Classification of textures seen from different distances and under varying illumination direction

Changes in the angle of illumination incident upon a 3D surface texture can significantly alter its appearance, implying variations in the image texture. These texture variations produce displacements of class members in the feature space, increasing the failure rates of texture classifiers. To avoid this problem, a model-based texture recognition system which classifies textures seen from different distances and under different illumination directions is presented in this paper. The system works on the basis of a surface model obtained by means of 4-source colour photometric stereo, used to generate 2D image textures under different illumination directions. The recognition system combines coocurrence matrices for feature extraction with a Nearest Neighbour classifier. Moreover, the recognition allows one to guess the approximate direction of the illumination used to capture the test image

A new approach to the classification of mammographic masses and normal breast tissue

A new approach to mammographic mass detection is presented in this paper. Although different algorithms have been proposed for such a task, most of them are application dependent. In contrast, our approach makes use of a kindred topic in computer vision adapted to our particular problem. In this sense, we translate the eigenfaces approach for face detection/classification problems to a mass detection. Two different databases were used to show the robustness of the approach. The first one consisted on a set of 160 regions of interest (RoIs) extracted from the MIAS database, being 40 of them with confirmed masses and the rest normal tissue. The second set of RoIs was extracted from the DDSM database, and contained 196 RoIs containing masses and 392 with normal, but suspicious regions. Initial results demonstrate the feasibility of using such approach with performances comparable to other algorithms, with the advantage of being a more general, simple and cost-effective approach

Using appearance and context for outdoor scene object classification

We propose a probabilistic object classifier for outdoor scene analysis as a first step in solving the problem of scene context generation. The method begins with a top-down control, which uses the previously learned models (appearance and absolute location) to obtain an initial pixel-level classification. This information provides us the core of objects, which is used to acquire a more accurate object model. Therefore, their growing by specific active regions allows us to obtain an accurate recognition of known regions. Next, a stage of general segmentation provides the segmentation of unknown regions by a bottom-strategy. Finally, the last stage tries to perform a region fusion of known and unknown segmented objects. The result is both a segmentation of the image and a recognition of each segment as a given object class or as an unknown segmented object. Furthermore, experimental results are shown and evaluated to prove the validity of our proposal

The role of different factors related to social impact of heavy events: considerations about the intensity thresholds in densely populated areas

In the assessment of social impact caused by meteorological events, factors of different natures need to be considered. Not only does hazard itself determine the impact that a severe weather event has on society, but also other features related to vulnerability and exposure. The requests of data related to insurance claims received in meteorological services proved to be a good indicator of the social impact that a weather event causes, according to studies carried out by the Social Impact Research Group, created within the framework of the MEDEX project. Taking these requests as proxy data, diverse aspects connected to the impact of heavy rain events have been studied. The rainfall intensity, in conjunction with the population density, has established itself as one of the key factors in social impact studies. One of the conclusions we obtained is that various thresholds of rainfall should be applied for areas of varying populations. In this study, the role of rainfall intensity has been analysed for a highly populated urban area like Barcelona. A period without significant population changes has been selected for the study to minimise the effects linked to vulnerability and exposure modifications. First, correlations between rainfall recorded in different time intervals and requests were carried out. Afterwards, a method to include the intensity factor in the social impact index was suggested based on return periods given by intensity duration frequency (IDF) curves.

Torrential rainfall in northeast of the Iberian Peninsula: synoptic patterns and WeMO influence

This study presents a catalogue of synoptic patterns of torrential rainfall in northeast of the Iberian Peninsula (IP). These circulation patterns were obtained by applying a T-mode Principal Component Analysis (PCA) to a daily data grid (NCEP/NCAR reanalysis) at sea level pressure (SLP). The analysis made use of 304 days which recorded >100 mm in one or more stations in provinces of Barcelona, Girona and Tarragona (coastland area of Catalonia) throughout the 1950-2005 period. The catalogue comprises 7 circulation patterns showing a great variety of atmospheric conditions and seasonal or monthly distribution. Likewise, we computed the mean index value of the Western Mediterranean Oscillation index (WeMOi) for the synoptic patterns obtained by averaging all days grouped in each pattern. The results showed a clear association between the negative values of this teleconnection index and torrential rainfall in northeast of the IP. We therefore put forward the WeMO as an essential tool for forecasting heavy rainfall in northeast of Spain

A Method for Sky-Condition Classification from Ground-Based Solar Radiation Measurements

Identification of clouds from satellite images is now a routine task. Observation of clouds from the ground, however, is still needed to acquire a complete description of cloud conditions. Among the standard meteorologicalvariables, solar radiation is the most affected by cloud cover. In this note, a method for using global and diffuse solar radiation data to classify sky conditions into several classes is suggested. A classical maximum-likelihood method is applied for clustering data. The method is applied to a series of four years of solar radiation data and human cloud observations at a site in Catalonia, Spain. With these data, the accuracy of the solar radiation method as compared with human observations is 45% when nine classes of sky conditions are to be distinguished, and it grows significantly to almost 60% when samples are classified in only five different classes. Most errors are explained by limitations in the database; therefore, further work is under way with a more suitable database