Joint learning and dictionary construction for pattern recognition
MetadataShow full item record
We propose a joint representation and classification framework that achieves the dual goal of finding the most discriminative sparse overcomplete encoding and optimal classifier parameters. Formulating an optimization problem that combines the objective function of the classification with the representation error of both labeled and unlabeled data, constrained by sparsity, we propose an algorithm that alternates between solving for subsets of parameters, whilst preserving the sparsity. The method is then evaluated over two important classification problems in computer vision: object categorization of natural images using the Caltech 101 database and face recognition using the Extended Yale B face database. The results show that the proposed method is competitive against other recently proposed sparse overcomplete counterparts and considerably outperforms many recently proposed face recognition techniques when the number training samples is small.
Showing items related by title, author, creator and subject.
Abd El-Sallam, Amar (2005)New approaches and algorithms are developed for the identification and estimation of low order models that represent multipath channel effects in Code Division Multiple Access (CDMA) communication systems. Based on these ...
Chai, Pey San Nancy (2011)Backhaul networks are used to interconnect access points and further connect them to gateway nodes which are located in regional or metropolitan centres. Conventionally, these backhaul networks are established using ...
Adaptive antenna array beamforming using a concatenation of recursive least square and least mean square algorithmsSrar, Jalal Abdulsayed (2011)In recent years, adaptive or smart antennas have become a key component for various wireless applications, such as radar, sonar and cellular mobile communications including worldwide interoperability for microwave ...