Pub Date : 2017-05-01DOI: 10.1109/SSPS.2017.8071623
Srishti Singh, Amrit Paul, M. Arun
A Compute Unified Device Architecture (CUDA) implementation of Deep Convolutional Neural Network (DCNN) for a digit recognition system is proposed to reduce the computation time of ANN and achieve high accuracy. A neural network with three layers of convolutions and two fully connected layers is developed by building input, hidden and output neurons to achieve an improved accuracy. The network is parallelized using a dedicated GPU on CUDA platform using Tensor flow library. A comparative analysis of accuracy and computation time is performed for sequential and parallel execution of the network on dual core (4 logical processors) CPU, octa core (16 logical processors) only CPU and octa core (16 logical processors) CPU with GPU systems. MNIST (Modified National Institute of Standards and Technology) and EMNIST (Extended MNIST) database are used for both training and testing. MNIST has 55000 training sets, 10000 testing sets and 5000 validation sets. EMNIST consists of 235000 training, 40000 testing and 5000 validation sets. The network designed requires high computation and hence parallelizing it shows significant improvement in execution time.
提出了一种基于CUDA的深度卷积神经网络(DCNN)的数字识别方法，以减少人工神经网络的计算时间，达到较高的识别精度。通过构建输入、隐藏和输出神经元，构建了具有三层卷积和两层全连接的神经网络，以提高准确率。该网络使用CUDA平台上的专用GPU使用Tensor flow库进行并行化。在双核(4个逻辑处理器)CPU、单八核(16个逻辑处理器)CPU和带GPU系统的八核(16个逻辑处理器)CPU上对网络的顺序和并行执行进行了精度和计算时间的比较分析。MNIST (Modified National Institute of Standards and Technology)和EMNIST (Extended MNIST)数据库用于培训和测试。MNIST有55000个训练集，10000个测试集和5000个验证集。EMNIST由235000个训练集、40000个测试集和5000个验证集组成。设计的网络需要高计算量，因此并行化在执行时间上有显著改善。
{"title":"Parallelization of digit recognition system using Deep Convolutional Neural Network on CUDA","authors":"Srishti Singh, Amrit Paul, M. Arun","doi":"10.1109/SSPS.2017.8071623","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071623","url":null,"abstract":"A Compute Unified Device Architecture (CUDA) implementation of Deep Convolutional Neural Network (DCNN) for a digit recognition system is proposed to reduce the computation time of ANN and achieve high accuracy. A neural network with three layers of convolutions and two fully connected layers is developed by building input, hidden and output neurons to achieve an improved accuracy. The network is parallelized using a dedicated GPU on CUDA platform using Tensor flow library. A comparative analysis of accuracy and computation time is performed for sequential and parallel execution of the network on dual core (4 logical processors) CPU, octa core (16 logical processors) only CPU and octa core (16 logical processors) CPU with GPU systems. MNIST (Modified National Institute of Standards and Technology) and EMNIST (Extended MNIST) database are used for both training and testing. MNIST has 55000 training sets, 10000 testing sets and 5000 validation sets. EMNIST consists of 235000 training, 40000 testing and 5000 validation sets. The network designed requires high computation and hence parallelizing it shows significant improvement in execution time.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126568976","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071635
R. Ranihemamalini, S. Ashwitha, M. Aarthy, A. Abhineyaa, Aditii
PLC (Power line communication) is a technology that provides high speed communication of voice and data and its is very cost effective method. It has been successfully implemented in many applications in real time. In this project one such application is used to digitize an institution by replacing circulars or notice boards by digital notice boards. Frequent updating is easy with a centralized systems. Data's are sent through existing power line to a particular power line node or various nodes. The information is obtained from server and it is displayed using LCD at the reception. when a message is received it is intimated to students using a voice board. A personal Computer, power line modem, voice board and an LCD display are used to design digital notice board via power line.
{"title":"Digital notice board implementation via power line communication","authors":"R. Ranihemamalini, S. Ashwitha, M. Aarthy, A. Abhineyaa, Aditii","doi":"10.1109/SSPS.2017.8071635","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071635","url":null,"abstract":"PLC (Power line communication) is a technology that provides high speed communication of voice and data and its is very cost effective method. It has been successfully implemented in many applications in real time. In this project one such application is used to digitize an institution by replacing circulars or notice boards by digital notice boards. Frequent updating is easy with a centralized systems. Data's are sent through existing power line to a particular power line node or various nodes. The information is obtained from server and it is displayed using LCD at the reception. when a message is received it is intimated to students using a voice board. A personal Computer, power line modem, voice board and an LCD display are used to design digital notice board via power line.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133971229","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071639
Kamyar Nemati, Kannan Ramakrishnan
A single cycle of an ECG signal is composed of multiple segments. The QRS segment is considered as the most important segment for accurate diagnosis in many heart related disorders and this segment should be preserved against any major signal distortion during the process of compression. In this paper, a novel hybrid ECG signal data compression technique is proposed, in which lossless compression is applied on QRS segments and lossy compression is applied on other segments, without actually implementing any wave-recognition algorithm. Experimental results have shown that with the optimal selection of threshold and aperture size, it is possible to preserve the quality of QRS segments for enhancing the diagnostic capability with the reconstructed signal while achieving higher compression efficiency at the same time.
