{"title":"An Experience in Image Compression Using Neural Networks","authors":"I. Vilović","doi":"10.1109/ELMAR.2006.329523","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329523","url":null,"abstract":"There are number trials of using neural networks as signal processing tools for image compression. In this paper, a direct solution method is used for image compression using the neural networks. An experience of using multilayer perceptron for image compression is presented. The multilayer perceptron is used for transform coding of the image. The network is trained for different number of hidden neurons with direct impact to compress ratio. It is experimented with different images that have been segmented in the blocks of various sizes for compression process. Reconstructed image is compared with original image using signal-to-noise ratio and number of bits per pixel. The results show the possibility of using multilayer perceptrons for image compression","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129295306","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":"Image Contrast Enhancement by Contourlet Transform","authors":"E. Nezhadarya, M. Shamsollahi","doi":"10.1109/ELMAR.2006.329520","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329520","url":null,"abstract":"We propose a new method for image contrast enhancement, based on a recently introduced 2D directional non-separable transform known as contourlet transform. Conventional 2D wavelet transform is separable and thus can not sparsely represent non-separable structures of the image, such as directional curves. The directionality feature of contourlet transform makes it a good choice for representation of curves and edges in the image. In this paper, a new enhancement function is proposed to enhance the edges by contourlet transform. The method is also compared with two usual contrast enhancement methods, histogram equalization and wavelet based contrast enhancement. It is shown that the contrast enhancement method based on contourlet transform is superior to both histogram equalization and the method based on wavelet transform, in both enhancement of fine structures in the image and denoising","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126741341","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":"Displacement sensor axis misalignment error","authors":"V. Tudić","doi":"10.1109/ELMAR.2006.329556","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329556","url":null,"abstract":"Because of valve displacement great importance in valve systems in many marine power aggregates and other servomechanisms and equipment, controlling measurement of this parameter would be taken. Hysteresis measurement must also be taken after every mounting and periodically revision activities. Controlling measurement complies of displacement sensor and computer system applied with adequate hardware and software solutions. Displacement sensor axis misalignment error cannot be avoided in any situation where sensor axis line of symmetry is not parallel with axis line of valve movement. Therefore, elevation error must be considered. Other errors and imperfections in measuring process because of clearly thesis description in this paper are negligible (measuring method, sensor class, nonlinearity, software signal transition). Paper goal is pointing error values regarding sensor axis elevation and its presentation in meaningful ways, with comprehensive further influences","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128560475","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":"Estimation of Value Added Services in Bosnia and Herzegovina","authors":"M. Hadzialic, A. Hajdarevic, E. Filipović","doi":"10.1109/ELMAR.2006.329579","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329579","url":null,"abstract":"Intention of all operators is to expand its profit as a well as to attract the business subscribers as they generated more traffic and have a high ARPU. The non voice services are the way to attract business subscribers, by identifying the needs of the companies for the non voice services. In the article we present situation on Bosnia and Herzegovina market and the possible way to earn revenue by offering the value added services based on GPRS. Different VPN models are shortly described and some of possible ways of assembling the non voice services are introduced","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122549614","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":"Interconnection between WLAN and 3GPP Networks","authors":"M. Suknaic, M. Grgic, B. Zovko-Cihlar","doi":"10.1109/ELMAR.2006.329548","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329548","url":null,"abstract":"The first scenarios of interworking between WLAN and 3GPP networks, which were predicted from 3GPP standards, are already in usage today. Both technologies, WLAN and 3GPP are developing to enable more bandwidth and faster data rates for the end users and represents in some areas complementary solutions. The cooperation between those two networks would enable additional radio capacity for 3GPP networks and common usage of existing 3GPP core architecture. New IEEE 802 standards offers alternative broadband access networks which will be in place before fourth generation (4G) of mobile networks and ready to connect to both mobile and fixed core networks","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114944642","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}
O. López, M. Martínez-Rach, J. Oliver, M. Malumbres
