Browsing by Author "Öktem,R."

Now showing 1 - 12 of 12

Citation - Scopus: 1
Alternative Feature Extraction Approaches for Car Plate Recognition;
(2005) Duman,Ş.; Öktem,R.; Çetin,A.E.; 01. Atılım University
License plate detection is an important problem for surveillance systems and traffic applications. This work primarily focuses on feature extraction approaches for extracting candidate car plate regions. For this purpose, we start with restricting our feature extraction regions by use of a hierarchical edge detection method. Edge detection is based on discrete wavelet transform. Performances of Haar and Daubechies filters are compared on that basis. Three different methods are proposed for feature extraction: histogram feature, horizontal profiling on the edge map, and segment features followed by segmentation. The performance of each algorithm is presented by use of tests on ATS images. © 2005 IEEE.
Bar code localization by image processing;
(2005) Öktem,R.; Çetin,A.E.; 01. Atılım University
This paper addresses the problem of bar code recognition by use of image processing. Bar codes are composed of parallel alternating dark-light stripes; hence they also appear as parallel lines connected at some orientation in a binary edge map. The proposed algorithms exploit that feature and use morphology and free angle thresholding for localization. Edge map is formed by Sobel operator and binary subband decomposition separately, and the two methods are compared in terms of time complexity and performance. Detailed discussion of test results are also presented. ©2005 IEEE.
Citation - Scopus: 10
Bar code localization in wavelet domain by using binary morphology;
(2004) Öktem,R.; 01. Atılım University
In this paper, a wavelet transform based bar code localization algorithm is proposed. The algorithm is designed to enable fast and memory efficient application for automatic bar code recognition systems that are used in big manufacturing and distribution units. The region of interest areas are kept and other regions are discarded by applying binary morphology on wavelet transform coefficients. © 2004 IEEE.
A bayes decision model for RSS based location estimation;
(2007) Dinçer,Z.; Öktem,R.; Aydin,E.; Department of Electrical & Electronics Engineering; 15. Graduate School of Natural and Applied Sciences; 01. Atılım University
This work introduces a location estimation method based on Bayes Decision Theory using Radio Signal Strengths for indoor environment. Signal Strengths are observed through three transmitters at three distinct frequencies in UHF band, an active RFID tag and a modem connected to a computer. The test environment is 2100cmx720cm, which is divided into classed of square grids. For each class, a set of received signal strengths are measured and processed. Assuming that the class in which the RFID tag was located in the previous time of measurement is known, the next location (class) is estimated using Bayes Decision Theory. Proposed method is tested in a laboratory environment with obstacles. Results show that proposed method will be successful in location estimation where the estimation error stays within around 2m.
Citation - Scopus: 6
A Fast Hough Transform Approximation and Its Application for Barcode Localization;
(2007) Safran,M.I.; Öktem,R.; 01. Atılım University
This paper addresses barcode localization in images acquired by wireles cameras. For this puipose, a fast Hough transform approximation by use of a sliding mask is developed. The approximation decomposes the lines at different orientations into distinct bitplanes. Barcode localization is achieved by considering the high density locations in the bitplanes via morphology and profiling. The time complexity of the proposed approximation is lower than the previously proposed fast Hough transform, though it achieves the equal performance in localization of barcodes.
Citation - Scopus: 5
Gezgin & Gezgin-2: Adaptive Real-time İmage Processing Subsystems For Earth Observing Small Satellites
(2006) Ismailoǧlu,N.; Benderli,O.; Yeşil,S.; Sever,R.; Okcan,B.; Şengül,O.; Öktem,R.; Chemical Engineering; 06. School Of Engineering; 01. Atılım University
GEZGİN and GEZGİN-2 are real-time multi-spectral image processing subsystems developed for BİLSAT-1 and RASAT satellites respectively, the first two earth observing small satellites of Turkey, Main functionality of these subsystems is to compress in real-time multi-spectral images received concurrently from imagers, using JPEG2000 Image Compression algorithm. The compression features are controlled through user-supplied parameters uploaded in-orbit, so that the compression rate could be adapted to bandwidth, image quality and other mission requirements. GEZGİN employs both reconfigurable hardware and a DSP processor for image processing, where as the more advanced GEZGİN-2 contains full integration of the JPEG2000 processing path plus other image pre-processing features on reconfigurable hardware, hence offering increased performance and full re-configurability in orbit. Both systems demonstrate space-tailored architectures for implementing image processing functions where adaptability becomes the crucial issue determining robustness, flexibility and survivability of the system. © 2006 IEEE.
