Almeria, holding the only dessert area of continental Europe, is a semiarid province located southeast the Iberian Peninsula. The development status of the different counties of the province is widely different. Near the coast, greenhouse growing and tourism have
generated an extremely active economic area. On the other side, inner areas of the province have gone down economically, with the reduction of mining and classic grows. In order to analyze new development alternatives, we built ESTIARA-Sig for the Ministry of Agriculture of Andalusia; our main objective developing this GIS was to catalog the different resources of the whole province to support development decisions. It includes four types of information: a) alphanumeric data (36 groups/tables, relative to statistics and resources), b) vectorial data (including the cartography), c) raster geographical data (obtained from satellite images, they let us to differentiate specifically greenhouse growing, populated and other areas), and d) photographic images (including types of constructions or special
locations). A dynamic user interface was added to facilitate its use. In this work, we present main characteristics of the system and analyze their use along last six years, presenting as conclusions the experience obtained in order to develop a new version.
There is a wide set of digital images, where the problem of detecting specific structures is filtering between multiple and complex lines and secondary elements. The real problem is extracting relevant information from images, discarding uninteresting information previously, during and after the segmentation process. In this work, we resume the advantages and disadvantages of each approach, concluding a basic preference of filtering as soon as possible. In this sense, we present a method of filtering during segmentation, which mixes the mobile windows and the seeded regions approaches. Main steps are: 1) The whole image is divided in windows with a size related with the searched structures; 2) Previous knowledge about the location of the searched elements is applied to reduce the number of windows; 3) The number of windows is reduced using distribution and compacity conditions; 4) The population of each work windows is analyzed to fix one threshold; 5) Filtered work pairs are segmented using simple two populations criteria; 6) Analyzing the detected segments, the list of work window-threshold pairs is extended to include new windows. Most relevant result is the definition of a new
border based segmentation approach, which gives good results searching specific objects in complex images.