Using support vector machines to enhance the performance of elastic graph matching for frontal face authentication

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 23; no. 7; pp. 735 - 746
• Main Authors: Tefas, A., Kotropoulos, C., Pitas, I.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.07.2001; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Authentication; Constraint optimization; Face recognition; Graph matching; Humans; Inequalities; Neural networks; Optimization; Pattern recognition; Performance enhancement; Polynomials; Similarity; Support vector machines; System testing
• ISSN: 0162-8828; 1939-3539
• DOI: 10.1109/34.935847

A novel method for enhancing the performance of elastic graph matching in frontal face authentication is proposed. The starting point is to weigh the local similarity values at the nodes of an elastic graph according to their discriminatory power. Powerful and well-established optimization techniques are used to derive the weights of the linear combination. More specifically, we propose a novel approach that reformulates Fisher's discriminant ratio to a quadratic optimization problem subject to a set of inequality constraints by combining statistical pattern recognition and support vector machines (SVM). Both linear and nonlinear SVM are then constructed to yield the optimal separating hyperplanes and the optimal polynomial decision surfaces, respectively. The method has been applied to frontal face authentication on the M2VTS database. Experimental results indicate that the performance of morphological elastic graph matching is highly improved by using the proposed weighting technique.