Proceedings XIV Brazilian Symposium on Computer Graphics and Image Processing

Machine design of a signal or image operator involves estimating the optimal filter from sample data. In principle, relative to the error measure used, the optimal filter is best; however, owing to design error, the designed filter might not perform well. In general it is suboptimal. The envelope constraint involves using two humanly designed filters that form a lower and upper bound for the desig... View full abstract»

DNA chips (i.e., microarrays) biotechnology is a hybridization (i.e., DNA matching) based process that makes it possible to quantify the relative abundance of mRNA from two distinct samples by analysing their fluorescence signals. This technique requires robotic placement (i.e., spotting) of thousands of cDNAs (i.e., complementary DNA) in an array format on glass microscope slides which provide ge... View full abstract»

Oscillatory neural networks are a relatively recent approach for the problem of image segmentation. Inside of this context, the oscillator neuron of Terman-Wang is presented, which is used as base element of an oscillatory network called LEGION (Locally Excitatory Globally Inhibitory Oscillator Network). The continuous version of the LEGION network, based on a set of differential equations, presen... View full abstract»

The purpose of this work is to identify pollen grains from its sample images. Pollen grain recognition is used for the classification of the apiaria samples. In this paper we present an image retrieval technique that is being applied to pollen grain identification, based on querying a database of reference neural networks View full abstract»

This paper presents an object-oriented approach for creating multi-region non-manifold models with NURBS. The main motivation is that the geometry and shape of realistic engineering objects are intrinsically complex, usually composed by several materials and regions. Therefore, automatic and/or adaptive meshing algorithms have become revealed themselves quite useful to increase the reliability of ... View full abstract»

The estimation of left ventricle motion and deformation from series of images has been an area of attention in the medical image analysis and still remains and open and challenging problem. The proper motion tracking of left ventricle wall can contribute to isolate the location and extent of ischemic or infarcted myocardium. We present a method that automatically estimates the velocity vector fiel... View full abstract»

We propose an integrated framework in which local perception and close manipulation skills are used in conjunction with a high-level behavioral interface based on a "smart object" paradigm as support for a virtual agent to perform autonomous tasks. In our model, virtual "smart objects" encapsulate information about possible interactions between the agent and its environment, including sub-tasks de... View full abstract»

Using digital image processing and pattern recognition techniques, a supervised classification procedure of bamboo vascular bundles was developed and tested on polished cross sections of bamboo culms from four different species. Results obtained for same species samples were similar and were consistent with visual observations View full abstract»

We present an algorithm for computing a robust adaptive polygonal approximation of an implicit curve in the plane. The approximation is adapted to the geometry of the curve because the length of the edges varies with the curvature of the curve. Robustness is achieved by combining interval arithmetic and automatic differentiation View full abstract»

The paper recalls the idea of classification trees in OCR (optical character recognition) systems and proposes a technique for the automatic design of these classification trees. The design of both the classification trees and of the classification operators are based on training from sample pairs of observed-ideal images, allowing the development of customized OCRs View full abstract»

This work presents a simpler method to obtain fingerprint classification by means of directional map smoothing developed in C++ programming language through statistical techniques. That strategy allows to extract attributes of an image to increase the quality because it is possible to reduce the noise if compared with the result obtained by other methods exposed in the literature View full abstract»

We present a computational framework for semi-automated assessment of skeletal age based on a multi-scale image analysis approach. Through 2D digital X-ray images of the left hand, maturity indicators are searched by means of a two-step process: the user interactively indicates a point inside the middle finger, and the computational method analyzes the image intensity profile along this line, sear... View full abstract»

An effective method for the analysis of donated corneas consists in the evaluation of the indexes of cellular density, pleomorphism and polimegatism. We have developed a system attached to the slit lamp and dedicated software for image treating and analysis of the referred indexes using the mathematical morphology procedure. The results of automatic determination of the cellular density has a corr... View full abstract»

This paper reports new results of a project to build virtual worlds aimed at the graphic simulation of an arena where small mobile robots can perform requested tasks while behaving according to their own motivation and reasoning. Each robot is an intelligent agent that perceives the virtual environment via a simulated vision system and reacts to translating or rotating its body by driving its own ... View full abstract»

In this paper, we propose a video watermarking technique to hide copyright information in MPEG motion vector. In this method, watermark is embedded in larger value motion vectors, and specially in the less phase angle changed component. Then, the motion vector is modified into a new bitstream from which the watermark information can be easily retrieved. From the experimental results, it indicates ... View full abstract»

We present a hierarchical method to match regions in image sequences based in graph theory. First, we build a graph representation for each image, the so-called tree of critical lakes, used in the multiscale watershed. In a second step, assignments between regions in subsequent images are accomplished through maximum clique detection in a association graph View full abstract»

In this paper we present an algorithm for estimating the rotation index of a closed loop from the number of singular points on it. On the basis of this index we also devise a procedure that guarantees to have an arbitrary loop being traced only once. Combining this procedure with a higher-order stepping algorithm, a robust intersection technique is resulted View full abstract»

This paper presents a novel approach to the real-time rendering of complex scenes problem. Up to the present date, a huge number of acceleration techniques have been proposed, although most are geared towards a specific kind of scene. Instead of using a single, or a fixed set of rendering acceleration techniques, we propose the use of several, and to select the best one based on the current viewpo... View full abstract»

The paper presents a procedure to implement an automatic system for supervised pattern recognition with an ongoing learning capability. The purpose is to continuously increase the knowledge of the system and, accordingly, to enhance its performance in classification tasks. The nearest neighbor rule is employed as the central classifier and several techniques are added to cope with the increase in ... View full abstract»

fMRI is a non-invasive technique to evaluate brain areas related to a requested task. The event-related fMRI is one kind of its design, which permits not only spatial resolution, but also temporal correlation. This information may be more easily understood by the clinicians, if showed in a dynamic way. The aim of this paper is to describe a fMRI visualization system to expose the brain images, in ... View full abstract»

This paper presents a methodology to support farm decision-making by characterizing regional potential and climatic risks involved during agricultural crop cycles. It introduces agricultural zoning based on a system that classifies digital images of agroclimatic indices. The methodology uses as a first step analysis and processing of climatic data from weather stations through GIS tools. These res... View full abstract»

In this paper we apply reversible integer wavelet transform to lossless compression of computerized tomography projections (sinograms). Lossy image compression methods can achieve high compression ratios, but sinograms should not loose information during compression process to not affect the image reconstruction View full abstract»

The article provides a research in pattern recognition using a hardware implemented classifier based on morphological associative memory (MAM). Most neural network (NN) models used for this purpose have a complex learning rule. Instead, we propose a morphological classifier that has a simple learning rule based on mathematical morphology and presents an infinity storage capacity. Initially, we def... View full abstract»