Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Facial expression recognition based on Local Binary Patterns: A comprehensive study
Image and Vision Computing
Face recognition with adaptive local hyperplane algorithm
Pattern Analysis & Applications
Face recognition using the nearest feature line method
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
The purpose of this paper is to present a comprehensive study of latest and most famous facial features extraction techniques and as well as classification techniques. We studied these techniques in two different perspectives; one is spatial domain and other is frequency domain. We found many advantages and disadvantages of each technique inside one domain and as well in between different domains. We observed that Local Binary Pattern is a new technique and now it is becoming very famous technique in spatial domain. LBP simply knows about micro patterns using the comparison with neighbour pixel grey scale values. Lot of work on LBP has yielded its different extensions which have optimized the base concept of LBP operator. Frequency domain covers the techniques which transform images into frequency domain and use either cosine or sine waves to extract the facial features. This method is a very strong and precise that only two to three features have the ability to describe the facial expressions. We have also studied different classification techniques in domain of facial expressions classification. In most of the solutions classification is done through KNN classifier. K Nearest Neighbour is a successful and non-parametric technique of machine learning in supervised learning techniques.