Academic journal article International Journal of Electronic Commerce Studies

Face Localization and Detection Based on Symmetry Detection and Texture Features

Academic journal article International Journal of Electronic Commerce Studies

Face Localization and Detection Based on Symmetry Detection and Texture Features

Article excerpt


This study refers mainly to the characteristics of symmetry and texture features in order to correctly locate a face within an image. Since we target facial expression and illumination variation in a facial image, this first requires an equalization process of adaptive smoothing of the shadows of the face caused by varying illumination. Following this, for symmetry axis detection, the study will address: Gradient Detection, Image Width and Location of Symmetry Axes, Symmetry Axes for Gradient Histogram (SAGH) and Selection; Weight is also added to strengthen symmetry characteristics. In order to verify the accuracy of the method, this study will use 6 experimental methods, namely SAGH, SAPG, WSAGH, WSAPG, WSAGH for no adaptive smoothing, and WSAPG for no adaptive smoothing. The image database used for this experiment is the Yale Face Database, with facial images that are subjected to different illumination, masked by shelters and displaying varying facial expressions. The experiment results show that the WSAPG method is the most accurate; achieving a 96.36% LM value, with the lowest GM value; it was the most successful at locating a face in the image. Hopefully it will be applied to enhancing current face recognition technology.

Keywords: Face Detection, Adaptive Smoothing, Symmetry Detection, Texture Feature

(ProQuest: ... denotes formulae omitted.)


Face recognition technology is part of the Biometric Systems field, and was used in the early stages of digital identity and crime detection. With the evolution of technology, face recognition technology has become widely used in other areas, like the popular social network, Facebook, where face recognition technology identifies the possible location of a face, and allows the user to label the person in the picture, the user will then be able to know where in the picture that person is. Face recognition technology can be applied to video1: if face recognition technology is applied to video, and integrated with the drivers' records, it can assist the police in crime detection by identifying the face locations of people violating the law.

Photography and photo equipment are widely applied in all aspects of life today, assisting people by making up for insufficiencies in visual management, and also producing huge amounts of people image data. A means of instantly identifying each person in such images is a very important subject for future visual images. Face recognition compares the similarity of facial characteristics, and identification of the correct characteristic range is necessary for identifying facial characteristics; thus the location of a face plays a very important role in identifying facial characteristics.

Face recognition technology mainly uses facial characteristics to achieve recognition. The difference between face recognition technology and other Biometric Systems is that it does not require special equipment in order to acquire facial characteristics for recognition; thus, it is suitable for easy use by the general public. For this reason, many researchers are focusing on face recognition and related studies. Current face recognition technology study uses color or gray images to conduct experiments. Color images use facial skin characteristics to conduct recognition2, while gray images cannot use these characteristics, using only facial characteristics to conduct recognition. Current recognition methods using facial characteristics include: the template matching method3, feature extraction4, 5, line edge map6, etc. When conducting face recognition, the face is usually located first before conducting recognition, in order to avoid noise interfering with the result. In the past, complicated calculations were involved in locating the face, such as7 using statistics of Principle Component Analysis (PCA) to project the facial characteristics in high-dimensional space, and selecting the important characteristics. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.