{"title":"A Heuristic Bitrate Control for Non-embedded Wavelet Image Encoders","authors":"O. López, M. Martínez-Rach, J. Oliver, M. Malumbres","doi":"10.1109/ELMAR.2006.329504","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329504","url":null,"abstract":"Most recently developed wavelet image emcoders support as native feature an embedded bitrate control that could be useful for applications where obtaining an accurate bitrate is critical. Well-known encoders like JPEG2000 and SPIHT employ embedded coding. However, this feature makes them highly complex, being a serious restriction for certain applications and devices (such as mobile multimedia communications involving PDAs, mobile phones, etc.). As a consequence, in the last years, authors proposed non-embedded encoders with vetyfast and low-memory-demanding encoding/decoding processes. In this paper, we propose rate control tools that are able to supply the required rate control accuracy with as low as possible complexity increase. Experimental tests show that good results are obtained by employing trivial models of the encoder engine, being able to modulate the accuracy degree with lightweight iterative versions","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126166676","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":"Assessment of Region-Based Moment Invariants for Object Recognition","authors":"B. Potočnik","doi":"10.1109/ELMAR.2006.329507","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329507","url":null,"abstract":"Geometric region-based moments as features for invariant object recognition are studied. Theoretically rotation, translation, and scale invariant Hu, Zernike, and Krawtchouk moments are used as features for region description. Accuracy of such description and efficiency is tested by recognition of letters and digits from extended Slovenian alphabet. Ten testing samples in six different image resolutions are constructed for each character from learning set. Testing set consists of 390 samples per resolution (altogether 2340 samples). Recognition accuracy obtained by using Hu moments is 95.6%, 87.4% with Zernike moments, and with Krawtchouk moments 64.1%. Object recognition by using Krawtchouk moments is the most sensitive to object rotation and scaling, which is confirmed with the description error of 9.28%. All moment invariants can be reliable used for object recognition in images with up to four times lower resolution as in original image","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128454494","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":"Rain Attenuation at Low Earth Orbiting Satellite Ground Station","authors":"S. Cakaj, K. Malaric","doi":"10.1109/ELMAR.2006.329559","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329559","url":null,"abstract":"The project \"MOST\" (micro variability and oscillations of stars) is a Canadian micro satellite space telescope mission. The micro satellite carries a Rumak-Maksutov telescope with an aperture of 15 cm. The size of the satellite is 65 cmtimes65 cmtimes30 cm and the mass is about 65 kg. The goals of the mission are to analyze the inner structure of stars, set a lower limit to the age of the universe and to search for Exoplanets. The project MOST consists of a low Earth orbiting (LEO) satellite and three ground stations, one of them in Vienna. The Vienna ground station system was set up at the Institute for Astronomy of the University of Vienna in cooperation with the Institute of Communications and Radio-Frequency Engineering of the Vienna University of Technology. During the link budget calculations atmospheric attenuation had to be considered. The satellite link operates in 2 GHz band. In this band the ionospheric effects are negligible. This paper presents the methodology applied for rain attenuation calculations","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"98 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128000997","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":"PDF Model of Multimedia and Scientific Images in the Wavelet Domain","authors":"J. Švihlík, P. Páta","doi":"10.1109/ELMAR.2006.329505","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329505","url":null,"abstract":"This work deals with a statistical model of the marginal probability density function (PDF) of digital images in the wavelet domain. Estimation of parameters of the model using least square method is also included. A dyadic decomposition as a special form of the discrete wavelet transform is used in this paper. There is described the statistical model of wavelet coefficients based on the generalized Laplacian. The modeling of PDF in the wavelet domain is well blown procedure, which is used for reconstruction of multimedia data. The multimedia data are characterized by their image content. The robotic astronomical systems, i.e. BOOTES (burst observer optical transient exploring system) provide a huge amount of a data with specific properties (i.e. bit depth, noise, objects). These data are very specific and it is necessary to analyze their PDF in the wavelet domain for their other processing. The parameters of the statistical model of scientific and multimedia data have been estimated and compared. It is very significant for proper setup of the reconstruction algorithms","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130006431","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":"Semantic Adaptation of Multimedia Content","authors":"M. Zufferey, H. Kosch","doi":"10.1109/ELMAR.2006.329575","DOIUrl":"https://doi.org/10.1109/ELMAR.2006.329575","url":null,"abstract":"The increasing diversity of devices and the heterogeneity of networks pose nowadays a challenge in the delivery and consumption of multimedia content. In this context, the part 7 of the MPEG-21 standard formally named digital item adaptation (DIA) targets the adaptation of multimedia content based on usage environment, such as network characteristics, terminal capabilities and user characteristics. But, MPEG-21 DIA does not take into account MPEG-7 semantics description tools, which provide means for a conceptual (semantic) description that is close to the human understanding of multimedia content. Therefore, to fill this gap, we proposed and implemented an interactive and user-centric framework called semantic adaptation framework (SAF). The SAF provides facilities for the generation of all the required semantic metadata and enables an MPEG-21 adaptation engine to semantically adapt the multimedia content in order to provide the user with the best possible experience","PeriodicalId":430777,"journal":{"name":"Proceedings ELMAR 2006","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130024846","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}
京公网安备 11010802042870号
求助内容：
应助结果提醒方式：