Vinayak Bairagi - Academia.edu (original) (raw)
Uploads
Papers by Vinayak Bairagi
International Journal of Advanced Research in Computer Science, Jun 20, 2017
Information represented in a digitized image format is very easy to handle. These image files con... more Information represented in a digitized image format is very easy to handle. These image files contain massive amounts of information, which requires efficient storage and transfer methods. There is requirement of investigation of quality issues, transfer methods, and storage mechanisms for such large size of these image files. Image compression requires less storage space for large image files. The transfer time is reduced for compressed files, while moving over networks. The aim of image compression techniques is to reduce the amount of data needed to accurately represent an image, such that this image can be economically transmitted or archived. In the field of medical imaging the use of computers is growing. Every day, a huge amount of data is produced from different medical imaging devices. Storage and transmission of this data becomes a problem, where bandwidth constraints are a major issue. This paper discusses the different types of image compression algorithm and the importance of image compression in medical communication. Some of the basic compression algorithms are used on test data and their performance is tested for wired communication.
EEG-Based Diagnosis of Alzheimer Disease, 2018
2017 International Conference on Soft Computing and its Engineering Applications (icSoftComp), 2017
Most recently popular biometrie systems are based on recognition and classification of unique scl... more Most recently popular biometrie systems are based on recognition and classification of unique sclera and iris patterns. Unique pattern of blood veins explore the interest in sclera recognition for person identification. However sclera segmentation of relaxed eye images in condition such as different stare direction, at-a-distance image and on-the-move image widely enquired. The drawback of iris is off angle imaging where position of iris and center for off angle imagining affect the performance of sclera segmentation in terms of accuracy. Another challenge in sclera segmentation and iris recognition is high resolution and dark images which causes draining process for mobile application. So we proposed a new method which is the fusion of both iris and sclera. In proposed system sclera and iris descriptor value are fuse together for reliable and accurate iris recognition system. The proposed method will test the execution of iris recognition system for different fusion model using iri...
Existing iris recognition system provides accurate and reliable results based on Near Infrared Im... more Existing iris recognition system provides accurate and reliable results based on Near Infrared Images when images are captured under constrained environment with user cooperation from fixed distance. But the performance of iris recognition system degrades for color eye images acquired under visible wavelength without user cooperation due to noise occurrence such as blur eye images, eyelash, occlusion and reflection. This paper present the multimodal eye biometric system based on support value based fusion for iris, sclera and pupil features depending on their match score value. Support value for iris, sclera and pupil is calculated using the log Gabor features, Y-shaped features and color histogram features. The robustness of proposed eye biometric system is tested on UBIRIS.V2 database for noisy eye images taken under unconstrained environment in visible wavelength. The propose algorithm significantly improve the accuracy of person authentication by reducing the time for segmentati...
EEG-Based Diagnosis of Alzheimer Disease, 2018
Nonlinear Dynamical analysis (NDA) methods are extensively used for variety of biomedical as well... more Nonlinear Dynamical analysis (NDA) methods are extensively used for variety of biomedical as well as physiological data analysis over last decades. The major contributions of these are the analysis of Electroencephalogram (EEG) signals in Alzheimer’s disease diagnosis. Various studies have shown the decreased complexity in EEG signals using nonlinear methods. The prominent decrease in information in cortical regions of human brain is quantified using various measures such as entropy, mutual information spectral features, and many more. This observation concludes the decreased complexities in EEG signals of patients with Alzheimer’s disease. This chapter focuses on various nonlinear abnormalities of EEG signals in patients with Alzheimer’s disease and its clinical implications. It can be concluded that nonlinear analysis of EEG signals may result in deeper understanding of neurophysiological mechanism in Alzheimer’s disease, which are not possible by study of spectral analysis.
International Journal of Innovative Technology and Exploring Engineering, 2019
Recent advancement in biometric system prefer multimodal biometric system instead of single biome... more Recent advancement in biometric system prefer multimodal biometric system instead of single biometric system to overcome challenges faced by unimodal biometric system such as intra class variation, noise sensitivity, non universality, spoofing attack, etc. Most of the existing iris biometric systems are dependent on ideal condition which needs user cooperation during image acquisition with help of NIR camera to avoid noise. Such system performance significantly degrades when images are taken under visible light without user cooperation called unconstrained environment. Proposed multi modal eye biometric system provides improvement in segmentation accuracy using entropy based convolution neural network (E-CNN) based on contour feature. It also reduces the time required for segmentation up to 0.9second. Multi algorithmic feature extraction for color, texture features of iris and pupil and Y-shaped features of sclera exploit the improvement in feature extraction performance. Proposed f...
