Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775712
S. Ghandali, M. Moghaddam
Signature verification and Identification has great importance in authentication systems. Persian signatures are different from other signature types because people usually do not use text in it and they draw a shape as their signature. In this paper, a method for off-line Persian signature identification and verification is proposed that is based on DWT (Discrete Wavelet Transform) and Image Fusion. To extract features, at first DWT is used to access details of signature; then several signatures instances of each person are fused together to generate reference pattern of person's signature. In the classification phase, Euclidean distance between the test image and each pattern is used in each sub band. Experimental results confirmed the effectiveness of proposed method.
{"title":"A Method for Off-line Persian Signature Identification and Verification Using DWT and Image Fusion","authors":"S. Ghandali, M. Moghaddam","doi":"10.1109/ISSPIT.2008.4775712","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775712","url":null,"abstract":"Signature verification and Identification has great importance in authentication systems. Persian signatures are different from other signature types because people usually do not use text in it and they draw a shape as their signature. In this paper, a method for off-line Persian signature identification and verification is proposed that is based on DWT (Discrete Wavelet Transform) and Image Fusion. To extract features, at first DWT is used to access details of signature; then several signatures instances of each person are fused together to generate reference pattern of person's signature. In the classification phase, Euclidean distance between the test image and each pattern is used in each sub band. Experimental results confirmed the effectiveness of proposed method.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130996667","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775724
T. Pham, M. Song, J. Y. Kim, S. Na, S. Hwang
In this paper we present a new approach for the detection of lip centers based on eye localization that is adopted into a lip reading system in mobile environments. First, the centers of left eyes and right eyes are localized directly. Then we use the geometry characteristics of faces to extract rough lip regions. Next, we use 2 steps of threshold adaptation to binarize lip images. The first threshold adaptation is used to estimate standard lip threshold for each image; and the second one is applied to compute thresholds for left and right lip image based on standard lip threshold. Finally we apply Sobel edge map based filter with projections to detect precise lip centers. Experimental study shows that our algorithm can work well under various illumination conditions that is one of the typical difficulties of image processing and computer vision problems.
{"title":"A Robust Lip Center Detection in Cell Phone Environment","authors":"T. Pham, M. Song, J. Y. Kim, S. Na, S. Hwang","doi":"10.1109/ISSPIT.2008.4775724","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775724","url":null,"abstract":"In this paper we present a new approach for the detection of lip centers based on eye localization that is adopted into a lip reading system in mobile environments. First, the centers of left eyes and right eyes are localized directly. Then we use the geometry characteristics of faces to extract rough lip regions. Next, we use 2 steps of threshold adaptation to binarize lip images. The first threshold adaptation is used to estimate standard lip threshold for each image; and the second one is applied to compute thresholds for left and right lip image based on standard lip threshold. Finally we apply Sobel edge map based filter with projections to detect precise lip centers. Experimental study shows that our algorithm can work well under various illumination conditions that is one of the typical difficulties of image processing and computer vision problems.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133377036","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775728
N. Cahill, R. Lawlor
In this paper a novel approach to doubletalk detection (DTD) is presented. This approach uses a modified non-negative matrix factorization (NMF) technique originally developed for monaural sound source separation to perform DTD. The efficacy of this approach is demonstrated through experiments using real room impulse responses (RIRs). The properties of this algorithm are then discussed with reference to experimental results.
{"title":"An Approach to Doubletalk Detection Based on Non-Negative Matrix Factorization","authors":"N. Cahill, R. Lawlor","doi":"10.1109/ISSPIT.2008.4775728","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775728","url":null,"abstract":"In this paper a novel approach to doubletalk detection (DTD) is presented. This approach uses a modified non-negative matrix factorization (NMF) technique originally developed for monaural sound source separation to perform DTD. The efficacy of this approach is demonstrated through experiments using real room impulse responses (RIRs). The properties of this algorithm are then discussed with reference to experimental results.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133360623","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775642
Zlatan Begić, M. Bolic
Multicast networking support is becoming an increasingly important future technology area for group-based applications. Although the deployment of multicast networks has been picking up, the area of multicast security has not received much attention. The few proposals for securing multicast communication do not address the unique requirements arising from the multicast group communication model. Integrating a multicast security solution involves numerous engineering tradeoffs. The end goal of effective operational performance and scalability over a heterogeneous internetwork is of primary interest for widescale adoption and application of such a capability. In this paper, various techniques that have been proposed to support multicast security are discussed and their relative merits are explored.
