Abstract
Curvelet transform is a promising tool for multi-resolution analysis on images. This paper explains a new approach for facial expression recognition based on curvelet features extracted using curvelet transform. Curvelet transform is applied on the database images and curvelet coefficients are obtained for selected scale for image analysis. Facial curvelet features are compressed using singular value decomposition (SVD) approach. Back propagation neural network (BPNN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are used as classifiers for classifying expressions into one of the seven categories like angry, disgust, fear, happy, neutral, sad and surprise. Experimentation is carried out on JAFFE database. The experimental results show that the novel approach is a better option for extracting feature values and classifying facial expressions.
Highlights
The area of Human Computer Interaction (HCI) plays an important role in resolving the absences of neutral sympathy in interaction between human being and machine
This paper focuses on the use of curvelet transform features compressed using singular value decomposition (SVD)(Singular Value Decomposition) for expression recognition using Adaptive Neuro-Fuzzy Inference System (ANFIS) (Adaptive Neuro-Fuzzy System ) and Back propagation Neural network (BPNN) classifier and presents comparative analysis of two classifiers for curvelet-SVD features
Experimentation is carried out using JAFFE database images [27],which are preprocessed using the approach mentioned in [28].Wavelet transform is applied on preprocessed images
Summary
The area of Human Computer Interaction (HCI) plays an important role in resolving the absences of neutral sympathy in interaction between human being and machine (computer). Use of computers for Facial expression and emotion recognition and its related information use in HCI has gained significant research interest which in turn given rise to a number of automatic methods to recognize facial expressions in images or video [610].Multiresolution analysis techniques like wavelets are generally used in computer vision areas including facial expression recognition and face recognition [11][12][13].Many results have been achieved with wavelet transform in signal reconstruction, image analysis, facial expression recognition, etc, but wavelet transform has significant limitations in representing image edges as reported recently in [14][15] This is due to a fact that wavelet transform can only reflect the point singularity and specialty, but difficult to express characteristics for curves and edges. Transform features compressed using SVD(Singular Value Decomposition) for expression recognition using ANFIS (Adaptive Neuro-Fuzzy System ) and Back propagation Neural network (BPNN) classifier and presents comparative analysis of two classifiers for curvelet-SVD features
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
