Pub Date : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708039
A. Ali, V. Asirvadam, A. Malik
This work proposed a geometrical model based on multiple triangular features for the purpose of handling the challenge of scale variations that affect the process of face recognition especially in real time applications where the test images are usually taken in random scales that may not be of the same scale as the probe image. Geometrical approaches have proved to be robust to lighting and illumination variation. Furthermore geometrical methods in general do not hold computational complexity and have the benefit of faster processing time, which make them appropriate for real time applications. Fifteen triangle similarity measurement equations were derived and used to build a class of feature vectors for each subject. Ten images in ten different scales were taken for each subject for a total of fifty samples. Classification results show that the proposed model is promising in handling the challenge of scale variations.
{"title":"Scale- invariant face recognition using triangular geometrical model","authors":"A. Ali, V. Asirvadam, A. Malik","doi":"10.1109/ICSIPA.2013.6708039","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708039","url":null,"abstract":"This work proposed a geometrical model based on multiple triangular features for the purpose of handling the challenge of scale variations that affect the process of face recognition especially in real time applications where the test images are usually taken in random scales that may not be of the same scale as the probe image. Geometrical approaches have proved to be robust to lighting and illumination variation. Furthermore geometrical methods in general do not hold computational complexity and have the benefit of faster processing time, which make them appropriate for real time applications. Fifteen triangle similarity measurement equations were derived and used to build a class of feature vectors for each subject. Ten images in ten different scales were taken for each subject for a total of fifty samples. Classification results show that the proposed model is promising in handling the challenge of scale variations.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"506 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115337171","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708040
Housam Khalifa Bashier, L. S. Hoe, Pang Ying Han, L. Ping
Face recognitions systems suffer from the problem associated with illumination variation. Therefore, there's a need to address this problem. In this paper, we present a novel algorithm for illumination normalization call Local Trapezoid Feature LTF. The features are derived from the trapezoid rule and the experiments results on extended Yale face database demonstrated the effectiveness and the superiority of the algorithm. Furthermore, our algorithm doesn't require dimensionality reduction or feature extraction.
{"title":"A novel illumination normalization algorithm for face recognition","authors":"Housam Khalifa Bashier, L. S. Hoe, Pang Ying Han, L. Ping","doi":"10.1109/ICSIPA.2013.6708040","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708040","url":null,"abstract":"Face recognitions systems suffer from the problem associated with illumination variation. Therefore, there's a need to address this problem. In this paper, we present a novel algorithm for illumination normalization call Local Trapezoid Feature LTF. The features are derived from the trapezoid rule and the experiments results on extended Yale face database demonstrated the effectiveness and the superiority of the algorithm. Furthermore, our algorithm doesn't require dimensionality reduction or feature extraction.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124081729","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708008
E. A. Awalludin, M. S. Hitam, Z. Bachok, W. Yussof, Aidy Mohamed Shawal M. Muslim
This paper presents a new edge detection method to efficiently detect coral reefs edges. The new edge detection method is based on an anisotropic diffusion where it is used to produce minimum image noise disturbances without reducing the significant edge information and at the same time preserving salient edges. The proposed method has been compared with other established edge detection methods such as Sobel, Prewitt, Roberts, LoG and Canny edge detectors under various noisy environments. The coral reefs images obtained at 3 meters depth were used in this study. The performance of the proposed method is compared with other established methods using visual inspection as well as parametric measure, i.e. Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). The experimental results show that the proposed method outperformed other established edge detection methods in both aspects.
