International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 11 | Nov -2016 www.irjet.net p-ISSN: 2395-0072 © 2016, IRJET | Impact Factor value: 4.45 | ISO 9001:2008 Certified Journal | Page 363 Real-Time Facial Age Estimation Using Image Processing For Automated Control Systems G.Meenakshi 1 , E.Kaviyarasan 2 , S.Sumathi 3 1 Assistant Professor, Dept. of ECE, Velammal Engineering College, Chennai, India. 2 Student, Dept. of ECE, Velammal Engineering College, Chennai, India. 3 Assistant Professor, Dept. of ECE, Velammal Engineering College, Chennai, India. ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Due to the temporal property of age progression, face images with aging features may display some sequential patterns with low-dimensional distributions. It is intuitive for us to apply manifold analysis to age estimation. To bring out the advantages of manifold learning, some methods should be combined with appropriate regression models. In this paper, a novel framework of age estimation via multiple linear regressions on the discriminative aging manifold of face images is proposed. For a new testing image, the extracted low-dimensional feature with the learned regression model is used to estimate the exact age or an age interval. Key Words: Principal Component Analysis (PCA), Age Identification, Currency Identification. 1. INTRODUCTION The methods used in this paper are applicable to the precise age estimation, since each testing image is labeled with a particular age value chosen from a continuous range. In addition to the foregoing state-of-the-art work, the Sequential Pattern is used to characterize the ageing factor. Since each face image corresponds to a unique age label, a relatively large size data set should have a significant trend for some underlying sequential patterns. Currency identification is done by using the above method. Identification of age is useful in many applications to avoid so many misuses. This can be implemented in Internet surfing for Minors, Cigarette and Alcohol vending machine, and also in age specific shopping centers, to avoid the teenagers from consumption of alcohol and also in vehicles, to avoid riding of vehicle by minors that may result in accidents. 1.1 EXISTING PROBLEM Due to the temporal property of age progression, facial images with aging features may display some sequential patterns with low-dimensional distributions. The few existing methods on the age estimation via face images can be divided into three categories: Anthropometric model - These methods are suitable for the coarse age estimation, for example, classifying face images into four classes: infant, teenager, middle-aged people, and the elderly. Aging pattern subspace - To handle highly incomplete data due to the difficulty in data collection, Aging pattern Subspace (AGES) models a sequence of personal aging face images by learning a subspace. Age regression -In the regression case, facial features are extracted from an appearance-based shape-texture model. An input face image is then represented by a set of fitted model parameters. The regression coefficients are finally estimated according to a known regression function. Fig -1: Examples of facial aging images with different expressions. 2. PRINCIPAL COMPONENT ANALYSIS Principal component analysis (PCA) is one of the most valuable results from applied linear algebra, which is used abundantly in all forms of analysis - from neuroscience to computer graphics, because it is a simple, non-parametric method of extracting relevant information from confusing data sets [] . It is a mathematical procedure that transforms possible number of correlated variables into a smaller number of uncorrelated variables, which is called principal components. The first principal component accounts for the variability in the data, and each succeeding component accounts for as much of the remaining variability. It is also called discrete Karhunen-Loève Transform (KLT), the Hotelling transform or Proper Orthogonal Decomposition