4 results
Search Results
Now showing 1 - 4 of 4
Conference Object A Segmentation Algorithm for Foreground/Background Extraction(Ieee, 2006) Oktem, Rusen; Guldogan, Esin; Gabbouj, MoncefThis 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.Article Citation - WoS: 40Citation - Scopus: 66Locally Adaptive Dct Filtering for Signal-Dependent Noise Removal(Springer, 2007) Oktem, Rusen; Egiazarian, Karen; Lukin, Vladimir V.; Ponomarenko, Nikolay N.; Tsymbal, Oleg V.This work addresses the problem of signal- dependent noise removal in images. An adaptive nonlinear filtering approach in the orthogonal transform domain is proposed and analyzed for several typical noise environments in the DCT domain. Being applied locally, that is, within a window of small support, DCT is expected to approximate the Karhunen- Loeve decorrelating transform, which enables effective suppression of noise components. The detail preservation ability of the filter allowing not to destroy any useful content in images is especially emphasized and considered. A local adaptive DCT filtering for the two cases, when signal-dependent noise can be and cannot be mapped into additive uncorrelated noise with homomorphic transform, is formulated. Although the main issue is signal-dependent and pure multiplicative noise, the proposed filtering approach is also found to be competing with the state-of-the-art methods on pure additive noise corrupted images.Conference Object An Indoor Navigation Aid Designed for Visually Impaired People(Ieee, 2008) Oktem, Rusen; Aydin, Elif; Cagiltay, Nergiz ErcilThis 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.Conference Object Citation - WoS: 1Gezgin & Gezgin-2(Ieee Computer Soc, 2006) Ismailoglu, N.; Benderli, O.; Yesil, S.; Sever, R.; Okcan, B.; Sengul, O.; Oktem, RusenGEZGIN and GEZGIN-2 are real-time multispectral image processing subsystems developedfor BILSAT-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. GEZGIN employs both reconfigurable hardware and a DSP processor for image processing, where as the more advanced GEZGIN-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.