{"title":"Anisotropic diffusion based edge detector for detecting coral reefs edges","authors":"E. A. Awalludin, M. S. Hitam, Z. Bachok, W. Yussof, Aidy Mohamed Shawal M. Muslim","doi":"10.1109/ICSIPA.2013.6708008","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708008","url":null,"abstract":"This paper presents a new edge detection method to efficiently detect coral reefs edges. The new edge detection method is based on an anisotropic diffusion where it is used to produce minimum image noise disturbances without reducing the significant edge information and at the same time preserving salient edges. The proposed method has been compared with other established edge detection methods such as Sobel, Prewitt, Roberts, LoG and Canny edge detectors under various noisy environments. The coral reefs images obtained at 3 meters depth were used in this study. The performance of the proposed method is compared with other established methods using visual inspection as well as parametric measure, i.e. Mean Square Error (MSE) and Peak Signal-to-Noise Ratio (PSNR). The experimental results show that the proposed method outperformed other established edge detection methods in both aspects.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"30 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123990316","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708004
Olfa Ben Rhaiem, L. Chaari
The H.264/SVC was developed as an extension of H.264/AVC; the latest scalable H.264 codec (SVC) provides combined temporal, quality and spatial scalability. This paper provides theoretical concepts of these different scalability approaches and analysis of their performances when video are transmitted over IEEE 802.11e WLANs. In order to validate our works, we have used an NS2 simulator environment based on SVEF (Scalable Video-Streaming Evaluation Framework). We have suggested evaluating H.264/SVC video coding over wireless network architecture, specifically when DCF or EDCA access mechanisms are used. In our analysis we have focused on Spatial, Quality, and Temporal video scalability approaches. The obtained results show that temporal scalability clearly outperforms other scalability category.
{"title":"H.264/SVC scalability performance analysis","authors":"Olfa Ben Rhaiem, L. Chaari","doi":"10.1109/ICSIPA.2013.6708004","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708004","url":null,"abstract":"The H.264/SVC was developed as an extension of H.264/AVC; the latest scalable H.264 codec (SVC) provides combined temporal, quality and spatial scalability. This paper provides theoretical concepts of these different scalability approaches and analysis of their performances when video are transmitted over IEEE 802.11e WLANs. In order to validate our works, we have used an NS2 simulator environment based on SVEF (Scalable Video-Streaming Evaluation Framework). We have suggested evaluating H.264/SVC video coding over wireless network architecture, specifically when DCF or EDCA access mechanisms are used. In our analysis we have focused on Spatial, Quality, and Temporal video scalability approaches. The obtained results show that temporal scalability clearly outperforms other scalability category.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"90 1-2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114027404","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707972
S. Hussain, Sami M. Gorashi
Image denoising is an active area of research and probably one of the most studied problems in the image processing fields. In this paper we describe a new hybrid image denoising algorithm which combines Gaussian based neighborhood spatial filter with wavelet transform that based on neighborhood thresholding function which takes the correlation of the magnitude of the wavelet coefficient with its neighbors into consideration to decide whether the coefficient is noisy or noise free. Accordingly, noises are detected with the help of the surrounding information and are removed. Experimental results show that the proposed algorithm can effectively remove the image noises with less processing time as compared with the state-of-the-art denoising algorithm.
{"title":"Image denoising algorithm based on hybrid neighborhood filter","authors":"S. Hussain, Sami M. Gorashi","doi":"10.1109/ICSIPA.2013.6707972","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707972","url":null,"abstract":"Image denoising is an active area of research and probably one of the most studied problems in the image processing fields. In this paper we describe a new hybrid image denoising algorithm which combines Gaussian based neighborhood spatial filter with wavelet transform that based on neighborhood thresholding function which takes the correlation of the magnitude of the wavelet coefficient with its neighbors into consideration to decide whether the coefficient is noisy or noise free. Accordingly, noises are detected with the help of the surrounding information and are removed. Experimental results show that the proposed algorithm can effectively remove the image noises with less processing time as compared with the state-of-the-art denoising algorithm.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121781526","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707987
C. Sinkaram, V. Asirvadam, N. M. Nor
This paper presents a preliminary simulation study of Lithium-ion batteries. The dynamic model of Li-ion batteries was created and the model was validated with previous results for different temperatures. It found that the developed model produce the results acquired with previous results. The Li-ion battery characteristics were simulated as voltage profiles for two different condition of initial State of Charge (SOC) and for two different values of temperature. The usable operating time and the battery were found to vary with SOC initial and temperature. It is also found that the usable run time of the battery increases with increase in SOC initial and decrease in temperature. The Li-ion discharge battery model was simulated for the Hybrid electrical Vehicle (HEV). The simulation results give a framework of a nonlinear dynamic performance of the Li-ion battery pack for the electrical scooter.
