Image transformation for beautification

• Main Author: Lim, Christine Kia Min
• Other Authors: Anamitra Makur
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/74912
• Institution: Nanyang Technological University

This project aims to identify comparable features in both images, a face with beautiful features and a face with in proportional features that can be improved. Additionally, to warp one shape into another, to achieve a visually beautiful face which involves basic image processing operations and MATLAB. As technology became more advanced, users can easily take a large number of digital photographs (image) of faces using their camera or hand phone. Sometimes, they wish to beautify a face photograph using image retouching tools. Instead of such a manual retouching, this project develops an automated beautification method. The method transforms a person's face into a better looking one with better features taken from other beautiful faces. Such transformation includes morphing, or changing, the dimensions of one face to another face. This report is divided into various chapters. Section I introduces the objective and scope of the project, followed by contributions made. In Section II, it shows the literature review of face detection, skin detection and image warping. Section III is an overview of the skin-pixel based techniques used in the project. Section IV detailed the face detection method using vision cascade object detector and results derived. Section V describes the process of coming up with a simple GUI interface. Lastly, Section VI shows the further improvements that can be made and concludes the report.