a rapid growth in their applications during the past decades. There has also been a rise in the need for energy-efficient and scalable routing along with the data aggregation protocols for the large scale deployments of sensor networks. The traditional routing algorithms suffer from drawbacks such as the presence of one hop long distance data transmissions, very large or very small clusters within a network at the same moment, over-accumulated energy consumption within the cluster-heads (CHs) etc. The lifetime of WSNs is also decreased due to these drawbacks. To overcome them, we have proposed a new method for the Multi Hop, Far-Zone and Load-Balancing Hierarchical-Based Routing Algorithm for Wireless Sensor Network (MFLHA). Various improvements have been brought forward by MFLHA. The first contribution of the proposed method is the existence of a large probability for the nodes with higher energy to become the CH through the introduction of the energy decision condition and energy-weighted factor within the electing threshold of the CH. Secondly, MFLHA forms a Far-Zone, which is defined as a locus where the sensors can reach the CH with an energy less than a threshold. Finally, the energy consumption by CHs is reduced by the introduction of a minimum energy cost method called the Multi-Hop Inter-Cluster routing algorithm. Our experimental results indicate that MFLHA has the ability to balance the network energy consumption effectively as well as extend the lifetime of the networks. The proposed method outperforms the competitors especially in the middle range distances.
Camera Auto-Calibration Using a Sequence of 2d Images With Small Rotations and Translations
(Crc Press-taylor & Francis Group, 2003) Hassanpour, Reza; Hassanpour, R; Atalay, V; Yazılım Mühendisliği
3D model generation needs depth information of the object in the input images. This information can be found using stereo imaging but it needs camera parameters. Camera calibration is not possible without some knowledge about the objects in the scene or assuming fixed or known values for the camera parameters. When using fixed camera parameters, however, small rotation angles or small translation in camera position can degenerate the results. The degeneracy can be omitted by adding new restrictions to the a-priori knowledge about the camera parameters. The calibrated data may be used to reconstruct 3D model of the scene.
Citation - Scopus: 18
Vision-Based Hand Gesture Recognition for Human Computer Interaction: a Review
(2008) Hassanpour, R.; Hassanpour, Reza; Wong, S.; Shahbahrami, A.; Yazılım Mühendisliği
Evolution of user interfaces shapes the change in the human-computer interaction. With the rapid emergence of threedimensional (3-D) applications; the need for a new type of interaction device arises as traditional devices such as mouse, keyboard, and joystick become inefficient and cumbersome within these virtual environments. Intuitive and naturalness characteristics of "Hand Gestures" in human computer interaction have been the driving force and motivation to develop an interaction device which can replace current unwieldy tools. This study is a survey on the methods of analyzing, modeling and recognizing hand gestures in the context of human-computer interaction. Taxonomy of the methods based on the applications that they have been developed for and the approaches that they have used to represent gestures is presented. Direction of future developments is also discussed. © 2008 IADIS.
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.
Real Time Hand-Face Tracking Using Skin Color and Motion
(int inst informatics & Systemics, 2005) Hassanpour, Reza; Hassanpour, Reza; Birdal, Ahmet; Yazılım Mühendisliği
Human hand gestures and face expressions are a major tool for communicating ideas between people. Hand gestures may also account for the main part of the communication when other tools are not preferred or simply not available. First step for an automatic interpretation of these gestures and expressions is their segmentation and tracking. We have developed an algorithm to track hand motions in real time. Our algorithm is based on the motion and color features of the interested areas. A modified form of Adaptive Mean Shift method is used for tracking hands and face. A rule based system monitors the correctness of the segmentation and tracking.
A Combined Spatial and Frequency Based Texture Model for Organ Segmentation in Computed Tomography Examinations
(Amer Scientific Publishers, 2014) Hassanpour, Reza; Shahbahrami, Asadollah; Wong, Stephan; Jafari, Aref
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.
Head Modeling With Camera Auto-Calibration and Deformation
(Akademische verlagsgesellsch Aka Gmbh, 2002) Hassanpour, R; Hassanpour, Reza; Atalay, V; Yazılım Mühendisliği
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 - WoS: 10
Citation - Scopus: 11
Low-Diameter Topic-Based Pub/Sub Overlay Network Construction With Minimum Maximum Node Degree
(Peerj inc, 2021) Yumusak, Semih; Layazali, Sina; Oztoprak, Kasim; 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 - WoS: 1
Citation - Scopus: 4
Automatic Detection of Mitochondria From Electron Microscope Tomography Images: a Curve Fitting Approach
(Spie-int Soc Optical Engineering, 2014) Mumcuoglu, Erkan U.; Perkins, Guy; Martone, Maryann; Tasel, Serdar F.; Hassanpour, Reza
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.
Real-Time 3d Hand Posture Reconstruction Using Stereo Vision
(Ieee, 2016) Hassanpour, Reza; Oztoprak, Kasim; Mogol, Ali Can
One of the important goals in Human Computer Interaction (HCI) is designing better and more intuitive interfaces for improving the interactions. There are lots of approaches to address this problem. One of these approaches is utilizing human hand gestures. The degree of freedom and complex structure of human hand however, make capturing and modeling of hand gestures a challenging problem. In this paper, an inexpensive, fast, and effective method is proposed to capture 3D hand postures and gestures. An articulated 3D hand model capable of incorporating anatomical restrictions is designed. Five markers with different colors are utilized to indicate the location of finger tips in the images. The proposed method, starting with the stereo calibration of the cameras, performs capturing and tracking the color markers attached to the finger tips, reconstructing the 3D coordinates of these points, and calculating the finger articulations by applying inverse kinematics to the developed 3D hand model. The hand posture reconstruction is performed in real-time.
Digital Video Stabilization Using Radon Transform
(IEEE, 2012) Babagholami-Mohamadabadi, Behnam; Bagheri-Khaligh, Ali; Hassanpour, Reza
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.