{"title":"Capacity study of lithium ion battery for hybrid electrical vehicle (HEV) a simulation approach","authors":"C. Sinkaram, V. Asirvadam, N. M. Nor","doi":"10.1109/ICSIPA.2013.6707987","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707987","url":null,"abstract":"This paper presents a preliminary simulation study of Lithium-ion batteries. The dynamic model of Li-ion batteries was created and the model was validated with previous results for different temperatures. It found that the developed model produce the results acquired with previous results. The Li-ion battery characteristics were simulated as voltage profiles for two different condition of initial State of Charge (SOC) and for two different values of temperature. The usable operating time and the battery were found to vary with SOC initial and temperature. It is also found that the usable run time of the battery increases with increase in SOC initial and decrease in temperature. The Li-ion discharge battery model was simulated for the Hybrid electrical Vehicle (HEV). The simulation results give a framework of a nonlinear dynamic performance of the Li-ion battery pack for the electrical scooter.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129203533","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708044
W. Lu, Bangning Zhang
A new approach is proposed for single channel blind signal separation(SCBSS) problem of communication signal and time-varying amplitude LFM interference based on Metropolis-Hastings mutation particle swarm optimized particle filtering (MHMPSOPF). The proposed algorithm aims to obtain the maximum a posterior (MAP) estimate of communication code and the unknown parameters using particle filtering by establishing the state space model for the interfered signal, Specially, in order to overcome the sample impoverishment problem, particle swarm optimized is introduced to the re-sampling process in particle filtering(PF). In such a way, the number of needed particles is reduced and the variety of particles is retained during the sequential estimation process, moreover, the proposed algorithm has superior performance under time-varying amplitude LFM interference. Simulation results show that the method is effective to separate communication signal and interference when the ISR is less than 20dB and SNR is more than 14dB.
{"title":"Single channel time-varying amplitude LFM interference blind separation using MHMPSO particle filtering","authors":"W. Lu, Bangning Zhang","doi":"10.1109/ICSIPA.2013.6708044","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708044","url":null,"abstract":"A new approach is proposed for single channel blind signal separation(SCBSS) problem of communication signal and time-varying amplitude LFM interference based on Metropolis-Hastings mutation particle swarm optimized particle filtering (MHMPSOPF). The proposed algorithm aims to obtain the maximum a posterior (MAP) estimate of communication code and the unknown parameters using particle filtering by establishing the state space model for the interfered signal, Specially, in order to overcome the sample impoverishment problem, particle swarm optimized is introduced to the re-sampling process in particle filtering(PF). In such a way, the number of needed particles is reduced and the variety of particles is retained during the sequential estimation process, moreover, the proposed algorithm has superior performance under time-varying amplitude LFM interference. Simulation results show that the method is effective to separate communication signal and interference when the ISR is less than 20dB and SNR is more than 14dB.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129207943","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6708028
K. Kadir, Hao Gao, A. Payne, J. Soraghan, C. Berry
Evaluating salvageable myocardial after myocardial infarction (MI) is an important prognosis in the follow up study of MI. Since the extent of myocardial edema delineates the ischemic area-at-risk (AAR) after MI the AAR can be used to estimate the amount of salvageable myocardial post-MI and therefore has potential clinical utility in the management of acute MI patients. Two methods for the segmentation and quantification of edema from T2 weighted MRI data have been presented. The methods presented in this paper are Two Statistical Mixture Model and Fuzzy C-means. Quantitative evaluations of segmentation accuracy for the two algorithms were performed by comparing to manual segmentation on real T2 weighted CMR data collected from Golden Jubilee National Hospital, Glasgow for 16 adult subjects.
