Andreza Mendonça

Two-dimensional discriminative filters for image template detection

The image template detection is usually a very important halfway step for a computational vision algorithm. In general, the basic idea of this type of algorithm is to receive an input image and generate a set of lines, borders, edges and other well known geometrical forms as outputs. Ben-Arie and Rao (1993) have proposed a linear filter that, given a template, maximizes the energy concentration in a single sample of its output. We propose a two-dimensional generalization of this method, formulating the template matching problem as a multivariable optimization. Three different objective functions are investigated. Simulation results show that the proposed method performs well on real images.

MANUTENÇÃO DOS RECURSOS NATURAIS NA FLORESTA NACIONAL DO BOM FUTURO E SEU ENTORNO, RONDÔNIA, BRASIL

In Brazil are recorded 65 National Forests (Flonas), with 32 of these located in the Amazon , representing 3.13% of total federal units that region. In Rondonia,3 Flonas were created (Bom Futuro, Jamari e Jacunda), and there is little information on the conservation status of these units. Thus, the overall objective was to avaliate the maintenance of natural resources in Flona Bom Futuro and its surroundings, located in the northwestern portion of the state of Rondonia, in the periods 1986-2011 through geoprocessing. The digital image processing, obtaining landscape metrics and location of the area were made using the software Processing Geographic Information Systems (Spring), version 5.1.8 that is available for free by the Institute for Space Research - INPE of Brazil website and gvsig , version 1.9, obtaining data mapping on a scale of 1: 50000. It was used the model of the Earth South American Datum (SAD- 69) and the Universal Transverse Mercator Projection System (UTM). The entire procedure for calculation of areas was performed with the buffer zone of 10km, thus the information represented 606.000ha plan for the first three years analyzed (1986 , 1996 and 2006 ) and approximately 389.576ha for the year 2011 , due to reduction Flona. The study showed an increasing of anthropogenic fires and occupation, due to decreased vegetation. Also showed that the reduction of Flona not contributed to the maintenance of natural resources.

Reduced cross-discrimination for discriminative filters

Image template detection is usually a very important halfway step for a computational vision algorithm. A recently proposed approach for it involves the use of discriminative filters. For a given template, they maximize the energy concentration in a single sample of its output. In this paper, we propose an extension for them that allows multiple template discrimination with reduced cross discrimination, using impulse restoration techniques. Simulation results suggest that the proposed method performs well, being an effective tool for decision problems.