10 results
Search Results
Now showing 1 - 10 of 10
Conference Object Part-Based Object Extraction for Complex Objects(Ieee, 2014) Koyuncu, Murat; Cetinkaya, BasarIndexing requirement for efficient accessing to visual data has been increased with the widespread use of multimedia applications. Satisfaction of this requirement mostly depends on the automatic extraction of objects in the visual data. In this study, component-based object extraction method is compared with object extraction in its entirety. Applied method, implemented system and conducted tests are presented in this paper. Test results show that, even in the case of a good segmentation is achieved for whole object, object components are classified more successfully compared to whole object.Conference Object Slim-Tree and Bitmatrix Index Structures in Image Retrieval System Using Mpeg-7 Descriptors(Ieee, 2008) Acar, Esra; Arslan, Serdar; Yazici, Adnan; Koyuncu, MuratContent-based retrieval of multimedia data has still been an active research area. The efficient retrieval in natural images has been proven a difficult task for content-based image retrieval systems. In this paper, we present a system that adapts two different index structures, namely Slim-Tree and BitMatrix, for efficient retrieval of images based on multidimensional low-level features such as color, texture and shape. These index structures also use metric space. We use MPEG-7 Descriptors extracted from images to represent these features and store them in a native XML database. The low-level features; Color Layout (CL), Dominant Color (DC), Edge Histogram (EH) and Region Shape (RS) are used in Slim-Tree and BitMatrix and aggregated by Ordered Weighted Averaging (OWA) method to find final similarity between any two objects. The experiments included in the paper are in the subject of index construction and update, query response time and retrieval effectiveness using ANMRR performance metric and precision/recall scores. The experimental results strengthen the case that uses BitMatrix along with Ordered Weighted Averaging method in content-based image retrieval systems.Conference Object Comparison of Qos Architectures for Voip Traffics in Ipv4 and Ipv6(Ieee, 2016) AL-Fayyadh, Hayder; Koyuncu, MuratThe Internet has become an integral part of human's life with an ever increasing number of applications and services that it provides to its customers. Both the numbers of Internet users and services provided by the Internet continue to rise tremendously. Quality of Service (QoS) is the ability of a network to provide better services for the users to divide the bandwidth according to the needs of different applications. With an increase in demand for multimedia applications like video streaming, VoIP and video conferencing, larger bandwidth requirement increases drastically since such applications are very sensitive to delay, packet loss, and jitter. IPv6 has new features which are designed to improve QoS supported by IPv4, as well as other improvements. This paper gives a comparative analysis of QoS architectures, namely Integrated Services (IntServ) and Differentiated Services (DiffServ), which are examined to see their effects for Voice over IP (VoIP) in IPv4 and IPv6 environments. For comparisons, OPNET Modeler is used for network modeling and testing. The obtained test results show the importance of IPv6 to support multimedia applications on the Internet.Conference Object Citation - WoS: 2Secure Communication Tests Carried Out With Next Generation Narrow Band Terminal in Satellite and Local Area Networks(Ieee, 2013) Dilli, Orkun; Akcam, Nursel; Koyuncu, Murat; Oguslu, EnderCommunication becomes more and more important day by day and especially secure communication from one end to the other holds a vital place in our daily life. Developed countries which are aware of this fact has started to carry out serious studies on secure communication from one end to the other. One of the most important studies is the project which appeared as FNBDT (Future Narrow Band Digital Terminal) at first and was renamed as SCIP (Secure Communication Interoperability Protocol) later on. FNBDT (Future Narrow Band Digital Terminal) or SCIP (Secure Communication Interoperability Protocol) is a communication protocol which is a result of secure communication need of different network devices in contact with each other. The main purpose of the protocol is to provide the new generation terminals which are source of transmission with secure communication with each other through different networks using narrow band. National and international studies on FNBDT/SCIP has focused on three main points; FNBDT protocol, SCIP protocol and codes of MELP (Mixed Excitation Linear Prediction) Studies about implementation of FNBDT/SCIP are much fewer than theoretical studies on the matter. Some tests of FNBDT/SCIP on satellite and local Networks are carried out to overcome this lack of implementation. It is aimed to set up calls on different Networks, to check transmission of voice and data with and without any loss and to find out the limits with these tests. Results of these tests were declared before. In this study, some tests on satellite and local Networks are carried out; as a result, values about call set ups and limits of voice and data transmission are compared with ITU (International Telecommunications Union) standards.Conference Object Citation - WoS: 1Optimal Energy Efficient Routing in Wireless Sensor Networks With Link Asymmetry(Ieee, 2012) Ozyer, Sibel T.; Tavli, Bulent; Koyuncu, MuratIn Wireless Sensor Networks (WSNs), link unidirectionality is an unavoidable