Pub Date : 2011-03-24DOI: 10.1109/ICCSP.2011.5739313
J. Jacob, A. Panicker, J. Mathew, A. P. Vinod
Motivated by the problem of multiple unlicensed cognitive radio users seek to access unused frequency channels licensed to the primary users in a wireless communication scenario, this paper presents a simulation environment that is able to simulate various effects of radio wave propagation and shadow fading in a software model. A cognitive radio designer's intent, knowledge about the critical issues and trade-offs underlying in a particular design are implicit in the simulations set up. However, this knowledge is tightly conjoined with specific features and a thorough simulation analysis is essential. Towards this, an algorithm was developed for performing this distributed sensing method between neighboring terminals in a network. VHF TV Broadcast FM Broadcast and GSM systems were investigated as possible candidates of primary users. It was found that a high degree of detection probability could be obtained for the TV and FM broadcast systems than for GSM systems under the same environmental parameters, largely due to the higher transmit powers involved in broadcast networks. The probability of false detection cannot be completely negated without risking an increase in the probability of non-detection of a present primary system. Hence a trade-off can be shown to exist between these two probabilities. It can be concluded that minimizing the possibility of interference to primary users should take priority in this scenario.
{"title":"Exploration of a distributed approach for simulating spectrum sensing in cognitive radio","authors":"J. Jacob, A. Panicker, J. Mathew, A. P. Vinod","doi":"10.1109/ICCSP.2011.5739313","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739313","url":null,"abstract":"Motivated by the problem of multiple unlicensed cognitive radio users seek to access unused frequency channels licensed to the primary users in a wireless communication scenario, this paper presents a simulation environment that is able to simulate various effects of radio wave propagation and shadow fading in a software model. A cognitive radio designer's intent, knowledge about the critical issues and trade-offs underlying in a particular design are implicit in the simulations set up. However, this knowledge is tightly conjoined with specific features and a thorough simulation analysis is essential. Towards this, an algorithm was developed for performing this distributed sensing method between neighboring terminals in a network. VHF TV Broadcast FM Broadcast and GSM systems were investigated as possible candidates of primary users. It was found that a high degree of detection probability could be obtained for the TV and FM broadcast systems than for GSM systems under the same environmental parameters, largely due to the higher transmit powers involved in broadcast networks. The probability of false detection cannot be completely negated without risking an increase in the probability of non-detection of a present primary system. Hence a trade-off can be shown to exist between these two probabilities. It can be concluded that minimizing the possibility of interference to primary users should take priority in this scenario.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116642159","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739388
V. Hari, V. P. Jagathy Raj, R. Gopikakumari
Modeling nonlinear systems using Volterra series is a century old method but practical realizations were hampered by inadequate hardware to handle the increased computational complexity stemming from its use. But interest is renewed recently, in designing and implementing filters which can model much of the polynomial nonlinearities inherent in practical systems. The key advantage in resorting to Volterra power series for this purpose is that nonlinear filters so designed can be made to work in parallel with the existing LTI systems, yielding improved performance. This paper describes the inclusion of a quadratic predictor (with nonlinearity order 2) with a linear predictor in an analog source coding system. Analog coding schemes generally ignore the source generation mechanisms but focuses on high fidelity reconstruction at the receiver. The widely used method of differential pulse code modulation (DPCM) for speech transmission uses a linear predictor to estimate the next possible value of the input speech signal. But this linear system do not account for the inherent nonlinearities in speech signals arising out of multiple reflections in the vocal tract. So a quadratic predictor is designed and implemented in parallel with the linear predictor to yield improved mean square error performance. The augmented speech coder is tested on speech signals transmitted over an additive white gaussian noise (AWGN) channel.
