Abstract
Image representation has been a fundamental problem for many real world applications, such as image database visualization, browsing, retrieval, etc. In this paper, we investigate the use of Laplacian Eigenmap (LE) for image representation and retrieval. Conventional, Principal Component Analysis (PCA) has been considered effective as to discovering the low dimensional structure of the image space. However, PCA can only discover the linear structure. It fails when the images are sampled from a low dimensional nonlinear manifold which is embedded in the high dimensional Euclidean space. By using Laplacian Eigenmap, we first build a nearest neighbor graph which models the local geometrical structure of the image space. A locality preserving mapping is then obtained to respect the graph structure. We compared the PCA and LE based image representations in the context of image retrieval. Experimental results show the effectiveness of the LE based representation.
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.
