semantic concepts

generating semantic concepts for images from their low-level visual features. The proposed system is built in two stages. First, an adaptation of k-means clustering using a non-Euclidean similarity metric is applied to discover the natural patterns of the data in the low-level feature space; the cluster

We present an innovative approach for storing and processing extracted low-level image features based on current Semantic Web technologies. We propose to use the COMM multimedia ontology as a “semantic ” alternative to the MPEG-7 standard, which is at the same time largely compliant with it. We

Abstract. In this work, we study people’s emotions evoked by viewing abstract art images based on traditional low-level image features within a binary classification framework. Abstract art is used here instead of artistic or photographic images because those contain contextual information

We contribute a novel gaze estimation technique, which is adaptable for person-independent applications. In a study with 17 participants, using a standard webcam, we recorded the subjects ’ left eye images for different gaze locations. From these images, we extracted five types of basic visual

We show a learning-based method for low-level vision problems. We set-up a Markov network of patches of the image and the underlying scene. A factorization approximation allows us to easily learn the parameters of the Markov network from synthetic examples of image/scene pairs, and to e ciently

-estimators of location is also established. Algorithms for two low-level vision tasks, discontinuity preserving smoothing and image segmentation are described as applications. In these algorithms the only user set parameter is the resolution of the analysis, and either gray level or color images are accepted as input

). We have developed and implemented two new algorithms; the first one is based on the computation of a set of geometrical features, such as nose width and length, mouth position, and chin shape, and the second one is based on almost-grey-level template matching. The results obtained on the testing sets

scales for further analysis. This article proposes a systematic methodology for dealing with this problem. A framework is proposed for generating hypotheses about interesting scale levels in image data, based on a general principle stating that local extrema over scales of different combinations of γ

An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons