New Feature Extraction Approach Based on Adaptive Fuzzy Systems for Reliable Biometric Identification (original) (raw)
Related papers
Soft computing approach for feature extraction of palm biometric
Multidisciplinary Science Journal
The method for developing a secure and reliable identification system relies on the use of biometrics. In this case, the palm vein is used as a security measure. The proposed system is powered by a convolutional neural network, which is a type of neural network that is commonly utilized for image recognition. The palm vein's visual features are extracted using a convolutional neural network. This method can improve the recognition rate and its performance parameters. The results of an experiment conducted with this method were better than those obtained with conventional techniques.
Fuzzy Extractors for Biometric Identification
2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)
2017 IEEE. Fuzzy extractor provides key generation from biometrics and other noisy data. The generated key is seamlessly usable for any cryptographic applications because its information entropy is sufficient for security. Biometric authentication offers natural and passwordless user authentication in various systems where fuzzy extractors can be used for biometric information security. Typically, a biometric system operates in two modes: verification and identification. However, existing fuzzy extractors does not support efficient user identification. In this paper, we propose a succinct fuzzy extractor scheme which enables efficient biometric identification as well as verification that it satisfies the security requirements. We show that the proposed scheme can be easily used in both verification and identification modes. To the best of our knowledge, we propose the first fuzzy extractor based biometric identification protocol. The proposed protocol is able to identify a user with constant computational cost rather than linear-time computation required by other fuzzy extractor schemes. We also provide security analysis of proposed schemes to show their security levels. The implementation shows that the performance of proposed identification protocol is constant and it is close to that of verification protocols.
Biometric Fuzzy Extractors Made Practical: A Proposal Based on FingerCodes
Lecture Notes in Computer Science, 2007
Recent techniques based on error-correction enable the derivation of a secret key for the (varying) measured biometric data. Such techniques are opening the way towards broader uses of biometrics for security, beyond identication. In this paper, we propose a method based on ngerprints to associate, and further retrieve, a committed value which can be used as a secret for security applications. Unlike previous work, this method uses a stable and ordered representation of biometric data, which makes it of practical use.
Soft Computing Approach to Multi-Modal Biometric System
The increasing demand for high secure and reliable authentication schemes, led to improvement in unimodal biometric system and hence multimodal biometric system has emerged as a mean of more secure and reliable authentication scheme. This work examines the multimodal fusion of palmprint (principal lines) and fingerprint (minutiae points). After an introduction to theoretical principles, related works in palmprint, fingerprint, and fusion of palmprint and fingerprint are highlighted. The developed system modules include image acquisition, morphological stage, feature extraction stage, fusion stage and classification stage. The database is composed of 600 posed fingerprints, 120 posed palmprints and 6480 fused posed palmprints and fingerprints. The data were trained and tested with a variant of neural network back-propagation algorithm. Three thresholds were employed viz; 0.35, 0.65 and 0.95. The results showed that threshold 0.95 produced average accuracy of 98.3%, threshold 0.65 produced average accuracy of 5%, and threshold 0.35 produced average accuracy 16.4%. I. INTRODUCTION Multimodal biometrics has become increasingly important, particularly because single modal biometrics has reached its bottleneck; i.e. non-universality, noise in sensor data and spoofing. Multimodal biometrics gives supplementary information between different modalities that increases recognition performance in term of accuracy and ability to overcome the drawbacks of single biometrics. Bhardwaj explained the advantages of using multimodal biometric system instead of conventional unimodal biometric system [1]. There are two types of biometric techniques: Physiological (face recognition, iris recognition, and finger print recognition). And the other one is Behavioral (signature recognition, gait, voice recognition). In this work we concentrate on the physiological features particularly finger print and palm print recognition. A palm print or finger print refers to an image acquired of the palm region or finger region of the hand. Most of the problems and limitations of biometrics are imposed by unimodal biometric systems, which rely on the evidence of only a single biometric trait. Some of these problems may be overcome by multi biometric systems and an efficient fusion scheme to combine the information presented in multiple biometric traits. In multimodal biometrics, the classification results obtained from each independent biometric channel is fused to obtain composite classification is known as biometric fusion. The fusion process in biometric provides increased reliability. Multimodal biometric fusion is very promising process to enhances the strengths and reduce the weaknesses of the individual measurements. Four possible levels of fusion methods are used for integrating data from two are more biometric systems. These are sensor level, feature extraction level, matching score level and decision level. Sensor level and feature extraction level are called pre-mapping fusion levels while matching score level and decision level are called post-mapping fusion levels. [2]. Although fusion increases accuracy, it generally increases computation costs and template sizes and reduces user acceptance. [3] The system proposed employed Otsu threshold for image normalization (both finger print and palm print). And the normalized images were subjected to morphological processing using Sobel gradient for palm prints and Histogram equalization-cum-secure alignment for finger prints. Palm print features were extracted with Gabol filter while Crossing Number was used to extract feature for finger prints. Both features are fused with concatenation and Classification is achieved by using a variant of Back-propagation Neural Network. The structure of human hand is discussed in the next section. Related works are discussed in section III, while section IV describes the structure of the proposed system. Results are discussed in section V and the conclusion is in section VI.