{"title":"Quadratic predictor based differential encoding and decoding of speech signals","authors":"V. Hari, V. P. Jagathy Raj, R. Gopikakumari","doi":"10.1109/ICCSP.2011.5739388","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739388","url":null,"abstract":"Modeling nonlinear systems using Volterra series is a century old method but practical realizations were hampered by inadequate hardware to handle the increased computational complexity stemming from its use. But interest is renewed recently, in designing and implementing filters which can model much of the polynomial nonlinearities inherent in practical systems. The key advantage in resorting to Volterra power series for this purpose is that nonlinear filters so designed can be made to work in parallel with the existing LTI systems, yielding improved performance. This paper describes the inclusion of a quadratic predictor (with nonlinearity order 2) with a linear predictor in an analog source coding system. Analog coding schemes generally ignore the source generation mechanisms but focuses on high fidelity reconstruction at the receiver. The widely used method of differential pulse code modulation (DPCM) for speech transmission uses a linear predictor to estimate the next possible value of the input speech signal. But this linear system do not account for the inherent nonlinearities in speech signals arising out of multiple reflections in the vocal tract. So a quadratic predictor is designed and implemented in parallel with the linear predictor to yield improved mean square error performance. The augmented speech coder is tested on speech signals transmitted over an additive white gaussian noise (AWGN) channel.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117109118","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739377
G. R. Reddy, K. Ramudu, Syed Zaheeruddin, R. Rao
In this paper, kernel fuzzy c-means (KFCM) was used to generate an initial contour curve which overcomes leaking at the boundary during the curve propagation. Firstly, KFCM algorithm computes the fuzzy membership values for each pixel. On the basis of KFCM the edge indicator function was redefined. Using the edge indicator function the segmentation of medical images which are added with salt and pepper noise was performed to extract the regions of interest for further processing. The results of the above process of segmentation showed a considerable improvement in the evolution of the level set function.
{"title":"Image segmentation using kernel fuzzy c-means clustering on level set method on noisy images","authors":"G. R. Reddy, K. Ramudu, Syed Zaheeruddin, R. Rao","doi":"10.1109/ICCSP.2011.5739377","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739377","url":null,"abstract":"In this paper, kernel fuzzy c-means (KFCM) was used to generate an initial contour curve which overcomes leaking at the boundary during the curve propagation. Firstly, KFCM algorithm computes the fuzzy membership values for each pixel. On the basis of KFCM the edge indicator function was redefined. Using the edge indicator function the segmentation of medical images which are added with salt and pepper noise was performed to extract the regions of interest for further processing. The results of the above process of segmentation showed a considerable improvement in the evolution of the level set function.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124979044","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739372
S. Prakash, I. Mcloughlin
The performance of an adaptive modulation system in Rayleigh fading channels exploiting spatial diversity through transmit antenna selection is analysed for the case of delay constrained networks. The system combines maximal ratio combining at the receiver and a transmit antenna selection system which switches between available antennas and modulation schemes at the transmitter. In a practical system, a delay between the channel being sampled at the receiver and acted upon by the transmitter will tend to degrade system performance. In this paper, a channel prediction scheme is employed at the receiver to provide estimates of future best transmission states, which includes selecting the best transmission antenna as well as the best supported M-QAM modulation scheme. The Shannon capacity for optimal rate and constant power is derived and presented, and used as a benchmark to evaluate the spectral efficiency of the discrete rate system optimised for instantaneous BER (bit error rate) and constant power constraint.
