Facial Expression Recognition Analysis

2102 Words9 Pages
Abstract—Facial Expression Recognition refers to the classification of facial features in one of the basic emotions: happiness, sadness, fear, disgust, surprise, anger and neutral. It is performed by means of feature extraction. Principle Component Analysis is a technique among the most common feature extraction technique used in Facial Expression Recognition. In this paper, a Facial Expression Recognition System for human’s expression identification using Principle Component Analysis with City-Block Distance Classifier is proposed. Eigen values and Eigen vectors of an image where calculated easily by means of Principle Component Analysis using these newly calculated Eigen values and Eigen vectors both test and train images are compared in…show more content…
VARIOUS FACIAL EXPRESSION RECOGNITION METHODS Facial expression recognition consists of three main steps. In the first step face image is acquired and detect the face regions from the images and pre-processing the input image to obtain the images that have a normalized size or intensity. Next is expression features are extracted from the saw facial image or image sequence. Then extracted features are given to the classifier and classifier provides the identifyd expression as output. The block diagram of facial expression recognition system is given in figure 1. Figure(1): Facial expression recognition system The input image can be represented in various ways. If face image can be represented as a whole unit then it is called holistic representation. If face image can be represented as a set of features then it is called analytic representation. Face can also be represented as a combination of these two then is called hybrid approach. A. Face Detection Face Detection is the process of localizing and extracting the face region from the background. It involves segmentation, extraction, and verification of faces as well as facial features from an uncontrolled background. It follows two different approaches: Emotion detection from still images and Emotion detection from images acquired from a video…show more content…
Since PAC convers whole image into feature vectors and then go for dimensionality reduction with the help of Singular Value Decomposition, it is easy to extract the Eigen Value and Eigen vectors which increases the accuracy or recognition rate of the expression recognition since these values carries the significant features of a particular image. Hence test case images are almost matching with the train image and identify the expression. Using this method average recognition rate of 89.47% is achieved also it provides 100% result for neutral and surprise

More about Facial Expression Recognition Analysis

Open Document