Papers by Santosh Shrikhande
International journal of scientific research in computer science, engineering and information technology, Feb 18, 2022
Diabetes is one of the prevalent diseases in the word with a high mortality rate. This disease ha... more Diabetes is one of the prevalent diseases in the word with a high mortality rate. This disease has created several health problems and side effects on other organs of the human body. Therefore, diagnosis of this disease at early stage is essential that can reduce the fatal rate of humans. There are several ways to diagnose the diabetes but early diagnosis is quite challenging task for the medical practitioners. Recently, data mining based techniques are widely used for early prediction of diabetes that gives promising results in diabetes prediction. This paper presents the detailed review of existing data mining techniques used for diabetes prediction with their comparative study. This study also provides analysis of existing methodologies that will help in future perspective for designing and developing novel diabetes predictive models.
Finger vein biometric has become most promising recognition method due to its accuracy, reliabili... more Finger vein biometric has become most promising recognition method due to its accuracy, reliability and security. This paper discusses a novel technique for finger veins features extraction using Discrete Wavelet Packet Transform (DWPT) based method. The DWPT without HH subband decomposition is applied on ROI of 96×64 size finger veins image up to third level. The average standard deviation and average energy of each decomposition level are used for the creation of features vector database. The Euclidean, City Block and Canberra distance classifiers are used for the classification of finger veins images. The performance of proposed method is evaluated on the standard finger veins image ROI database of SDUMLA Shandong University. Experimental results show that the proposed method gives better results as compare to the standard Discrete Wavelet Transform (DWT) and DWPT Methods.
International Journal of Engineering and Computer Science
Every person has a unique finger vein pattern existing within each finger. Unlike facial features... more Every person has a unique finger vein pattern existing within each finger. Unlike facial features or fingerprints, finger vein authentication systems aren’t vulnerable to forgery. Finger vein authentication systems are more secure and reliable, and less expensive, than biometric security systems using fingerprint. This paper presents a novel security framework based on finger vein pattern. Finger Vein pattern in used in ID based cryptography to generate the keys for data encryption. These keys are combined with generator of Elliptic Curve Cryptography (ECC) to exchange the keys using Diffie Hellman key exchange algorithm. Once the keys are exchanged, the data is encrypted using Advance Encryption Standard (AES). This framework is tested in Internet of Things (IoT) environment for enhancing the security. The IoT based security systems implemented in the banks and other organizations can be enhanced considerably using the proposed security model.
International Journal of Computer Sciences and Engineering, 2018
Biometric based system securities are superior because they provide a non-transferable means of i... more Biometric based system securities are superior because they provide a non-transferable means of identifying people not just cards, password or PINs. However many biometric traits are not secure against forgery and spoofing which breaks the biometric security systems. To overcome these security problems of previous biometric systems, people are looking towards vein biometrics which uses unique vascular pattern from human body. Finger vein biometrics has become most promising biometric recognition system due to its accuracy, security and convenience. Recently many researchers are working for developing novel approaches for finger vein pattern based biometric recognition system. This paper presents an approach for personal identification using local and global feature of finger vein pattern images. The local directional features of vein pattern are extracted using Local Directional features method and global texture features extracted using Discrete Wavelet Transform (DWT) and Rotated Wavelet Filters (RWF) jointly. The feature vector is created by combining the local directional code based features with DWT and RWF based features together at feature level. Then, Canberra distance metric is used for the similarity measurement and classification. Experimental results have shown that the performance of proposed method outperforms other methods in terms of recognition accuracy and error rate.
International Journal of Computer Applications, 2016
Finger vein biometric have been recognized as the most effective and promising recognition method... more Finger vein biometric have been recognized as the most effective and promising recognition method due to its accuracy and security. This paper discusses a method for finger vein image features extraction using 2-D Rotated Wavelet Filters (RWF) and Discrete Wavelet Transform (DWT) jointly. A set of 2-D RWF filters improves characterization of diagonally oriented texture features from a finger vein image. The 2-D RWF and DWT jointly used for decomposition of a finger vein image ROI up to third level. The standard deviation and energy of each subband from every decomposition level are used for the creation of features vector. Then Canberra distance classifier is used for the classification of finger vein images. The performance of this method has evaluated on the standard finger vein image database of Shandong University (SDUMLA), China. Experimental results have shown that the method with RWF and DWT jointly gives better results as compare to the traditional DWT based methods.
International journal of scientific research in computer science, engineering and information technology, Feb 18, 2022
Diabetes is one of the prevalent diseases in the word with a high mortality rate. This disease ha... more Diabetes is one of the prevalent diseases in the word with a high mortality rate. This disease has created several health problems and side effects on other organs of the human body. Therefore, diagnosis of this disease at early stage is essential that can reduce the fatal rate of humans. There are several ways to diagnose the diabetes but early diagnosis is quite challenging task for the medical practitioners. Recently, data mining based techniques are widely used for early prediction of diabetes that gives promising results in diabetes prediction. This paper presents the detailed review of existing data mining techniques used for diabetes prediction with their comparative study. This study also provides analysis of existing methodologies that will help in future perspective for designing and developing novel diabetes predictive models.
2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2015
Finger vein biometric has become most promising recognition method due to its accuracy, reliabili... more Finger vein biometric has become most promising recognition method due to its accuracy, reliability and security. This paper discusses a novel technique for finger veins features extraction using Discrete Wavelet Packet Transform (DWPT) based method. The DWPT without HH subband decomposition is applied on ROI of 96×64 size finger veins image up to third level. The average standard deviation and average energy of each decomposition level are used for the creation of features vector database. The Euclidean, City Block and Canberra distance classifiers are used for the classification of finger veins images. The performance of proposed method is evaluated on the standard finger veins image ROI database of SDUMLA Shandong University. Experimental results show that the proposed method gives better results as compare to the standard Discrete Wavelet Transform (DWT) and DWPT Methods.
Biometrics is the method of automatic identification of an individual by using their certain meas... more Biometrics is the method of automatic identification of an individual by using their certain measurable physiological or behavioral characteristics like fingerprints, palm prints, hand geometry, iris, retinas, faces, hand veins, facial expressions, signatures, and voiceprints. Biometrics has overcome the problems of traditional verification methods like cards, tokens and Password or PINs. Biometric indicators have an edge over traditional security methods in that these attributes cannot be easily forgotten, stolen or shared; personally they have to go through the system. This paper reviews all biometrics and their various studies that have explored the technical and convenience issues and comparison between all the biometrics with an objective to provide insights on their reliability, performance, security, convenience and acceptance.
Uploads
Papers by Santosh Shrikhande