{"title":"Analysis of adaptive modulation with antenna selection under channel prediction errors","authors":"S. Prakash, I. Mcloughlin","doi":"10.1109/ICCSP.2011.5739372","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739372","url":null,"abstract":"The performance of an adaptive modulation system in Rayleigh fading channels exploiting spatial diversity through transmit antenna selection is analysed for the case of delay constrained networks. The system combines maximal ratio combining at the receiver and a transmit antenna selection system which switches between available antennas and modulation schemes at the transmitter. In a practical system, a delay between the channel being sampled at the receiver and acted upon by the transmitter will tend to degrade system performance. In this paper, a channel prediction scheme is employed at the receiver to provide estimates of future best transmission states, which includes selecting the best transmission antenna as well as the best supported M-QAM modulation scheme. The Shannon capacity for optimal rate and constant power is derived and presented, and used as a benchmark to evaluate the spectral efficiency of the discrete rate system optimised for instantaneous BER (bit error rate) and constant power constraint.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129716105","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739406
T. Prashanth, Radhika Venugopalan
Raga refers to melodic modes used in Indian Classical Music. It's a series of five or more musical notes upon which a melody is made. Note identification forms the basis for Raga Identification in Music. Characterisation of a note in Carnatic Music is challenging due to the extensive use of Gamakas. In this paper, we propose a System that takes a wav file as input, analyses the frequency characteristics and performs note mapping. The prominent notes in the Raga are selected by a Statistical T Test based on the duration of occurrence of a note. A Test data of around 15 raga alapanas was used. The renditions ranged from 3 – 8 minute clips of various artistes, both male and female. The System performs with an accuracy of 90%.
{"title":"Note identification in Carnatic Music from Frequency Spectrum","authors":"T. Prashanth, Radhika Venugopalan","doi":"10.1109/ICCSP.2011.5739406","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739406","url":null,"abstract":"Raga refers to melodic modes used in Indian Classical Music. It's a series of five or more musical notes upon which a melody is made. Note identification forms the basis for Raga Identification in Music. Characterisation of a note in Carnatic Music is challenging due to the extensive use of Gamakas. In this paper, we propose a System that takes a wav file as input, analyses the frequency characteristics and performs note mapping. The prominent notes in the Raga are selected by a Statistical T Test based on the duration of occurrence of a note. A Test data of around 15 raga alapanas was used. The renditions ranged from 3 – 8 minute clips of various artistes, both male and female. The System performs with an accuracy of 90%.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116338399","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739341
Vivek Dhoot, Sanjeev Gupta
In this paper, return loss of a newly proposed cantor based multifractal multiband monopole antenna is analyzed using two numerical methods for validation. The Finite Integration Technique (FIT) and the Finite Difference Time Domain Method (FDTD) are used for analysis. The proposed antenna has multiband characteristics covering several wireless applications in Ultra Wideband (UWB) including WLAN 2 .4 GHz applications. A commercially available simulator CST (Based on FIT) and a MATLAB program based on FDTD method (Written as a simulator) are utilized for observing return loss of the proposed antenna. Then a resonance comparision is done which shows great analogy i.e. validates the result of one numerical method against another one.
{"title":"Return loss validation of a novel cantor based antenna using FIT and FDTD","authors":"Vivek Dhoot, Sanjeev Gupta","doi":"10.1109/ICCSP.2011.5739341","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739341","url":null,"abstract":"In this paper, return loss of a newly proposed cantor based multifractal multiband monopole antenna is analyzed using two numerical methods for validation. The Finite Integration Technique (FIT) and the Finite Difference Time Domain Method (FDTD) are used for analysis. The proposed antenna has multiband characteristics covering several wireless applications in Ultra Wideband (UWB) including WLAN 2 .4 GHz applications. A commercially available simulator CST (Based on FIT) and a MATLAB program based on FDTD method (Written as a simulator) are utilized for observing return loss of the proposed antenna. Then a resonance comparision is done which shows great analogy i.e. validates the result of one numerical method against another one.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115973874","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739359
K. V. Madhav, M. R. Ram, E. Krishna, K. Nagarjuna Reddy, K. Reddy
In high risk situations such as cardiac arrhythmias, ambulatory monitoring, stress tests, sleep disorder investigations and post-operative hypoxemia situations, monitoring of respiratory activity would be mandatory. Electrocardiogram (ECG), blood pressure (BP) and photoplethysmographic (PPG) signals can be used for extraction of respiratory activity, and will eventually eliminate the use of additional respiratory sensor. Using a simple and standard non-parametric mathematical technique, Principal Component Analysis (PCA), the respiratory related information is extracted from complex data sets such as PPG and BP signals. The respiratory induced variations (RIV) of PPG and BP signals are described by coefficients of computed principal components. Singular value ratio (SVR) trend is used to find the periodicity, which is one of the crucial parameters in forming the data sets for PCA. Test results on MIMIC data base clearly indicated a strong correlation between the extracted and actual respiratory signals. Statistical measures in both time and frequency domains such as Relative Correlation Coefficient (RCC) and Magnitude Squared Coherence (MSC) respectively and Accuracy Rate (AR) are calculated to demonstrate the fact, that respiratory signal is present in the form of first principal components.
