Open Access Open Access  Restricted Access Subscription or Fee Access

An Efficient and Simple Approach to Extract Features for Facial Expression Recognition

M. V. Jonnalagedda, D. D. Doye

Abstract



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.

Keywords


Feature Extraction, Standard Deviation, Inter-Quartile Range, Local Binary pattern, Support Vector Machine

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.