phenomenon. The existence of unidirectional links can be attributed to several physical factors induced by the transceiver characteristics as well as other environmental phenomena. Transmission power heterogeneity is the dominant paradigm that leads to unidirectionality. In this study, we investigate the effects of transmission power heterogeneity on the lifetime of WSNs through a novel Linear Programming (LP) framework both for networks that utilize only bidirectional links and for those that can use unidirectional links in addition to bidirectional links. Our results show that transmission power heterogeneity can lead to more than 25 % decrease in network lifetime for protocols that can operate only on bidirectional links when compared to a network without any heterogeneity. However, if the use of unidirectional links is also enabled then, the decrease in network lifetime is at most 12 %.Conference Object Feature Fusion in Part-Based Object Detection(Ieee, 2015) Koyuncu, Murat; Cetinkaya, BasarIn this study, classification of complex objects in images as a whole is compared with classification of its distinctive components using different features. In addition, the impact of feature fusion in part-based object detection is investigated. Applied method, implemented system, conducted tests and their results are presented in this paper. Test results show that, even in the case of a good segmentation, object components are classified more successfully compared to whole object and feature fusion method improves the obtained results to a certain degree.Conference Object A Component-Based Object Detection Method Extended With a Fuzzy Inference Engine(Ieee, 2015) Koyuncu, Murat; Cetinkaya, BasarIn this paper, we propose a component-based object detection method extended with the fuzzy inference technique. The proposed method detects constituent components of a complex object instead of a whole object in images. For component detection, multiple multi-class support vector machines (SVM) are used in parallel. Each SVM classifies the candidate component using a different low-level image feature. The obtained results are fused to reach a decision about the component. Then, a fuzzy object extractor determines the whole object considering the detected components and their geometric configurations. The fuzzy object extractor is a fuzzy inference engine which tests various combinations of detected components and their fuzzified directions and distances. The initial tests yield promising results and encourage further studies to extend proposed method.Conference Object A Novel Fuzzy Visual Object Classification Approach(Ieee, 2012) Altintakan, Umit Lutfu; Yazici, Adnan; Koyuncu, MuratSupport Vector Machines (SVMs) have been extensively used for visual object classification to bridge the semantic gap between the low level features and high level concepts. SVM treats each training input equally during the construction of its decision surface which results in poor learning machines if training data include outliers. In this paper, a novel fuzzy visual object classification approach utilizing Self-Organizing Maps (SOMs) in SVM is proposed. The experimental results show the effectiveness of the proposed Fuzzy SVM compared to the traditional SVM.Conference Object Citation - WoS: 1A Framework for Fuzzy Video Content Extraction, Storage and Retrieval(Ieee, 2010) Koyuncu, Murat; Yilmaz, Turgay; Yildirim, Yakup; Yazici, AdnanThis study presents a new comprehensive framework for semantic content extraction from raw video, storage of the extracted data and retrieval of the stored data. Objects, spatial relations between objects, events and temporal relations between events, which are considered as semantic contents of the video, are extracted automatically to a certain extend with the developed approach. Extraction process is supported by manual annotation when automatic extraction is not satisfactory. The extracted information is stored in an intelligent fuzzy object-oriented database in which the database is enhanced with a fuzzy knowledge-based system. Domain specific deduction rules can be defined to derive new information about semantic contents of the video. The database is also supported by an access structure to increase retrieval efficiency. The proposed framework is capable of handling uncertain data arising from annotation process or video nature.Conference Object Citation - WoS: 2Comparison of Scheduling Algorithms for Multimedia Applications in Ipv4 and Ipv6(Ieee, 2015) Koyuncu, Murat; AL-Fayyadh, HayderProviding guaranteed services in the Internet has become extremely essential to fulfill the requirements of the Internet users. With an increase in the number of users and demand for multimedia applications like video streaming, VoIP and video conferencing, larger bandwidth requirement increases drastically since such applications are very sensitive to delay, packet loss, and jitter. In such an environment, Quality of Service (QoS) is an important network performance parameter having a significant impact on multimedia applications. Besides other improvements, IPv6 was designed to improve QoS supported by IPv4. This paper gives a comparative analysis of three well-known queuing algorithms (First-in, First-Out-FIFO, Priority Queuing-PQ and Weighted-Fair Queuing-WFQ) which are examined to see their effects for multimedia applications in the IPv4 and IPv6 networks. OPNET is used for modeling, simulation and analyzing. Although IPv6 with PQ provides best performance for multimedia applications, IPv6 with WFQ is more appropriate when low priority traffic is also available.