{"title":"Hybrid lossless and lossy compression technique for ECG signals","authors":"Kamyar Nemati, Kannan Ramakrishnan","doi":"10.1109/SSPS.2017.8071639","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071639","url":null,"abstract":"A single cycle of an ECG signal is composed of multiple segments. The QRS segment is considered as the most important segment for accurate diagnosis in many heart related disorders and this segment should be preserved against any major signal distortion during the process of compression. In this paper, a novel hybrid ECG signal data compression technique is proposed, in which lossless compression is applied on QRS segments and lossy compression is applied on other segments, without actually implementing any wave-recognition algorithm. Experimental results have shown that with the optimal selection of threshold and aperture size, it is possible to preserve the quality of QRS segments for enhancing the diagnostic capability with the reconstructed signal while achieving higher compression efficiency at the same time.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115724562","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071626
R. P. Iyer, Archanaa Raveendran, S. Bhuvana, R. Kavitha
This article presents an overview of hyperspectral image analysis and processing techniques based on remote sensing. Image analysis methods will be explained in detail. A general framework is presented for working with hyperspectral imagery, including removal of atmospheric effects. Due to large dimensionality of the feature space, hyperspectral data poses a challenge to image interpretation in the following ways: 1) need of calibration of data2) redundancy in information and 3) high volume data. Hence, a brief discussion on dimensionality reduction will also be presented in this review.
{"title":"Hyperspectral image analysis techniques on remote sensing","authors":"R. P. Iyer, Archanaa Raveendran, S. Bhuvana, R. Kavitha","doi":"10.1109/SSPS.2017.8071626","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071626","url":null,"abstract":"This article presents an overview of hyperspectral image analysis and processing techniques based on remote sensing. Image analysis methods will be explained in detail. A general framework is presented for working with hyperspectral imagery, including removal of atmospheric effects. Due to large dimensionality of the feature space, hyperspectral data poses a challenge to image interpretation in the following ways: 1) need of calibration of data2) redundancy in information and 3) high volume data. Hence, a brief discussion on dimensionality reduction will also be presented in this review.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117311841","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071562
J. Kaur, S. Gaikwad
In the current scenario, there exist huge amount of audio files with mixed sound sources. These mixed sounds consist of different frequencies viz. high frequency (string instruments like guitar), low frequencies (base instrument like drums, tabla) and intermediate human speech frequency. All these frequencies makes a music signal which is required for pleasure. The music creation is achieved by mixing of multiple signals using mixer. Our aim is to reverse the process of mixing and extract an audio signals so that they can be used in applications like karaoke, remix, instrumental music, audio restoration etc. One of the major application is noise cancellation and music transcription. In this paper we have demonstrated separation of single channel separation from mixed audio signal with the accuracy of 93% and average extraction speed of 20 seconds per minute of audio.
{"title":"Extraction of single channel from mixed audio sample using adaptive factorization","authors":"J. Kaur, S. Gaikwad","doi":"10.1109/SSPS.2017.8071562","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071562","url":null,"abstract":"In the current scenario, there exist huge amount of audio files with mixed sound sources. These mixed sounds consist of different frequencies viz. high frequency (string instruments like guitar), low frequencies (base instrument like drums, tabla) and intermediate human speech frequency. All these frequencies makes a music signal which is required for pleasure. The music creation is achieved by mixing of multiple signals using mixer. Our aim is to reverse the process of mixing and extract an audio signals so that they can be used in applications like karaoke, remix, instrumental music, audio restoration etc. One of the major application is noise cancellation and music transcription. In this paper we have demonstrated separation of single channel separation from mixed audio signal with the accuracy of 93% and average extraction speed of 20 seconds per minute of audio.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116132197","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071610
Ravindra Sonavane, Poonam Sonar, Surendra Sutar
A proper and accurate classification technique with detection of brain tumor has been presented and proposed. The system uses neural network based approach for brain and breast image classification. Now a day's Magnetic resonance imaging (MRI technique is used for early detection of any abnormal changes in tissues and organs. The projected method is evaluated on two distinct databases i.e. Clinical database is database of brain MRI and one more Standard Digital Database for Screening Mammography (DDSM). The proposed system consists of Preprocessing using image normalization, morphological operations using erosion, dilation and Anisotropic Diffusion Filter (ADF), Extraction of texture feature using gray level co-occurrence matrix (GLCM) and classification into normal and abnormal using machine learning algorithm and quantization techniques i.e. LVQ. The proposed system achieved the accuracy of 68.85% for DDSM mammography database and 79.35% on clinical brain MRI database.