EEG-Based Diagnosis of Alzheimer Disease, 2018
Artificial intelligence (AI) is an emerging component of computer science, which tries to make co... more Artificial intelligence (AI) is an emerging component of computer science, which tries to make computers more intelligent. Hence, Machine Learning is one of the most rapidly emerging parts of AI. Machine Learning algorithms were designed since the past and used to analyze large datasets in medical field. Presently, Machine Learning algorithms serve as indispensable tools for data analysis. It can be regarded as the most rapidly growing field, which integrates intersection of computer science and statistics, involving use of AI and data science. In this chapter, we focus on various Machine Learning algorithms, which can be used for classification of EEG datasets into two groups, namely Alzheimer’s disease and healthy groups. It can be concluded that progression in advanced computing and AI, medical analysis, and classification of data is become simpler and easy.
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
International Journal of Medical Engineering and Informatics
Advances in Intelligent Systems and Computing
Journal of Statistics and Management Systems
Biomedical and Pharmacology Journal
Journal of Advanced Research in Dynamical and Control Systems
Periodicals of Engineering and Natural Sciences (PEN)
Computer-aided diagnostic (CAD) studies are used for scientific observations for explanation sinc... more Computer-aided diagnostic (CAD) studies are used for scientific observations for explanation since very long time, but they are extraordinarily powerful to perform completely machine-driven algorithmic analyses for brain magnetic resonance imaging lesions. Structural and purposeful imbalance within the human brain could be reviewed. This imbalance analysis of the brain has terrific importance in an image analysis. In the present work, the imbalance between the two hemispheres is considered as the base for the detection of the tumour. We have segmented the brain into the two halves using thresholding technique, followed by statistical feature extraction for the double authentication of the existence of tumour which proves to be the better approach. The approach also takes into consideration corrections needed for the tilt observed while capturing the MRI.
International Journal of Advanced Research in Computer Science, Jun 20, 2017
Information represented in a digitized image format is very easy to handle. These image files con... more Information represented in a digitized image format is very easy to handle. These image files contain massive amounts of information, which requires efficient storage and transfer methods. There is requirement of investigation of quality issues, transfer methods, and storage mechanisms for such large size of these image files. Image compression requires less storage space for large image files. The transfer time is reduced for compressed files, while moving over networks. The aim of image compression techniques is to reduce the amount of data needed to accurately represent an image, such that this image can be economically transmitted or archived. In the field of medical imaging the use of computers is growing. Every day, a huge amount of data is produced from different medical imaging devices. Storage and transmission of this data becomes a problem, where bandwidth constraints are a major issue. This paper discusses the different types of image compression algorithm and the importance of image compression in medical communication. Some of the basic compression algorithms are used on test data and their performance is tested for wired communication.
EEG-Based Diagnosis of Alzheimer Disease, 2018
2017 International Conference on Soft Computing and its Engineering Applications (icSoftComp), 2017
Most recently popular biometrie systems are based on recognition and classification of unique scl... more Most recently popular biometrie systems are based on recognition and classification of unique sclera and iris patterns. Unique pattern of blood veins explore the interest in sclera recognition for person identification. However sclera segmentation of relaxed eye images in condition such as different stare direction, at-a-distance image and on-the-move image widely enquired. The drawback of iris is off angle imaging where position of iris and center for off angle imagining affect the performance of sclera segmentation in terms of accuracy. Another challenge in sclera segmentation and iris recognition is high resolution and dark images which causes draining process for mobile application. So we proposed a new method which is the fusion of both iris and sclera. In proposed system sclera and iris descriptor value are fuse together for reliable and accurate iris recognition system. The proposed method will test the execution of iris recognition system for different fusion model using iri...