Citation - Scopus: 11
Gezgi̇n-2: an Advanced Image Processing Subsystem for Earth-Observing Small Satellites
(2005) Ismailoǧlu,N.; Benderli,O.; Yeşil,S.; Sever,R.; Okcan,B.; Öktem,R.; Chemical Engineering; 06. School Of Engineering; 01. Atılım University
GEZGİN-2 is a real-time image processing subsystem, currently being developed for RASAT, the second small satellite to be launched by TÜBİTAK-BİLTEN, in 2007. It is an advanced version of the GEZCİN payload, implementing JPEG 2000 image compression algorithm and currently flying on the BİLSAT-1 satellite. The main enhancements in GEZGİN-2 are the integration of the full processing path of JPEG 2000 algorithm in a single Field Programmable Gate Array (FPGA) for increased processing performance and high speed data links complying with the ESA Spacewire standard, for data transfer at a rate of 100 Mbps. In addition to JPEG2000, GEZGIN-2 facilitates image pre-processing for cloud/sea detection and image/data encryption implemented on a daughter-board called GÖLGE. As in GEZGİN, GEZGİN-2 allows for adjustment of compression ratio for different mission times by means of run-time supplied parameters and full reconfigurability in orbit. © 2005 IEEE.
Citation - Scopus: 14
An indoor navigation aid designed for visually impaired people
(IEEE Computer Society, 2008) Öktem,R.; Aydin,E.; Çaǧiltay,N.E.; Department of Electrical & Electronics Engineering; 15. Graduate School of Natural and Applied Sciences; 01. Atılım University
This work introduces the hardware architecture and general principles of a portable indoor navigation system for guiding visually impaired people. It operates through wireless communication between a compact hardware interface unit carried by the user, a central processing unit and an active RFID unit. The RFID unit collects signals as regard to the position of the user, the central system processes those signals to estimate the position of the user and proposes a route and direction for the user to follow, whereas hardware interface unit provides interaction. The orienteering of the user is obtained by a tactile compass. © 2008 IEEE.
Citation - Scopus: 14
A Remote Laboratory for Training in Radio Communications: Errl
(2007) Kara,A.; Aydin,E.U.; Öktem,R.; Çaǧiltay,N.; Department of Electrical & Electronics Engineering; 15. Graduate School of Natural and Applied Sciences; 01. Atılım University
This paper presents, first, a short survey of remote laboratory initiatives in electrical and computer engineering, and then discusses design and development phases of remote laboratory environment on radio communications, the ERRL (European Remote Radio Laboratory). As being the first attempt in establishing of such a large scale remote laboratory on radio communications, ERRL enables access to high technology RF equipments and setups through the Internet. The software structure, target groups and experimental set ups of ERRL are shortly discussed. First attempts on implementation of pilot experiments are discussed. © 2007 IEEE.
A Segmentation Algorithm for Foreground/Background Extraction;
(2006) Öktem,R.; Güldoǧan,E.; Gabbouj,M.; 01. Atılım University
This paper describes a three-pass segmentation algorithm followed by a foreground/background extraction rule. Being imperfect, the basic objective of the proposed segmentation is to enable the extraction of objects that may be of main interest to the user, and the background. The formed segments are assigned points, according to the location of their center of mass and bounding box coordinates, and spatial dispersion. Each segment is labelled as foreground or background in compliance with the grade point they get. © 2006 IEEE.
Study of an Rfid Based Moving Object Tracking System
(2007) Aydin,E.; Öktem,R.; Dinçer,Z.; Akbulut,I.K.; Department of Electrical & Electronics Engineering; 15. Graduate School of Natural and Applied Sciences; 01. Atılım University
This paper presents a study on localization and tracking of an object carrying an active RFID tag. The study incorporates processing of the signals received from transmitters, in a way to locate and track the coordinate in an indoor environment. During the course of the project, both outdoor and indoor experiments have been conducted. Empirical distance vs signal strength formulations are formed by use of the collected data. Deviation of the reported values from the theory is analyzed, and the effects of reflections from doors, windows, etc. are observed. In order to improve the accuracy of tracking, Bayesian and Kalman Filtering approaches are incorporated.
Citation - Scopus: 8
Study of an Rfid Based Moving Object Tracking System
(2007) Aydin,E.; Öktem,R.; Dinçer,Z.; Akbulut,I.K.; Department of Electrical & Electronics Engineering; 15. Graduate School of Natural and Applied Sciences; 01. Atılım University
This paper presents a study on localization and tracking of an object carrying an active RFID tag. The study incorporates processing of the signals received from transmitters, in a way to locate and track the coordinate in an indoor environment. During the course of the project, both outdoor and indoor experiments have been conducted. Empirical distance vs signal strength formulations are formed by use of the collected data. Deviation of the reported values from the theory is analyzed, and the effects of reflections from doors, windows, etc. are observed. In order to improve the accuracy of tracking, Bayesian and Kalman Filtering approaches are incorporated.