{"title":"Classification of MRI brain tumor and mammogram images using learning vector quantization neural network","authors":"Ravindra Sonavane, Poonam Sonar, Surendra Sutar","doi":"10.1109/SSPS.2017.8071610","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071610","url":null,"abstract":"A proper and accurate classification technique with detection of brain tumor has been presented and proposed. The system uses neural network based approach for brain and breast image classification. Now a day's Magnetic resonance imaging (MRI technique is used for early detection of any abnormal changes in tissues and organs. The projected method is evaluated on two distinct databases i.e. Clinical database is database of brain MRI and one more Standard Digital Database for Screening Mammography (DDSM). The proposed system consists of Preprocessing using image normalization, morphological operations using erosion, dilation and Anisotropic Diffusion Filter (ADF), Extraction of texture feature using gray level co-occurrence matrix (GLCM) and classification into normal and abnormal using machine learning algorithm and quantization techniques i.e. LVQ. The proposed system achieved the accuracy of 68.85% for DDSM mammography database and 79.35% on clinical brain MRI database.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122124994","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071570
N. Belsha, N. Hariprasad
Vegetables play a major role in Indian agriculture by providing economic viability, nutritional security, and fit well into the predominant intensive cropping systems prevailing in different parts of our country. To develop technologies that enhance quality and productivity of vegetables and solve increasing biotic and abiotic diseases is the major challenge in vegetable research. The vegetable disease identification and classification is the most important and catching attention research topic in the agriculture science. Image processing is the most suitable and best tool for classification and retrieval system. The Proposed work is to retrieve and classify the various types of infected and non-infected vegetable image. Searching the vegetable image from the large database for the analysis of the quality is difficult to defeat this Content-Based Image Retrieval (CBIR) system is introduced. A novel approach of CBIR system is used in the vegetable images by using feature extraction techniques. In classification of the infected vegetables is done through the process of feature extraction and classification. The final results shows for enhanced system of five types of vegetables like carrot, potato, bell pepper, Cabbage and tomato, Area of Infection of infected vegetable, and performance analysis of Infected/Non-infected vegetables.
{"title":"The enhanced content based image retrieval system and classification of infected vegetables","authors":"N. Belsha, N. Hariprasad","doi":"10.1109/SSPS.2017.8071570","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071570","url":null,"abstract":"Vegetables play a major role in Indian agriculture by providing economic viability, nutritional security, and fit well into the predominant intensive cropping systems prevailing in different parts of our country. To develop technologies that enhance quality and productivity of vegetables and solve increasing biotic and abiotic diseases is the major challenge in vegetable research. The vegetable disease identification and classification is the most important and catching attention research topic in the agriculture science. Image processing is the most suitable and best tool for classification and retrieval system. The Proposed work is to retrieve and classify the various types of infected and non-infected vegetable image. Searching the vegetable image from the large database for the analysis of the quality is difficult to defeat this Content-Based Image Retrieval (CBIR) system is introduced. A novel approach of CBIR system is used in the vegetable images by using feature extraction techniques. In classification of the infected vegetables is done through the process of feature extraction and classification. The final results shows for enhanced system of five types of vegetables like carrot, potato, bell pepper, Cabbage and tomato, Area of Infection of infected vegetable, and performance analysis of Infected/Non-infected vegetables.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121048670","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071611
G. K. Reddy, D. Punniamoorthy, Vikram S. Kamadal, S. Srinivas
The log-periodic antennas (LP), also know as a log-periodic array or log-periodic aerial which are very effectively useful to achieve large bandwidth. By careful design of planar log-periodic antennas with impedance matching we get large bandwidth. The chebyshev impedance matching is one of the best techniques to produce large bandwidth in log-periodic antenna. In this paper four arm log-periodic antenna is designed for the both linear and circular polarization. When the 900 phase delay applied between the two dipoles the antenna produce circular polarization. The antenna is operated at 3GHz gives the band of operation from 2GHz band upto K/Ka band. According to IEEE 802.11 the 5.1GHz to 5.8GHz band is occupied for Wi-Fi applications. So there is a need to eliminate the Wi-Fi band by using integrating filter method. The antenna is designed and simulated by using HFSS software, the variation of voltage standing wave ratio(VSWR), return loss and axial ratio plots are generated from 2GHz to 18GHz. The antenna is fabricated on FR 4 substrate for band rejection by using integrating filter method. Measured results are well accepted with simulated results.
