{"title":"PDF based face recognition system in different colour channels using discrete wavelet decomposition","authors":"G. Anbarjafari, H. Demirel","doi":"10.1109/SIU.2009.5136447","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136447","url":null,"abstract":"In this paper, a new high performance face recognition system based on the probability distribution functions of pixels obtained from intensity images in HSI and YCbCr colour channels and their decomposed images obtained by discrete wavelet decomposition is proposed. The PDFs of the equalized face images in spatial and subband domains in different colour channel are used as statistical feature vectors for the recognition of faces by minimizing the Kullback- Leibler Distance between the PDF of a given face and the PDFs of faces in the database. Majority voting and feature vector fusion methods have been employed to combine feature vectors obtained from different colour channels to improve the recognition performance.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125936789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Comparison of HK and SC curvature descriptions in a scale-space for the purpose of 3D object recognition","authors":"E. Akagunduz, ilkay Ulusoy","doi":"10.1109/SIU.2009.5136551","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136551","url":null,"abstract":"Most 3D object recognition methods use mean-Gaussian curvatures (HK) [2] or shape index-curvedness (SC) [2] values for classification. Although these two curvature descriptions classify objects into same categories, their mathematical defintions vary. In this study a comparison between the two curvature description is carried out for the purpose of 3D object recognition. Since unlike S; H, K and C values are not invariant of scale and resolution, a method to set them fully invariant to any transforation is proposed. The results show that scale and resolution invariant HK curvature values gives better recognition results compared to SC curvature values.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117212001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Palmprint recognition with applying different kernel matrix sizes on Gabor wavelet features","authors":"M. Aykut, M. Ekinci","doi":"10.1109/SIU.2009.5136379","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136379","url":null,"abstract":"This paper presents Gabor based Kernel Principal Component Analysis (KPCA) palmprint recognition method for human identification. The intensity values of palmprint images extracted by using an image preprocessing method are first normalized. Then these images are transformed to the spectral domain by using Gabor wavelet transform. The transformed palm images exhibit strong characteristics of spatial locality, scale, and orientation selectivity. Next, the feature vectors are nonlinearly maps into a high dimensional feature space with KPCA method. In this method during kernel matrix calculation, the sample numbers per class changed and it's effect investigated. Finally, weighted Euclidean distance based nearest neighbor method is realized for classification. The proposed algorithm tested on the most-well known palmprint database, PolyU, includes 7752 samples of 386 different people.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124520618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Stereo video broadcast over DVB-H","authors":"L. Aksay, A. Tikanmaki, A. Gotchev, Gözde Bozda","doi":"10.1109/SIU.2009.5136461","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136461","url":null,"abstract":"This paper presents modelling and analysis of a mobile 3DTV broadcast system for handheld devices. The underlying technology behind our system is the DVB-H specification which brings ordinary TV broadcast services to battery-powered handheld receivers. In our system, we simulated the broadcast of stereo video content over DVB-H to mobile handheld devices with autostereoscopic displays. In this way, mobile users can watch 3D content without need for eyeglasses or any special equipment.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115172099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A nonquadratic regularization based image reconstruction technique for SAR data with phase errors","authors":"N. O. Onhon, M. Çetin","doi":"10.1109/SIU.2009.5136459","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136459","url":null,"abstract":"One of the fundamental problems in Synthetic Aperture Radar (SAR) imaging is phase errors. Phase errors occur when the time required for the transmitted signal from SAR to the target and back cannot be obtained properly either because the distance between the SAR platform and the target cannot be measured exactly or in the case of random delays in the signal due to propagation in atmospheric turbulence. Phase errors cause blurring of the reconstructed image in the cross range direction. In this study, a nonquadratic regularization-based framework is proposed for joint image formation and phase error removal. The method involves the optimization of a cost function with respect to the image as well as the phase errors. Experimental results show the effectiveness of the proposed method","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115200938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The effect of classical Turkish musics on the autonomic nervous system","authors":"D. Yilmaz, M. Yıldız, Koray Isildak","doi":"10.1109/SIU.2009.5136560","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136560","url":null,"abstract":"In this study, the effects of two different forms of classical Turkish music (hüseyni and saba) on the Authonomous Nerves System (ANS) are investigated. During listening these music forms, the electrocardiogram (ECG) and respiration records were made from two seperated subjects groups which are age and gender matched. These records have three periods: first period is before the listening, second is listening and third is after the listening. Heart rate variability (HRV) signal are obtained form record and power spectral densities (PSD) of HRV are estimated. According to the results of calculated parameters, both of two forms of Turkish music is cause significant differences on the very low frequency (VLF) power that is effected by hormonal and thermal control or vasomotor aktivities. The high frequency (HF) power of HRV PSD's is increase at listening the form of saba Turkish music and sympatho-vagal balance (LF/HF ratio) is shifted in dominance of parasympathetic activities.