{"title":"Security in Multicast Networks","authors":"Zlatan Begić, M. Bolic","doi":"10.1109/ISSPIT.2008.4775642","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775642","url":null,"abstract":"Multicast networking support is becoming an increasingly important future technology area for group-based applications. Although the deployment of multicast networks has been picking up, the area of multicast security has not received much attention. The few proposals for securing multicast communication do not address the unique requirements arising from the multicast group communication model. Integrating a multicast security solution involves numerous engineering tradeoffs. The end goal of effective operational performance and scalability over a heterogeneous internetwork is of primary interest for widescale adoption and application of such a capability. In this paper, various techniques that have been proposed to support multicast security are discussed and their relative merits are explored.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127179857","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775652
Jonghyun Park, Gueesang Lee, A. Lai, Euichul Kim, Junsik Lim, Soohyung Kim, Hyungjeong Yang, Sang-Wook Oh
In this paper, a system for automatic detection and recognition of Korean texts or shop names in outdoor signboard images is described. The system includes detection, binarization and extraction of text in a signboard image captured by a camera of a mobile phone for the recognition of the shop name. It can deal with different font styles and sizes as well as illumination changes. Individual characters detected by connected component analysis are recognized by using nonlinear mesh, in which feature vectors of vertical and horizontal components are extracted from the binarized image. Proposed methods have been applied to a Korean text translation system, which can automatically detect and recognize Korean texts and generate the translation result.
{"title":"Automatic Detection and Recognition of Shop Name in Outdoor Signboard Images","authors":"Jonghyun Park, Gueesang Lee, A. Lai, Euichul Kim, Junsik Lim, Soohyung Kim, Hyungjeong Yang, Sang-Wook Oh","doi":"10.1109/ISSPIT.2008.4775652","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775652","url":null,"abstract":"In this paper, a system for automatic detection and recognition of Korean texts or shop names in outdoor signboard images is described. The system includes detection, binarization and extraction of text in a signboard image captured by a camera of a mobile phone for the recognition of the shop name. It can deal with different font styles and sizes as well as illumination changes. Individual characters detected by connected component analysis are recognized by using nonlinear mesh, in which feature vectors of vertical and horizontal components are extracted from the binarized image. Proposed methods have been applied to a Korean text translation system, which can automatically detect and recognize Korean texts and generate the translation result.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129637566","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775685
M. Najjarzadeh, A. Ayatollahi
In this paper, a FIR filter is designed using particle swarm optimization (PSO). Two design cases are organized as follows: low-pass and band-pass filter. In addition, the authors examine the utility of various error norms such as least mean squares (LMS) and minimax, and their impact on convergence behavior and optimal resultant frequency response. The effect of different population and iteration in PSO based FIR filter design is investigated, too. Examples of 1-D FIR filters are given using the above methodologies to illustrate the usefulness and efficiency of the proposed techniques.
{"title":"FIR Digital Filters Design: Particle Swarm Optimization Utilizing LMS and Minimax Strategies","authors":"M. Najjarzadeh, A. Ayatollahi","doi":"10.1109/ISSPIT.2008.4775685","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775685","url":null,"abstract":"In this paper, a FIR filter is designed using particle swarm optimization (PSO). Two design cases are organized as follows: low-pass and band-pass filter. In addition, the authors examine the utility of various error norms such as least mean squares (LMS) and minimax, and their impact on convergence behavior and optimal resultant frequency response. The effect of different population and iteration in PSO based FIR filter design is investigated, too. Examples of 1-D FIR filters are given using the above methodologies to illustrate the usefulness and efficiency of the proposed techniques.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129306742","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775688
C. J. Debono, N.P. Borg
Wireless sensor networks (WSN) have gained significant attention due to their ability to monitor physical phenomena within a wide range of applications. These networks are generally deployed in remote areas and are battery powered. This means that the lifetime of the network depends on the energy consumption, thus necessitating careful hardware and software design to sustain the long period of operation without human intervention. One way of reducing the energy required is to minimize the number of data transmissions. A prediction-based data reduction algorithm based on the least-mean-square (LMS) algorithm was implemented on a field programmable gate array (FPGA) to reduce the communication between the sensor nodes and the base station. Measurement results show that communication can be reduced by as much as 90% in a temperature monitoring application if an error of 0.5 degree is acceptable. This has a large impact on the lifetime of the wireless sensor network since the transceiver can be switched off during non-communication periods saving precious energy.
{"title":"The Implementation of an Adaptive Data Reduction Technique for Wireless Sensor Networks","authors":"C. J. Debono, N.P. Borg","doi":"10.1109/ISSPIT.2008.4775688","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775688","url":null,"abstract":"Wireless sensor networks (WSN) have gained significant attention due to their ability to monitor physical phenomena within a wide range of applications. These networks are generally deployed in remote areas and are battery powered. This means that the lifetime of the network depends on the energy consumption, thus necessitating careful hardware and software design to sustain the long period of operation without human intervention. One way of reducing the energy required is to minimize the number of data transmissions. A prediction-based data reduction algorithm based on the least-mean-square (LMS) algorithm was implemented on a field programmable gate array (FPGA) to reduce the communication between the sensor nodes and the base station. Measurement results show that communication can be reduced by as much as 90% in a temperature monitoring application if an error of 0.5 degree is acceptable. This has a large impact on the lifetime of the wireless sensor network since the transceiver can be switched off during non-communication periods saving precious energy.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122794251","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775653
N. Myridis
In this paper, we introduce a new field of systems applications, that of Computer-based Systems in Society (CbSyS). In this context, factors as topologies & architectures, sensor grids & networks, information processing etc., are combined in order to solve social problems as for instance to assist handicaps. As an introductory paradigm we develop a sensor-based system designed for the assistance of blinds, entitled B-light. This is a navigation system, object-oriented, sensor-based, which enables embedded configuration as well as networking perspective. The overall system can be composed by a multifaceted assembly of components of software and hardware. We cite herein the generic context of implementation. The analysis and presentation is vertical, beginning from the theoretical grounding of the application framework and reaching the representative implementation of an ad-hoc system. Elements of embedded systems, of sensor networks, of signal, image & information processing can be combined into any specific implementation. The anticipated benefits of the herein presented system, as well as of the general framework of CbSyS are vital since they offer solutions and improvements in critical problems in Society.
