Efficient features extraction for fingerprint classification with multi layer perceptron neural network (original) (raw)
Related papers
FINGERPRINT RECOGNITION USING ARTIFICIAL NEURAL NETWORK
Abstract- N Network s The ability of the ANN to learn given patterns makes them suitable for such applications. Fingerprint recognition is one such area that can be used as a means of biometric verification where the ANN can play a critical rule. An ANN can be configured and trained to handle such variations observed in the texture of the fingerprint.
ARTIFICIAL NEURAL NETWORK BASED FINGERPRINT RECOGNITION
2012
Artificial Neural Network (ANN)s are efficient means of prediction, optimization and recognition. The ability of the ANN to learn given patterns makes them suitable for such applications. Fingerprint recognition is one such area that can be used as a means of biometric verification where the ANN can play a critical rule. An ANN can be configured and trained to handle such variations observed in the texture of the fingerprint. The specialty of the work is associated with the fact that if the ANN is configured properly it can tackle the variations in the fingerprint images and that way provide the insights for developing a system which requires these samples for verification and authorization. A system is designed to provide authentication decision using the fingerprint inputs can be a reliable means of verification. Such a system designed using ANN and using fingerprint inputs is described here. Experimental results show that the system is reliable enough for considering it as a part of a verification mechanism.
Performance of Fingerprint Enhancement and Classification Using Neural Network
INTERNATIONAL JOURNAL OF COMPUTER APPLICATION
Fingerprints are the best and most widely used form of biometric authentication. Everyone is known to have unique, immutable fingerprints. Fingerprints are secure to use because they do not change in one"s lifetime. Since fingerprints are unique, even between identical twins, they are perfect for various security uses. The goal of biometric authentication system is to compare two fingerprint images. The authentication in aadhaar card is done by this comparison. Human fingerprints are rich in details called minutiae, which can be used as identification marks for security purposes. Fingerprint authentication systems are based on local ridge features known as minutiae extraction, marking minutiae accurately and rejecting false ones. However, fingerprint images get degraded and corrupted due to variations in skin and impression conditions. To get accurate minutiae, image enhancement techniques are employed prior to minutiae extraction. This paper presents techniquesto verify the identity of fingerprint. So the minutiae points of fingerprint images are classified using support vector machine algorithm for the identification of type of fingerprints.
Fingerprint Classification Using Fuzzy-neural Network and Other Methods
IAES International Journal of Artificial Intelligence (IJ-AI)
The fingerprints are unique to each individual; they can be used as a means to distinguish one individual from another.Therefore they are used to identify a person. Fingerprint Classification is done to associate a given fingerprint to one of the existing classes, such as left loop, right loop, arch, tented arch and whorl. Classifying fingerprint images is a very complex pattern recognition problem, due to properties of intra-class diversitiesand inter-class similarities. Its objective is to reduce the responsetime and reducing the search space in an automatic identificationsystem fingerprint (AIS), in classifying fingerprints. In these papers we present a system of fingerprint classificationbased on singular characteristics for extracting feature vectorsand neural networks and fuzzy neural networks, SVM and Knearest neighbour for classifying.
A Survey of Fingerprint Analysis using Artificial Neural Networks
Fingerprint Analysis is one of the efficient biometric tool which is highly used to verify the identity of the user. Artificial neural networks consist of various sets of neurons which resembles the neurons in the human brains. ANN is most widely used in the fingerprint analysis because of quick learning Techniques. Usually the ANN is trained to determine the characteristics that will be occurring in the fingerprint and extraction of those characteristics. In the training phase the extracted characterizations are compared with the templates that will be present in the stored database. A wavelet is used to divide a continuous signal into a scalable component, this technique of wavelets help to determine and differentiate the mordant characteristics of the fingerprint.
This paper presents a two stage novel technique for fingerprint feature extraction and classification. Fingerprint images are considered as texture patterns and Multi Layer Perceptron (MLP) is proposed as a feature extractor. The same fingerprint patterns are applied as input and output of MLP. The characteristics output is taken from single hidden layer as the properties of the fingerprints. These features are applied as an input to the classifier to classify the features into five broad classes. The preliminary experiments were conducted on small benchmark database and the found results were promising. The results were analyzed and compared with other similar existing techniques.
A TECHNIQUE OF FINGERPRINT RECOGNITION USING ARTIFICIAL NEURAL NETWORK
This paper is present fingerprint recognition with the technique of artificial neural network. Fingerprint is widely accepted for personnel identification. In this technique we used back propagation algorithm. Firstly we used filter and histogram process of the input image than we trained artificial neural network on the input image.
FINGERPRINT IDENTIFICATION SYSTEM USING NEURAL NETWORK
Here I design and develop a pattern recognition system using Artificial Neural Network (ANN) and MATLAB that can recognize the type of image based on the features extracted from the choose image. Also I am comparing Backpropagation Neural Network and Cellular Neural Network. This system which can fully recognizing the types of the data had been add in the data storage or called as training data. The Graphic User Interface (GUI) in MATLAB toolbox is used. This is the alternative way to change the common usage of the MATLAB which are uses the command inserts at command window. From this kind of system, we just need to insert the features data or training data. The recognition done after we insert the test data. The system will recognize whether the output is match with the training data. Then output will produce a kind of graph that describes the feature of the data which is same as the training data. Index Terms: Matlab, Backpropagation Neural Network, Cellular Neural Network, Minutiae.
Fingerprint Verification Based on Back Propagation Neural Network
CEAI, Vol.15, No.3 pp. 53-60, 2013, 2013
This paper is concerned with novel features for fingerprint classification based on the Euclidian distance between the center point and their nearest neighbor bifurcation minutiae's. The main advantage of the new method is the dimension reduction of the features vectors used to characterize fingerprint, compared with the classic characterization method based on the relative position of bifurcation minutiae points. In addition, this new method avoids the problem of geometric rotation and translation over the acquisition phase. Whatever, the degree of fingerprint rotation, the extraction features used to characterize fingerprint remains the same. The characterization efficiency of the proposed method is compared to the method based on the spatial coordinate of fingerprint minutiae's. The comparison is based on a characterization criterion, usually used to evaluate the class quantification and the features discriminating ability. After that, the classification accuracy of the proposed approach is evaluated with Back Propagation Neural Network (BPNN). Extensive experiments prove that the fingerprint classification based on a novel features and BPNN classifier gives better results in fingerprint classification than several other features and methods. Finally the results of the proposed method are evaluated on the FVC 2002 database.
Neural Networks, 2001
In this paper, we propose a non-linear model for fingerprints matching which handles more efficiently the nonlinear deformation problem in fingerprint matching. It is based on the fact that a fingerprint image is composed of different minutiae with various orientations separated by a spatial distance that can be successfully represented by an interaction vector. After extracting the minutiae and the fingerprint core point we determine the orientation of the ridges around the core point and each minutia. The distance and orientation between the core point and each minutia are calculated and used in the interaction model to obtain the minutiae-core interaction index. A distance metric is used to compare the interaction descriptors of two fingerprints. The results of the comparisons are used to calculate the minutiaecore index of the fingerprint. Our non-linear model is experimented on FVC2000 DB1 and we feel it is promising although the results are fairly good.