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116234293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A study for development of propagation model based on ray tracing for coverage prediction in terrestrial broadcasting systems","authors":"M. Tabakcioglu, Ahmet Ozmen, A. Kara","doi":"10.1109/SIU.2009.5136359","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136359","url":null,"abstract":"In this work, improvements on propagation prediction models based on ray tracing in coverage estimation for digital broadcasting systems are presented. For this purpose, firstly, propagation models based on Geometrical Theory of Diffraction (GTD) are discussed, and then an improved model is proposed for prediction of propagation path loss or electric field strength at the receiver. The proposed model incorporates first order expansion of classical GTD in field computation and convex hull for ray tracing. Simulation results are presented for comparison of various models in terms of computation time and accuracy.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116544194","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Multiple base station placement with k-means Local+","authors":"Z. C. Taysi, M. A. Guvensan, A. Yavuz","doi":"10.1109/SIU.2009.5136541","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136541","url":null,"abstract":"Sensor applications have many different constraints such as the network lifetime, the number of sensor nodes and base stations (BS). The main goal of the researchers is to maximize the network lifetime with minimum budget. BS positioning and the choice of routing algorithm are two important criteria in maximizing the lifetime. Many wireless sensor network (WSN) applications, like the intelligent agriculture, habitat and weather monitoring, are based on continuous data delivery model. In these applications, each sensor node generally collects data of the same size and periodically transfers this data to BS by multi-hop communication. To maximize the network lifetime of such applications, we propose a new BS placement algorithm for deploying multiple base stations, called k-means Local+ which provides up to 45% longer network lifetime than single k-means algroithm [1].","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122438388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Induction motor fault diagnosis via current analysis on time domain","authors":"S. Gunal, D. Gokhan Ece, O. Gerek","doi":"10.1109/SIU.2009.5136439","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136439","url":null,"abstract":"This study proposes a novel approach to induction motor fault diagnosis through motor current analysis. Most of the previous works employing motor current analysis use spectral methods to extract required features for detecting motor faults. The proposed method, however, utilizes time domain information for this purpose. Energy, local extrema, kurtosis and skewness parameters constitute the feature set extracted from the motor current on time domain within sliding window. In fault detection and classification experiments, six identical three-phase induction motors are used with one of them being healthy reference and the remaining five motors being deliberately broken to have different faults. The proposed time domain based features are employed in well known Bayesian classifier. Efficiency of the proposed method is examined at various motor load levels. Experimental results verify that the proposed method successfully detects and discriminates different motor faults.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122819464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Data fusion in satellite images and their quantitative analysis","authors":"Bora Ugurku, H. Yildirim, M. Emin Ozel","doi":"10.1109/SIU.2009.5136408","DOIUrl":"https://doi.org/10.1109/SIU.2009.5136408","url":null,"abstract":"Data fusion may be considered a kind of complex image processing method which combines the different satellite images to bring complementary and useful information into one single composite image. The fused image will usually have better spectral and spatial resolutions to see more detailed and sometimes new features not seen in the original images. In the present work, Landsat 7 ETM, 1999 dated satellite data which is belong to Canakkale Province is used. The multispectral satellite image that is rich spectrally and panchromatic(PAN) image that is rich spatially but poor spectrally are fused by using two different methods based on Intensity, Hue, Saturation (IHS) Transformation and Principal Component Analysis. Both of the methods are assessed by looking through the relationship between the vegetation indexes of final images and multispectral satellite image.","PeriodicalId":219938,"journal":{"name":"2009 IEEE 17th Signal Processing and Communications Applications Conference","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121895253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}