Open AccessEfficient technique to estimate age using PCA & multi SVM classification
Author(s) -
Laiphrakpam Jibanpriya Devi,
Javed Iqbal
Publication year - 2017
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i1.2.8999
Subject(s) - computer science , support vector machine , pattern recognition (psychology) , artificial intelligence , matching (statistics) , matlab , feature (linguistics) , face (sociological concept) , euclidean distance , principal component analysis , facial recognition system , data mining , mathematics , statistics , social science , linguistics , philosophy , sociology , operating system
Human interaction with computer is recent trend in computer technology. In order to obtain age information, image-based age estimation systems have been developed using information from the human facial images. We develop a new technology which identify the characteristic of human being like age. Facial information study will lead us to identify age. While generic growth patterns that are characteristics of different age groups can be identified. In order to create an accurate algorithm for age classification, we build an appropriate datasets for training is build using SVM classification method. We build an application base on MATLAB software to estimate age based on the trained data. Feature of face is extracted using PCA method and stored the data in array matrix. The accuracy of the trained data is 95.65%. We have an average matching percentage of 92%. We have Euclidean distance calculation method to verify the matched data and we found 100% verified.