This paper proposes a novel method for feature extraction from the curvelet subbands using statistical methods. The face images is decomposed and then in curvelet basis a special set of statistical coefficients using higher order moments is extracted as the feature vector. Curvelet represent the image edges and the curved singularities in images more efficiently than wavelet. In addition, generalized neural network is used for verification to enhance the recognition accuracy which is trained by feature vector. The performance of proposed method is evaluated on two face databases: FERET and ORL. Extensive experimental results and comparison with the existing methods show the effectiveness of the proposed recognition method. © 2012 Springer India Pvt. Ltd.
CITATION STYLE
Sharma, P., Arya, K. V., & Yadav, R. N. (2012). Extraction of facial features using higher order moments in curvelet transform and recognition using generalized mean neural networks. In Advances in Intelligent and Soft Computing (Vol. 131 AISC, pp. 769–780). https://doi.org/10.1007/978-81-322-0491-6_70
Mendeley helps you to discover research relevant for your work.