No abstract

This paper presents a pioneering approach for weld bead detection in radiographic images obtained by the Double Wall Double Image (DWDI) technique. Such task constitutes an essential step for several high level processes, such as fully automatic flaw identification on welded joints. Sets of sample pixels, corresponding to candidate solutions provided by a genetic algorithm (GA), are compared to pre-defined synthetic weld bead and pipe models in an image matching procedure. The fitness of each set (individual) is evaluated based on a linear combination of its genotype (evaluated by a heuristic function) and phenotype. The evolutionary process automatically selects the best individual in the population and, thus, provides information such as position, orientation and dimension of the detected object. The proposed approach successfully detects pipes and weld beads in radiographic images of different complexities, encouraging future works.Index Terms-DWDI radiographic images, weld bead detection, genetic algorithms, phenotype and heuristic functions.U.S. Government work not protected by U.S.

This paper proposes a fuzzy classifier based on type-2 fuzzy sets to be applied in land cover classification. The classifier is built from the available data and considers the merging of information acquired from different experts. The data regards a thematic mapper representing the land cover of a real plain cultivated area. The experts are represented by different bands which discretize the spectral sensor information. The new method proposed to design the classifier as well as the use of general type-2 fuzzy sets allows the modeling of input-output relations and minimize the effects of uncertainties in the usual fuzzy rule-based classifiers. The experiments carried out attest the efficiency of the proposed general type-2 fuzzy classifier.

Resumo-Este artigo trata do problema da compressão de mapas de profundidade para aplicações de vídeo 3D, baseadas na síntese de vistas virtuais. Neste sentido,é proposto um algoritmo alternativo aos atuais padrões de codificação de imagem, que evita os problemas conhecidos na compressão de mapas de profundidade. O algoritmo propostoé baseado numa segmentação flexível e predição hierárquica, apropriados para a representação das bordas abruptas dos objetos. O sinal de resíduoé aproximado por uma função linear.Quando comparado com os algoritmos concorrentes, os experimentos mostram que os mapas de profundidade codificados pelo nosso algoritmo possuem desempenho estado-da-arte na síntese de vistas virtuais.Palavras-Chave-Codificação de mapas de profundidade, aproximação linear, codificação preditiva, síntese de vistas.Abstract-This paper studies the problem of depth map compression for 3D video applications, based on virtual view synthesis. In this context, we propose an alternative algorithm to the current image coding standards, which avoids the known problems of depth map compression. The proposed algorithm is based on a flexible segmentation, combined with an hierarchical prediction step, that efficiently represent the objects' sharp edges. The residue signal is approximated by a linear function.When compared to other alternative algorithms, the experiments show that depth maps compressed with our algorithm achieve state-of-the-art performance on virtual view synthesis.

This paper proposes a simple and innovative method to design rule bases for inference systems by joining wellknown theories to treat uncertainty, such as probability and fuzzy systems. The rule base design is based on some modifications in the Wang-Mendel method in the sense that all the information obtained from the training set can be considered. The proposed method provides fuzzy rules where each consequent is determined in a probabilistic way. The resulting fuzzy system is applied in a classification problem and has its performance compared with a fuzzy classifier obtained by the original Wang-Mendel method. The results show that the design method being proposed outperforms the traditional WM method, especially when data is noisy.