As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In this paper, we focus on a new semi-supervised framework based on a new form of manifold regularization, which contains both underlying discriminative and local geometry structure of unlabeled samples, thus can mine as much underlying knowledge lurking in the unlabeled samples as possible. Meanwhile, this method introduces an equality type constraint that aims to minimize the error over the unlabeled patterns into the defining constraint structure of the proposed learning framework. The method is tested in the challenging problem of terrain perception. Results obtained demonstrate the effectiveness and feasibility of the proposed method for terrain image classification.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.