Existing iris recognition system provides accurate and reliable results based on Near Infrared Im... more Existing iris recognition system provides accurate and reliable results based on Near Infrared Images when images are captured under constrained environment with user cooperation from fixed distance. But the performance of iris recognition system degrades for color eye images acquired under visible wavelength without user cooperation due to noise occurrence such as blur eye images, eyelash, occlusion and reflection. This paper present the multimodal eye biometric system based on support value based fusion for iris, sclera and pupil features depending on their match score value. Support value for iris, sclera and pupil is calculated using the log Gabor features, Y-shaped features and color histogram features. The robustness of proposed eye biometric system is tested on UBIRIS.V2 database for noisy eye images taken under unconstrained environment in visible wavelength. The propose algorithm significantly improve the accuracy of person authentication by reducing the time for segmentati...
EEG-Based Diagnosis of Alzheimer Disease, 2018
Nonlinear Dynamical analysis (NDA) methods are extensively used for variety of biomedical as well... more Nonlinear Dynamical analysis (NDA) methods are extensively used for variety of biomedical as well as physiological data analysis over last decades. The major contributions of these are the analysis of Electroencephalogram (EEG) signals in Alzheimer’s disease diagnosis. Various studies have shown the decreased complexity in EEG signals using nonlinear methods. The prominent decrease in information in cortical regions of human brain is quantified using various measures such as entropy, mutual information spectral features, and many more. This observation concludes the decreased complexities in EEG signals of patients with Alzheimer’s disease. This chapter focuses on various nonlinear abnormalities of EEG signals in patients with Alzheimer’s disease and its clinical implications. It can be concluded that nonlinear analysis of EEG signals may result in deeper understanding of neurophysiological mechanism in Alzheimer’s disease, which are not possible by study of spectral analysis.
International Journal of Innovative Technology and Exploring Engineering, 2019
Recent advancement in biometric system prefer multimodal biometric system instead of single biome... more Recent advancement in biometric system prefer multimodal biometric system instead of single biometric system to overcome challenges faced by unimodal biometric system such as intra class variation, noise sensitivity, non universality, spoofing attack, etc. Most of the existing iris biometric systems are dependent on ideal condition which needs user cooperation during image acquisition with help of NIR camera to avoid noise. Such system performance significantly degrades when images are taken under visible light without user cooperation called unconstrained environment. Proposed multi modal eye biometric system provides improvement in segmentation accuracy using entropy based convolution neural network (E-CNN) based on contour feature. It also reduces the time required for segmentation up to 0.9second. Multi algorithmic feature extraction for color, texture features of iris and pupil and Y-shaped features of sclera exploit the improvement in feature extraction performance. Proposed f...
EEG-Based Diagnosis of Alzheimer Disease, 2018
Artificial intelligence (AI) is an emerging component of computer science, which tries to make co... more Artificial intelligence (AI) is an emerging component of computer science, which tries to make computers more intelligent. Hence, Machine Learning is one of the most rapidly emerging parts of AI. Machine Learning algorithms were designed since the past and used to analyze large datasets in medical field. Presently, Machine Learning algorithms serve as indispensable tools for data analysis. It can be regarded as the most rapidly growing field, which integrates intersection of computer science and statistics, involving use of AI and data science. In this chapter, we focus on various Machine Learning algorithms, which can be used for classification of EEG datasets into two groups, namely Alzheimer’s disease and healthy groups. It can be concluded that progression in advanced computing and AI, medical analysis, and classification of data is become simpler and easy.
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
Brain Seizure Detection and Classification Using EEG Signals
International Journal of Medical Engineering and Informatics
Advances in Intelligent Systems and Computing
Journal of Statistics and Management Systems
Biomedical and Pharmacology Journal
Journal of Advanced Research in Dynamical and Control Systems
Periodicals of Engineering and Natural Sciences (PEN)
Computer-aided diagnostic (CAD) studies are used for scientific observations for explanation sinc... more Computer-aided diagnostic (CAD) studies are used for scientific observations for explanation since very long time, but they are extraordinarily powerful to perform completely machine-driven algorithmic analyses for brain magnetic resonance imaging lesions. Structural and purposeful imbalance within the human brain could be reviewed. This imbalance analysis of the brain has terrific importance in an image analysis. In the present work, the imbalance between the two hemispheres is considered as the base for the detection of the tumour. We have segmented the brain into the two halves using thresholding technique, followed by statistical feature extraction for the double authentication of the existence of tumour which proves to be the better approach. The approach also takes into consideration corrections needed for the tilt observed while capturing the MRI.