{"title":"Wideband four arm log-periodic planar antenna with Wi-Fi band rejection","authors":"G. K. Reddy, D. Punniamoorthy, Vikram S. Kamadal, S. Srinivas","doi":"10.1109/SSPS.2017.8071611","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071611","url":null,"abstract":"The log-periodic antennas (LP), also know as a log-periodic array or log-periodic aerial which are very effectively useful to achieve large bandwidth. By careful design of planar log-periodic antennas with impedance matching we get large bandwidth. The chebyshev impedance matching is one of the best techniques to produce large bandwidth in log-periodic antenna. In this paper four arm log-periodic antenna is designed for the both linear and circular polarization. When the 900 phase delay applied between the two dipoles the antenna produce circular polarization. The antenna is operated at 3GHz gives the band of operation from 2GHz band upto K/Ka band. According to IEEE 802.11 the 5.1GHz to 5.8GHz band is occupied for Wi-Fi applications. So there is a need to eliminate the Wi-Fi band by using integrating filter method. The antenna is designed and simulated by using HFSS software, the variation of voltage standing wave ratio(VSWR), return loss and axial ratio plots are generated from 2GHz to 18GHz. The antenna is fabricated on FR 4 substrate for band rejection by using integrating filter method. Measured results are well accepted with simulated results.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126268701","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071604
P. Sundaram, R. Neela
This paper presents a novel method for analysis and assessment of various power quality events using Hilbert transform based Fuzzy system. Hilbert transform analyzes the distorted kinds of voltage waveforms and then extract their important features. The various kinds of distorted voltage waveforms are developed through the Matlab parametric equation. These extracted features are given to Fuzzy system in order to classify both the single and combined form of power quality events. The results indicates that the Hilbert transform based Fuzzy system can effectively classify the single and combined form of Power Quality events. The classification accuracy of the proposed method are validated by comparing them against Kalman filter, S-transform based fuzzy classifiers.
{"title":"Analysis and classification of power quality events using Hilbert transform and fuzzy system","authors":"P. Sundaram, R. Neela","doi":"10.1109/SSPS.2017.8071604","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071604","url":null,"abstract":"This paper presents a novel method for analysis and assessment of various power quality events using Hilbert transform based Fuzzy system. Hilbert transform analyzes the distorted kinds of voltage waveforms and then extract their important features. The various kinds of distorted voltage waveforms are developed through the Matlab parametric equation. These extracted features are given to Fuzzy system in order to classify both the single and combined form of power quality events. The results indicates that the Hilbert transform based Fuzzy system can effectively classify the single and combined form of Power Quality events. The classification accuracy of the proposed method are validated by comparing them against Kalman filter, S-transform based fuzzy classifiers.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129218368","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 : 2017-05-01DOI: 10.1109/SSPS.2017.8071571
Bhagyashree Besra, R. Mohapatra
Vascular biometrie is the method of analyzing the vein patterns or the patterns of blood vessels under the skin. The property of it being unforgeable, unspoofable, universal and unique, makes it highly preferable for a biometric authentication method. In this experiment, we have used CIE vein database, consisting of 1200 infrared palm images and 1200 infrared wrist images, each of 1280×960 resolution and of a 24-bit bitmap. In this paper, we have introduced a pre-processing phase followed by a feature extraction method. In the first stage, these images undergo several steps like; a) image acquisition, b) pre-processing, c) image normalization and d) post-processing. The binary image which is obtained in this phase is input for the next phase. Feature extraction of the vein patterns from the resulted binary image is based on line tracking algorithm with randomly start positions. Hence, the result has been recorded and found to be enhanced with this pre-processed technique.
{"title":"Extraction of segmented vein patterns using repeated line tracking algorithm","authors":"Bhagyashree Besra, R. Mohapatra","doi":"10.1109/SSPS.2017.8071571","DOIUrl":"https://doi.org/10.1109/SSPS.2017.8071571","url":null,"abstract":"Vascular biometrie is the method of analyzing the vein patterns or the patterns of blood vessels under the skin. The property of it being unforgeable, unspoofable, universal and unique, makes it highly preferable for a biometric authentication method. In this experiment, we have used CIE vein database, consisting of 1200 infrared palm images and 1200 infrared wrist images, each of 1280×960 resolution and of a 24-bit bitmap. In this paper, we have introduced a pre-processing phase followed by a feature extraction method. In the first stage, these images undergo several steps like; a) image acquisition, b) pre-processing, c) image normalization and d) post-processing. The binary image which is obtained in this phase is input for the next phase. Feature extraction of the vein patterns from the resulted binary image is based on line tracking algorithm with randomly start positions. Hence, the result has been recorded and found to be enhanced with this pre-processed technique.","PeriodicalId":382353,"journal":{"name":"2017 Third International Conference on Sensing, Signal Processing and Security (ICSSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130853311","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：