Retrieving Landscape Images Using Scene Structural Matrix G. Qiu and S. Sudirman School of Computer Science, The University of Nottingham Jubilee Campus, Nottingham NG8 1BB, UK {qiu,sxs}@cs.nott.ac.uk Abstract. In this paper, we present Scene Structural Matrix (SSM) and apply it to the retrieval of landscape images. The SSM captures the overall structural characteristics of the scene by indexing the geometric features of the image. A binary image tree (bintree) is used to partition the image and from which we derive multi-resolution geometric structural descriptors of the image. It is shown that SSM is particularly effective in retrieving images with strong structural features, such as landscape photographs. We show that SSM is robust against spatial and spectral distortions thus making it superior to current state of the art techniques such as color correlogram in certain applications. We will also show that images retrieved by the SSM are more relevant than those returned by color correlogram and color histogram. 1 Introduction Content-based indexing and retrieval [1] have attracted extensive research interests in recent years. Traditional methods use global statistics of local image features, e.g., color histogram [2], color correlogram [3] and their variance as image indices. These methods have been shown to be very successful in retrieving images with similar local feature distributions. However, since these measures do not take into account the locations of the local features, the retrieved results often do not make a lot of sense. For example, using a landscape image with blue sky on top and green countryside at the bottom as query example and trying to retrieve images with similar structures, i.e., blue sky on top and green countryside at the bottom, methods based on global statistics of local features often give very unsatisfactory results. Another scenario is one in which two or more images of the same scene photographed under different imaging conditions, e.g., images of a countryside taken at dusk or dawn under a clear or a cloudy sky. Using one of these images as a query example often fails to retrieve other images of the same scene taken under different time or conditions. In yet another situation maybe one in which a same scene imaged by different, uncalibrated devices. Using one image taken by one device may fail to find the same scene taken by other devices. In this paper, we present a method which uses a binary image tree [8] to partition an image recursively into hierarchical sub-images and introduce the Scene Structural Matrix (SSM), a 2-dimensional table to summarize the geometric structures of the H.-Y. Shum, M. Liao, and S.-F. Chang (Eds.): PCM 2001, LNCS 2195, pp. 921–926, 2001. c  Springer-Verlag Berlin Heidelberg 2001