Learn More
The objective of this paper is classifying images by the object categories they contain, for example motorbikes or dolphins. There are three areas of novelty. First, we introduce a descriptor that represents local image shape and its spatial layout, together with a spatial pyramid kernel. These are designed so that the shape correspondence between two(More)
We explore the problem of classifying images by the object categories they contain in the case of a large number of object categories. To this end we combine three ingredients: (i) shape and appearance representations that support spatial pyramid matching over a region of interest. This generalizes the representation of Lazebnik et al., (2006) from an image(More)
We investigate whether dimensionality reduction using a latent generative model is beneficial for the task of weakly supervised scene classification. In detail, we are given a set of labeled images of scenes (for example, coast, forest, city, river, etc.), and our objective is to classify a new image into one of these categories. Our approach consists of(More)
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised manner, and to use this object distribution to perform scene classification. We achieve this discovery using probabilistic Latent Semantic Analysis (pLSA), a generative model from(More)
Image segmentation has been, and still is, a relevant research area in Computer Vision, and hundreds of segmentation algorithms have been proposed in the last 30 years. However, it is well known that elemental segmentation techniques based on boundary or region information often fail to produce accurate segmentation results. Hence, in the last few years,(More)
A colour texture segmentation method which unifies region and boundary information is presented in this paper. The fusion of several approaches which integrate both information sources allows us to exploit the benefits of each one. We propose a segmentation method which uses a coarse detection of the perceptual (colour and texture) edges of the image to(More)
We present a new approach to model and classify breast parenchymal tissue. Given a mammogram, first, we will discover the distribution of the different tissue densities in an unsupervised manner, and second, we will use this tissue distribution to perform the classification. We achieve this using a classifier based on local descriptors and probabilistic(More)
We address the problem of traffic grooming in WDM rings with all-to-all uniform unitary traffic. We want to minimize the total number of SONET add-drop multiplexers (ADMs) required. This problem corresponds to a partition of the edges of the complete graph into subgraphs, where each subgraph has at most C edges (where C is the grooming ratio) and where the(More)
The one sided crossing minimization problem consists of placing the vertices of one part of a bipartite graph on prescribed positions on a straight line and finding the positions of the vertices of the second part on a parallel line and drawing the edges as straight lines such that the number of pairwise edge crossings is minimized. This problem represents(More)
Thousands of images are generated every day, which implies the necessity to classify, organise and access them using an easy, faster and efficient way. Scene classification, the classification of images into semantic categories (e.g. coast, mountains and streets), is a challenging and important problem nowadays. Many different approaches concerning scene(More)