{"title":"Computer-Based Systems in Society (CbSyS)","authors":"N. Myridis","doi":"10.1109/ISSPIT.2008.4775653","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775653","url":null,"abstract":"In this paper, we introduce a new field of systems applications, that of Computer-based Systems in Society (CbSyS). In this context, factors as topologies & architectures, sensor grids & networks, information processing etc., are combined in order to solve social problems as for instance to assist handicaps. As an introductory paradigm we develop a sensor-based system designed for the assistance of blinds, entitled B-light. This is a navigation system, object-oriented, sensor-based, which enables embedded configuration as well as networking perspective. The overall system can be composed by a multifaceted assembly of components of software and hardware. We cite herein the generic context of implementation. The analysis and presentation is vertical, beginning from the theoretical grounding of the application framework and reaching the representative implementation of an ad-hoc system. Elements of embedded systems, of sensor networks, of signal, image & information processing can be combined into any specific implementation. The anticipated benefits of the herein presented system, as well as of the general framework of CbSyS are vital since they offer solutions and improvements in critical problems in Society.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130811749","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775682
A. Ouanane, A. Serir
In the present paper, a concept of compression using block ridgelet transform is introduced. This kind of analysis/synthesis fingerprint representation takes the form of basis elements which exhibit very high directional sensitivity and are highly anisotropic. This transform tailored for fingerprint, associated to a quantized global orientation flow provides a suit representation of the oriented ridges structure. The design and implementation of ridgelet compression scheme are discussed. In order to evaluate the performance of the algorithm, FCV2002, FCV2004 and NIST fingerprint databases have been considered. The results show that this method has a serious potential in fingerprint compression.
{"title":"Fingerprint Compression by Ridgelet Transform","authors":"A. Ouanane, A. Serir","doi":"10.1109/ISSPIT.2008.4775682","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775682","url":null,"abstract":"In the present paper, a concept of compression using block ridgelet transform is introduced. This kind of analysis/synthesis fingerprint representation takes the form of basis elements which exhibit very high directional sensitivity and are highly anisotropic. This transform tailored for fingerprint, associated to a quantized global orientation flow provides a suit representation of the oriented ridges structure. The design and implementation of ridgelet compression scheme are discussed. In order to evaluate the performance of the algorithm, FCV2002, FCV2004 and NIST fingerprint databases have been considered. The results show that this method has a serious potential in fingerprint compression.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131197108","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}
Pub Date : 2008-12-01DOI: 10.1109/ISSPIT.2008.4775711
T. Taniguchi, N. Bin Ramli, Y. Karasawa
This paper presents a maximal ratio combining (MRC) subband adaptive array using decision feedback approach. The subband adaptive array could extend the MRC scheme for frequency flat environments to be used in frequency selective channels, but the nonuniqueness of subband weights with respect to their phase rotation disturbs the efficient synthesis of output signal through the inverse DFT (discrete Fourier transform). Our method adopts two-step approach to solve this problem: In the first step, we use simple phase adjustment and derive hard-decision temporary output. Then in the second step, it is used as a training sequence to determine optimum phase compensation. Though this idea seems very simple, the proposed scheme significantly improves the performance of MRC based adaptive array and it is verified through computer simulations together with some features.
{"title":"Maximal Ratio Combining Subband Adaptive Array Using Decision Feedback Approach","authors":"T. Taniguchi, N. Bin Ramli, Y. Karasawa","doi":"10.1109/ISSPIT.2008.4775711","DOIUrl":"https://doi.org/10.1109/ISSPIT.2008.4775711","url":null,"abstract":"This paper presents a maximal ratio combining (MRC) subband adaptive array using decision feedback approach. The subband adaptive array could extend the MRC scheme for frequency flat environments to be used in frequency selective channels, but the nonuniqueness of subband weights with respect to their phase rotation disturbs the efficient synthesis of output signal through the inverse DFT (discrete Fourier transform). Our method adopts two-step approach to solve this problem: In the first step, we use simple phase adjustment and derive hard-decision temporary output. Then in the second step, it is used as a training sequence to determine optimum phase compensation. Though this idea seems very simple, the proposed scheme significantly improves the performance of MRC based adaptive array and it is verified through computer simulations together with some features.","PeriodicalId":213756,"journal":{"name":"2008 IEEE International Symposium on Signal Processing and Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127358599","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
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：