{"title":"Extraction of respiratory activity from PPG and BP signals using Principal Component Analysis","authors":"K. V. Madhav, M. R. Ram, E. Krishna, K. Nagarjuna Reddy, K. Reddy","doi":"10.1109/ICCSP.2011.5739359","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739359","url":null,"abstract":"In high risk situations such as cardiac arrhythmias, ambulatory monitoring, stress tests, sleep disorder investigations and post-operative hypoxemia situations, monitoring of respiratory activity would be mandatory. Electrocardiogram (ECG), blood pressure (BP) and photoplethysmographic (PPG) signals can be used for extraction of respiratory activity, and will eventually eliminate the use of additional respiratory sensor. Using a simple and standard non-parametric mathematical technique, Principal Component Analysis (PCA), the respiratory related information is extracted from complex data sets such as PPG and BP signals. The respiratory induced variations (RIV) of PPG and BP signals are described by coefficients of computed principal components. Singular value ratio (SVR) trend is used to find the periodicity, which is one of the crucial parameters in forming the data sets for PCA. Test results on MIMIC data base clearly indicated a strong correlation between the extracted and actual respiratory signals. Statistical measures in both time and frequency domains such as Relative Correlation Coefficient (RCC) and Magnitude Squared Coherence (MSC) respectively and Accuracy Rate (AR) are calculated to demonstrate the fact, that respiratory signal is present in the form of first principal components.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131192956","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739322
K. Kumar, N. Gunasekaran
This paper proposes a configuration of a new wide band microstrip patch antenna in wireless communications devices such as base stations. A New Novel wide band Π shaped microstrip patch antenna is presented with a wide impedance bandwidth of 67.8% centered at 5.5 GHz is achieved. The antenna structure is designed and simulated. Simulated results for the antenna parameters such as return loss, impedance bandwidth and the surface current distributions are discussed. The radiation patterns are obtained at 4.5 GHz, 5.5 GHz and 7.5 GHz. Due to three resonant slots on the patch it gives more bandwidth. This proposed Antenna is simple in structure with coaxial feed can well meet the wireless communication. The substrates are microwave substrate and foam material and the patch is placed on a thin dielectric layer, which is placed over the foam substrate. The simulated front to back (F/B) ratio is better than 20 dB throughout the frequency band)
{"title":"A Novel wide band planar Π shaped base station antenna","authors":"K. Kumar, N. Gunasekaran","doi":"10.1109/ICCSP.2011.5739322","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739322","url":null,"abstract":"This paper proposes a configuration of a new wide band microstrip patch antenna in wireless communications devices such as base stations. A New Novel wide band Π shaped microstrip patch antenna is presented with a wide impedance bandwidth of 67.8% centered at 5.5 GHz is achieved. The antenna structure is designed and simulated. Simulated results for the antenna parameters such as return loss, impedance bandwidth and the surface current distributions are discussed. The radiation patterns are obtained at 4.5 GHz, 5.5 GHz and 7.5 GHz. Due to three resonant slots on the patch it gives more bandwidth. This proposed Antenna is simple in structure with coaxial feed can well meet the wireless communication. The substrates are microwave substrate and foam material and the patch is placed on a thin dielectric layer, which is placed over the foam substrate. The simulated front to back (F/B) ratio is better than 20 dB throughout the frequency band)","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"2007 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127310631","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739302
K.M Nitin Babu, K. K. Vinaymurthi
This paper demonstrates an economical implementation of Gaussian Minimum shift keying (GMSK) modulator for Global System for Mobile communication (GSM) system using the basics of direct waveform synthesis. This method makes use of pre-calculated filter response of Gaussian filter for pulse shaping and Phase concatenation circuit for accumulation. Baseband in-phase and quadrature-phase component generation using quarter Sine or Cosine waveform LUT. (Further these signals are given for up-conversion.) Hardware realization is done using VHDL; circuits are synthesized. Prototyped our design in Altera Cyclone-3 FPGA (Field Programmable Gate Array), verified using R&S (Rhode and Schwarz) Vector signal analyzer. The design and hardware implementation of this modulator was done for indigenous GSM BTS (Base transceiver station) project.
