Age normalization of face photo by image decomposition and reconstruction
Date of Issue2017-05-24
School of Electrical and Electronic Engineering
Aging is an inevitable process of human and it is affected signiﬁcantly by many factors such as health, gender, race, and lifestyle, which make it very difficult to establish an accurate modeling of aging in human faces. Aging normalization or modeling for special age group can predict one's appearance, which help to find the missing children and track criminal suspects and terrorists etc. This project try a novel idea to decompose the face image into different components and reconstruct the images with specific components to create specific effect on the face image. It is important to collect a large number of face photos in the specific age group and apply some methods to summarize the features of the groups. In this case, Principal Component Analysis (PCA) is studied and applied to achieve the desired result. Special effect on adding or removing the glasses is added according to the user’s preference. User can also adjust the difference between the reconstructed image and original test image. MATLAB (MATrix LABoratory) is applied to process all face images in computer.
Final Year Project (FYP)
Nanyang Technological University