Image indexing and retrieval using an ART-2A neural network architecture

Traditional content-based image retrieval (CBIR) systems use low-level features such as colors, shapes, and textures of images. Although, users make queries based on semantics, which are not easily related to such low-level characteristics. Recent works on CBIR confirm that researchers have been trying to map visual low-level characteristics and high-level semantics. The relation between low-level characteristics and image textual information has motivated this article which proposes a model for automatic classification and categorization of words associated to images. This proposal considers a self-organizing neural network architecture, which classifies textual information without previous learning. Experimental results compare the performance results of the text-based approach to an image retrieval system based on low-level features. (c) 2008 Wiley Periodicals, Inc.

Histological Outcomes on the Development of New Space-making Devices for Maxillary Sinus Floor Augmentation

Background: Previous studies have pointed out that the mere elevation of the maxillary sinus membrane promotes bone formation without the use of augmentation materials. Purpose: This experimental study aimed at evaluating if the two-stage procedure for sinus floor augmentation could benefit from the use of a space-making device in order to increase the bone volume to enable later implant installation with good primary stability. Materials and Methods: Six male tufted capuchin primates (Cebus apella) were subjected to extraction of the three premolars and the first molar on both sides of the maxilla to create an edentulous area. The sinuses were opened using the lateral bone-wall window technique, and the membrane was elevated. One resorbable space-making device was inserted in each maxillary sinus, and the bone window was returned in place. The animals were euthanatized after 6 months, and biopsy blocks containing the whole maxillary sinus and surrounding soft tissues were prepared for ground sections. Results: The histological examination of the specimens showed bone formation in contact with both the schneiderian membrane and the device in most cases even when the device was displaced. The process of bone formation indicates that this technique is potentially useful for two-stage sinus floor augmentation. The lack of stabilization of the device within the sinus demands further improvement of space-makers for predictable bone augmentation. Conclusions: It is concluded that (1) the device used in this study did not trigger any important inflammatory reaction; (2) when the sinus membrane was elevated, bone formation was a constant finding; and (3) an ideal space-making device should be stable and elevate the membrane to ensure a maintained connection between the membrane and the secluded space.

A novel MAP-MRF approach for multispectral image contextual classification using combination of suboptimal iterative algorithms

In this paper we present a novel approach for multispectral image contextual classification by combining iterative combinatorial optimization algorithms. The pixel-wise decision rule is defined using a Bayesian approach to combine two MRF models: a Gaussian Markov Random Field (GMRF) for the observations (likelihood) and a Potts model for the a priori knowledge, to regularize the solution in the presence of noisy data. Hence, the classification problem is stated according to a Maximum a Posteriori (MAP) framework. In order to approximate the MAP solution we apply several combinatorial optimization methods using multiple simultaneous initializations, making the solution less sensitive to the initial conditions and reducing both computational cost and time in comparison to Simulated Annealing, often unfeasible in many real image processing applications. Markov Random Field model parameters are estimated by Maximum Pseudo-Likelihood (MPL) approach, avoiding manual adjustments in the choice of the regularization parameters. Asymptotic evaluations assess the accuracy of the proposed parameter estimation procedure. To test and evaluate the proposed classification method, we adopt metrics for quantitative performance assessment (Cohen`s Kappa coefficient), allowing a robust and accurate statistical analysis. The obtained results clearly show that combining sub-optimal contextual algorithms significantly improves the classification performance, indicating the effectiveness of the proposed methodology. (C) 2010 Elsevier B.V. All rights reserved.