{"title":"GMSK modulator for GSM system, an economical implementation on FPGA","authors":"K.M Nitin Babu, K. K. Vinaymurthi","doi":"10.1109/ICCSP.2011.5739302","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739302","url":null,"abstract":"This paper demonstrates an economical implementation of Gaussian Minimum shift keying (GMSK) modulator for Global System for Mobile communication (GSM) system using the basics of direct waveform synthesis. This method makes use of pre-calculated filter response of Gaussian filter for pulse shaping and Phase concatenation circuit for accumulation. Baseband in-phase and quadrature-phase component generation using quarter Sine or Cosine waveform LUT. (Further these signals are given for up-conversion.) Hardware realization is done using VHDL; circuits are synthesized. Prototyped our design in Altera Cyclone-3 FPGA (Field Programmable Gate Array), verified using R&S (Rhode and Schwarz) Vector signal analyzer. The design and hardware implementation of this modulator was done for indigenous GSM BTS (Base transceiver station) project.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115484286","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 : 2011-03-24DOI: 10.1109/ICCSP.2011.5739357
H. Imtiaz, S. Fattah
A multi-resolution feature extraction algorithm for face recognition based on two-dimensional discrete wavelet transform (2D-DWT) is proposed in this paper, which exploits the local spatial variations in a face image effectively. Instead of considering the entire face image, an entropy-based local band selection criterion is developed, which selects high-informative horizontal bands from the face image for feature extraction. In order to capture the local spatial variations within these bands precisely, a histogram-based local dominant feature selection criterion is proposed. The proposed dominant wavelet coefficients, in terms of frequency of occurrence, corresponding to each local region residing inside those horizontal bands not only reduces the feature dimension drastically but also provides high within-class compactness and high between-class separability. Extensive experimentation is carried out upon standard face databases and in comparison to those obtained by some of the existing methods, a very high degree of recognition accuracy is achieved by the proposed method.
{"title":"A wavelet-domain local feature selection scheme for face recognition","authors":"H. Imtiaz, S. Fattah","doi":"10.1109/ICCSP.2011.5739357","DOIUrl":"https://doi.org/10.1109/ICCSP.2011.5739357","url":null,"abstract":"A multi-resolution feature extraction algorithm for face recognition based on two-dimensional discrete wavelet transform (2D-DWT) is proposed in this paper, which exploits the local spatial variations in a face image effectively. Instead of considering the entire face image, an entropy-based local band selection criterion is developed, which selects high-informative horizontal bands from the face image for feature extraction. In order to capture the local spatial variations within these bands precisely, a histogram-based local dominant feature selection criterion is proposed. The proposed dominant wavelet coefficients, in terms of frequency of occurrence, corresponding to each local region residing inside those horizontal bands not only reduces the feature dimension drastically but also provides high within-class compactness and high between-class separability. Extensive experimentation is carried out upon standard face databases and in comparison to those obtained by some of the existing methods, a very high degree of recognition accuracy is achieved by the proposed method.","PeriodicalId":408736,"journal":{"name":"2011 International Conference on Communications and Signal Processing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115717933","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：