Integrated Biometric Verification System Using Soft Computing Approach
Neural Processing Letters, 2007
Among various biometric verification systems, fingerprint verification is one of the most reliable and widely accepted. One essential part of fingerprint verification is the minutiae extraction system. Most existing minutiae extraction methods require image preprocessing or post processing resulting in additional complex computation and time. Hence, direct gray-scale minutiae extraction approach on the image is preferred. One of these approaches is the use of Fuzzy Neural Network (FNN) as a recognition system to detect the presence of minutiae pattern. Currently, the development of FNN as a tool of recognition has shown a promising prospect. Some researchers have proposed several types of FNN. In particular, a Generic Self Organizing Fuzzy Neural Network (GENSOFNN) has been shown to excel in comparison with other FNN. Therefore, a new approach to perform direct grayscale minutiae extraction based on GENSOFNN is proposed in this paper. Experimental results show the potential of using GENSOFNN for real-time point of sale (POS) terminal for verification.
An improved algorithm for feature extraction from a fingerprint fuzzy image
Optica Applicata
Proper fingerprint feature extraction is crucial in fingerprint-matching algorithms. For good results, different pieces of information about a fingerprint image, such as ridge orientation and frequency, must be considered. It is often necessary to improve the quality of a fingerprint image in order for the feature extraction process to work correctly. In this paper we present a complete (fully implemented) improved algorithm for fingerprint feature extraction, based on numerous papers on this topic. The paper describes a fingerprint recognition system consisting of image preprocessing, filtration, feature extraction and matching for recognition. The image preprocessing includes normalization based on mean value and variation. The orientation field is extracted and Gabor filter is used to prepare the fingerprint image for further processing. For singular point detection, the Poincare index with a partitioning method is used. The ridgeline thinning is presented and so is the minutia e...
Fingerprint recognition based on adaptive neuro-fuzzy inference system
Pattern Recognition and Machine Intelligence, 2013
Fuzzy logic (FL) is a powerful problem solving methodology receiving wide spread acceptance for a range of applications. FL is also considered for image understanding applications such as edge detection, feature extraction, classification and clustering. It provides a simple and easy way to draw a definite conclusion from ambiguous, imprecise or vague information. Like Artificial Neural Network (ANN) models, some fuzzy inference system (FIS)s have the capability of universal approximation. The adaptive neuro-fuzzy inference system (ANFIS) belongs to the class of systems commonly known as neuro-fuzzy systems (NFs). NFs combines the advantages of ANN with those of fuzzy systems. An ANFIS based identification system is described here which uses fingerprint as an input. Experiments are carried out using a number of samples. Obtained results show that the system is reliable enough for considering it as a part of a verification mechanism.
Accurate Personal Identification Using Left and Right Palmprint Images Based on ANFIS Approach
International Journal of Mineral Processing and Extractive Metallurgy, 2017
The aim of present research work on palmprint recognition using discrete wavelet packet transform (DWPT) algorithm for feature extraction & ANFIS (Adaptive Neuro-Fuzzy Inference System) for palmprint matching. Biometrics based fingerprint, face, iris recognition has been investigated over many year. Palmprint recognition is an emerging technology in recent years due to the transaction frauds, security breaches and personal identification etc. compare to fingerprint, palmprint contain rich features like, principle line, wrinkles, ridges, and minute points, and it provides high standard security. This paper developing multibiometrics using left and right palmprint images and gives higher accuracy then single biometrics system. Registered IITD palmprint database is collected from IIT Delhi, biometric research library. It consist 2600 images from both left and right hand. This experiment perform palmprint recognition for enhance security using IITD database. MATLAB have been used as the programming tool to implement and investigate the performance of the segmentation and feature extraction method using image processing toolbox.
International Journal of Biomedical Engineering and Technology, 2017
For the security reasons, person identification has got primary place by means of some of the physiological features. In this paper, multimodal biometry is utilised for the person identification with the help of three physiological features such as finger print, palm print and hand vein. Initially, in the pre-processing stage, the unwanted portions, noise content and the blur effects are removed from the input finger print, palm print and hand vein images. The features from these three modalities are extracted. The combined feature vector is obtained by chaff points and extracted features. After getting the combined feature vector points, the secret key points are added with the combined feature vector points to generate the fuzzy vault. Finally, in the recognition stage, test person's combined vector is compared with the fuzzy vault database. Now we can obtain the corresponding finger print, hand vein and palm print images.
A Comparative Analysis of Different Feature Extraction Techniques for Palm-print Images
In this advanced decade, automatic identification of individuals is a significant achievement due to the high demand of security system. Hence, individual recognition using biometrics data is leading in the field of image processing. Although biometrics data analysis using thumb impression and finger-prints are very popular since many years, sometimes it leads to false acceptance and rejection if any physical change occurs in the finger ridges. There may be a high risk of hacking the biometrics data which is now a big challenge for cyber security employees. This paper captures the palm-print images of individuals as referred biometrics data for individual recognition. The research work is based on one of the prior issue that is feature extraction to extract the features of palm-print image such as principle lines, textures, ridges and pores etc. For this, some of the feature extraction techniques such as Derivatives of Gaussian filter (DoG), Discrete Cosine Transform (DCT), Fast Fou...