Geoprocessamento e sensoriamento remoto aplicado na determinação da aptidão agrícola de uma microbacia

Soil use for the development of activities as agriculture and livestock has been causing great alterations in the environment, mainly when these are practiced intensively, disrespecting the fragility and aptitude of the natural resources. Therefore, it is essential that the planning of the agricultural activities is done, taking into consideration the several environmental criteria involved in the decision-making process. Thus, this study aimed to analyze the agricultural aptitude classes of lands from a watershed through geographical information system (GIS). The Arroio Ajuricaba watershed is located in the Municipality of Marechal Cândido Rondon - PR among the coordinates UTM 787309m E and 793892m E; 7275026m N and 7281310m N, in the Spindle 21, presenting an area of 1681ha. Soil maps, in semi detail scale, was the digital cartographic base used. The results allowed to conclude that 42.41% of the basin presented a good aptitude for farming in handling level of high technology (handling level C), regular aptitude for B, and restricted aptitude for A [class 1(a)bC] and that 12% of the area had regular aptitude for farming in the three handling levels (class 1abc). The watershed lands (14.24%) presented regular aptitude for farming in handling level C, restricted aptitude for B, and inapt for A [class of aptitude 2(b)c]; 15.85% presented good aptitude for planted pasture (class 4P) and 12.21% were considered without aptitude for agricultural use (class 6). We can say that 71.94% of the lands has aptitude for farming, although they present different degrees of limitations that request different treatments for its conservation.

Edge detection in digital images using fuzzy numbers

The purpose of this paper is to introduce a new approach for edge detection in grey shaded images. The proposed approach is based on the fuzzy number theory. The idea is to deal with the uncertainties concerning the grey shades making up the image and, thus, calculate the appropriateness of the pixels in relation to a homogeneous region around them. The pixels not belonging to the region are then classified as border pixels. The results have shown that the technique is simple, computationally efficient and with good results when compared with both the traditional border detectors and the fuzzy edge detectors. Copyright © 2009, Inderscience Publishers.

Infrared face recogniton by optimum-path forest

This paper presents a novel, fast and accurate appearance-based method for infrared face recognition. By introducing the Optimum-Path Forest classifier, our objective is to get good recognition rates and effectively reduce the computational effort. The feature extraction procedure is carried out by PCA, and the results are compared to two other well known supervised learning classifiers; Artificial Neural Networks and Support Vector Machines. The achieved performance asserts the promise of the proposed framework. ©2009 IEEE.

Assessment of manipulation accuracy of digitized occlusal radiographic images--sub and over exposure.

The aim of this study was to evaluate whether digitized images obtained from occlusal radiographs taken with low or over dose of radiation could be improved with the aid of computer software for digital treatment. Thirteen occlusal radiographs of a dry skull were taken employing 13 different exposure times. The radiographs were digitized and then manipulated with the program for image editing. 143 evaluations were performed by specialists in dental radiology who classified radiographs as appropriate or not appropriate for interpretation. Test Z was used for statistical analysis of the data and the results showed that it is possible to manipulate digitized radiographic images taken with 75% of the ideal exposure time and to make them suitable for interpretation and diagnosis. Conversely, it was concluded that the over exposed images, 57.50% above the standard exposure time, were inadequate.

Morphological routine proposal to extraction of highways in digital images of high resolution

This research proposes to apply techniques of Mathematics Morphology to extract highways in digital images of high resolution, targeting the upgrade of cartographic products. Remote Sensing data and Mathematical Morphological techniques were integrated in the process of extraction. Mathematical Morphology's objective is to improve and extract the relevant information of the visual image. In order to test the proposed approach some morphological operators related to preprocess, were applied to the original images. Routines were implemented in the MATLAB environment. Results indicated good performances by the implemented operators. The integration of the technologies aimed to implement the semiautomatic extraction of highways with the purpose to use them in processes of cartographic updating.