An Efficient and Simple Approach to Extract Features for Facial Expression Recognition
Megha Jonnalagedda, Dharmpal Dronacharya Doye · International journal of mathematics and computation · 2015
Researchers have used statistical parameters of variability for extracting features for a Facial Expression recognition system, but in combination with Gabor Wavelets or Fast Fourier Transform or Discrete Fourier Transform. This paper reports the facial features extracted using only statistical parameters of variability. Two sets of facial features are extracted here. One set of features is derived using mean and standard deviation and the other using median and Inter-Quartile Range. These statistical parameters of variability are computed along the rows and columns of an image so as to effectively determine the variations in expressions. These parameters being computationally less complex, require smaller computation time. In addition to this, they have resulted in smaller feature vector size and good recognition rate. The maximum recognition rates obtained are 94.76% for JAFFE database and 91.11% for Cohn-Kanade database, which are comparable and in some cases better than the other techniques used for facial expression recognition. Variations in illumination are taken care by applying Histogram Equalization technique before extracting features.