Abstract
AbstractOne-class Support Vector Machine (OCSVM) is an effective method in researching of one-class classification problems, which extracts a hyperplane in a kernel feature space such that a given fraction of training objects may reside beyond the hyperplane, while the hyperplane has maximal distance to the origin. However, OCSVM is generally based on vector pattern, hence, when the input of the classifier is a non-vector pattern, such as a face image, it has to be concatenated to construct a vector firstly. In this paper, inspired by 2D feature extractions and 2D classifier designs, we develop a new OCSVM based on matrix patterns, called MatOCSVM. Experimental results on ORL face database and Letter text-base show that the proposed method is competitive in one-class classification performance compared to OCSVM.KeywordsOne-class support vector machines (OCSVM)Matrix patternVector patternPattern recognitionOne-class classification
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.
