COMPREHENSIVE EVALUATION OF APPEARANCE-BASED TECHNIQUES FOR PALMPRINT FEATURES EXTRACTION USING PROBABILISTIC NEURAL NETWORK, COSINE MEASURES AND EUCLIDEAN DISTANCE CLASSIFIERS
Journal Title: Scientific Bulletin, Series: Electronics and Computer Science - Year 2018, Vol 18, Issue 1
Abstract
Most biometric systems work by comparing features extracted from a query biometric trait with those extracted from a stored biometric trait. Therefore, to a great extent, the accuracy of any biometric system is dependent on the effectiveness of its features extraction stage. With an intention to establish a suitable appearance based features extraction technique, an independent comparative study of Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) algorithms for palmprint features extraction is reported in this article. Euclidean distance, Probabilistic Neural Network (PNN) and cosine measures were used as classifiers. Results obtained revealed that cosine metrics is preferable for ICA features extraction while PNN is preferable for LDA features extraction. Both PNN and Euclidean distance yielded a better recognition rate for PCA. However, ICA yielded the best recognition rate in terms of FAR and FRR followed by LDA then PCA.
Authors and Affiliations
Noah Oluwatobi Akande, ROSELINE OGUNDOKUN, OLUWAKEMI CHRISTIANA ABIKOYE, Isiaka Akinkunmi ADEYEMO, Taye Oladele ARO
Keywords
Related Articles
- EP ID EP362353
- DOI -
- Views 87
- Downloads 0
EXAMPLE ARCHITECTURE FOR AN INTERURBAN TRAFFIC MANAGEMENT SYSTEM
The paper presents considerations regarding the architecture for an inter-urban traffic management system, describing all the main components: the functional architecture, the physical architecture and the communication...
SIMPLE DESIGN METHOD FOR MICROWAVE BAND-PASS FILTERS
In this paper, a simple method for designing and simulating low-frequency band-pass filters of around 1GHz is presented. In this aim, an original combination of three free software applications is proposed. It will be sh...
METHODES FOR KNOWING THE CLASS OF STUDENTS
Nowadays most classes are made up of 28 to 30 students, so the class teacher’s work is not easy. To avoid situations in which students are treated discriminatory, it is recommended that when he/she takes the class for tu...
NEURAL PATTERNS EDITOR, A JAVA APPLICATION FOR EDITING AND ANALYSING PATTERNS FOR TRAINING OR TESTING NEURAL NETWORKS
Neural Patterns Editor is a graphical application used for creating binary patterns that are used with neural networks ( for the training or for the testing ). It is also used for storing the patterns in text files, edit...
INVESTIGATING THE PERFORMANCE OF A SECURE RASPBERRY PI SNMPV3 AGENT
due to its low cost, size and high versatility. SNMP protocol is used to monitor dedicated network devices and systems both Windows and Linux. Raspberry Pi can be used to monitor the network as a SNMP agent. There are, h...