{"title":"Two Statistical Mixture Model vs. Fuzzy C-Means: In the application of edema segmentation","authors":"K. Kadir, Hao Gao, A. Payne, J. Soraghan, C. Berry","doi":"10.1109/ICSIPA.2013.6708028","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6708028","url":null,"abstract":"Evaluating salvageable myocardial after myocardial infarction (MI) is an important prognosis in the follow up study of MI. Since the extent of myocardial edema delineates the ischemic area-at-risk (AAR) after MI the AAR can be used to estimate the amount of salvageable myocardial post-MI and therefore has potential clinical utility in the management of acute MI patients. Two methods for the segmentation and quantification of edema from T2 weighted MRI data have been presented. The methods presented in this paper are Two Statistical Mixture Model and Fuzzy C-means. Quantitative evaluations of segmentation accuracy for the two algorithms were performed by comparing to manual segmentation on real T2 weighted CMR data collected from Golden Jubilee National Hospital, Glasgow for 16 adult subjects.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133435111","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707988
V. K. Pamula, S. R. Vempati, H. Khan, A. K. Tipparti
This paper presents the performance analysis of three linear diversity combining schemes in terms of outage probability (OP), level crossing rate (LCR) and average outage duration (AOD) over Nakagami-0.5 fading channels. Closed-form expressions for OP, LCR and AOD are derived for selection combining (SC), equal gain combining (EGC) and maximal-ratio combining (MRC) receive diversity schemes. The expressions derived are numerically evaluated to study the effect of diversity order and exponentially decaying multipath intensity profile (MIP) on the system performance.
{"title":"Performance analysis of linear diversity combining schemes on Nakagami-0.5 fading channels","authors":"V. K. Pamula, S. R. Vempati, H. Khan, A. K. Tipparti","doi":"10.1109/ICSIPA.2013.6707988","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707988","url":null,"abstract":"This paper presents the performance analysis of three linear diversity combining schemes in terms of outage probability (OP), level crossing rate (LCR) and average outage duration (AOD) over Nakagami-0.5 fading channels. Closed-form expressions for OP, LCR and AOD are derived for selection combining (SC), equal gain combining (EGC) and maximal-ratio combining (MRC) receive diversity schemes. The expressions derived are numerically evaluated to study the effect of diversity order and exponentially decaying multipath intensity profile (MIP) on the system performance.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123976918","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 : 2013-10-01DOI: 10.1109/ICSIPA.2013.6707994
Y. F. A. Gaus, F. Wong, K. Teo, R. Chin, R. R. Porle, L. P. Yi, A. Chekima
This paper presents a method of gesture recognition using Hidden Markov Model (HMM). Gesture itself is based on the movement of each right hand (RH) and left hand (LH), which represents the word intended by the signer. The feature vector selected, gesture path, hand distance and hand orientations are obtained from RH and LH then trained using HMM to produce the respective gesture class. While training, in handling HMM state, we introduce fixed state and variable state, where in fixed state, the numbers of state is generally fixed for all gestures and while the number of state in variable state is determined by the movement of the gesture. It was found that fixed state gave the highest rate of recognition achieving 83.1%.
{"title":"Comparison study of Hidden Markov Model gesture recognition using fixed state and variable state","authors":"Y. F. A. Gaus, F. Wong, K. Teo, R. Chin, R. R. Porle, L. P. Yi, A. Chekima","doi":"10.1109/ICSIPA.2013.6707994","DOIUrl":"https://doi.org/10.1109/ICSIPA.2013.6707994","url":null,"abstract":"This paper presents a method of gesture recognition using Hidden Markov Model (HMM). Gesture itself is based on the movement of each right hand (RH) and left hand (LH), which represents the word intended by the signer. The feature vector selected, gesture path, hand distance and hand orientations are obtained from RH and LH then trained using HMM to produce the respective gesture class. While training, in handling HMM state, we introduce fixed state and variable state, where in fixed state, the numbers of state is generally fixed for all gestures and while the number of state in variable state is determined by the movement of the gesture. It was found that fixed state gave the highest rate of recognition achieving 83.1%.","PeriodicalId":440373,"journal":{"name":"2013 IEEE International Conference on Signal and Image Processing Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126080595","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：