Self-organising neural networks for adaptive control

Self-organizing neural networks have been implemented in a wide range of application areas such as speech processing, image processing, optimization and robotics. Recent variations to the basic model proposed by the authors enable it to order state space using a subset of the input vector and to apply a local adaptation procedure that does not rely on a predefined test duration limit. Both these variations have been incorporated into a new feature map architecture that forms an integral part of an Hybrid Learning System (HLS) based on a genetic-based classifier system. Problems are represented within HLS as objects characterized by environmental features. Objects controlled by the system have preset targets set against a subset of their features. The system's objective is to achieve these targets by evolving a behavioural repertoire that efficiently explores and exploits the problem environment. Feature maps encode two types of knowledge within HLS — long-term memory traces of useful regularities within the environment and the classifier performance data calibrated against an object's feature states and targets. Self-organization of these networks constitutes non-genetic-based (experience-driven) learning within HLS. This paper presents a description of the HLS architecture and an analysis of the modified feature map implementing associative memory. Initial results are presented that demonstrate the behaviour of the system on a simple control task.

From lung images to lung models : a review

Automated 3D lung modeling involves analyzing 2D lung images and reconstructing a realistic 3D model of the lung. This paper presents a review of the existing works on automatic formation of 3D lung models from 2D lung images. A common framework for 3D lung modeling is proposed. It consists of eight components: image acquisition, image pre-processing, image segmentation, boundary creation, image recognition, image registration, 3D surface reconstruction, and 3D rendering and visualization. The algorithms used by the existing systems to implement these components are also reviewed.

On the automated interpretation and indexing of American football

This work combines natural language understanding and image processing with incremental learning to develop a system that can automatically interpret and index American Football. We have developed a model for representing spatio-temporal characteristics of multiple objects in dynamic scenes in this domain. Our representation combines expert knowledge, domain knowledge, spatial knowledge and temporal knowledge. We also present an incremental learning algorithm to improve the knowledge base as well as to keep previously developed concepts consistent with new data. The advantages of the incremental learning algorithm are that is that it does not split concepts and it generates a compact conceptual hierarchy which does not store instances.

Super-resolution of a 3-dimensional scene from novel viewpoints

Super-resolution is a method of post-processing image enhancement that increases the spatial resolution of video or images. Existing super-resolution techniques apply only to images captured of a planar scene. This paper aims to extend super-resolution concepts from the 2D domain to the 3D domain, drawing on ideas from both superresolution and multi-view geometry, two fields of research that until now have predominantly been studied in isolation. 2D super-resolution methods are not without their complexities and limitations. However, once multiple views of a scene are considered within a super-resolution framework, a new range of issues arise that must also be resolved. For example, when input images of a scene with variation in depth are considered, it is no longer clear how and where the images should be registered. This paper describes the use of sparse 3D reconstruction in order to ‘register’ the input images, which are then transferred to a novel image plane and combined to increase the perceived detail in the scene. Experimental results using real images captured from generally positioned input cameras are presented.

Automatic face recognition for film character retrieval in feature-length films

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

Correspondência estéreo usando imagens em multiresolução com profundidade variável

We propose a multi-resolution, coarse-to-fine approach for stereo matching, where the first matching happens at a different depth for each pixel. The proposed technique has the potential of attenuating several problems faced by the constant depth algorithm, making it possible to reduce the number of errors or the number of comparations needed to get equivalent results. Several experiments were performed to demonstrate the method efficiency, including comparison with the traditional plain correlation technique, where the multi-resolution matching with variable depth, proposed here, generated better results with a smaller processing time

Uso de técnicas de Geoprocessamento e Sensoriamento Remoto no levantamento e integração de dados necessários a gestão ambiental dos campos de extração de óleo e gás do Canto do Amaro e Alto da Pedra no município de Mossoró - RN

The objective of this work is to identify, to chart and to explain the evolution of the soil occupation and the envirionment vulnerability of the areas of Canto do Amaro and Alto da Pedra, in the city of Mossoró-RN, having as base analyzes it multiweather of images of orbital remote sensors, the accomplishment of extensive integrated works of field to a Geographic Information System (GIS). With the use of inserted techniques of it analyzes space inserted in a (GIS), and related with the interpretation and analyzes of products that comes from the Remote Sensoriamento (RS.), make possible resulted significant to reach the objectives of this works. Having as support for the management of the information, the data set gotten of the most varied sources and stored in digital environment, it comes to constitute the geographic data base of this research. The previous knowledge of the spectral behavior of the natural or artificial targets, and the use of algorithms of Processing of Digital images (DIP), it facilitates the interpretation task sufficiently and searchs of new information on the spectral level. Use as background these data, was generated a varied thematic cartography was: Maps of Geology, Geomorfológicals Units soils, Vegetation and Use and Occupation of the soil. The crossing in environment SIG, of the above-mentioned maps, generated the maps of Natural and Vulnerability envirionmental of the petroliferous fields of I Canto do Amaro and Alto da Pedra-RN, working in an ambient centered in the management of waters and solid residuos, as well as the analysis of the spatial data, making possible then a more complex analysis of the studied area

Diagnostic agreement of conventional and inverted scanned panoramic radiographs in the detection of the mandibular canal and the mental foramen.

The aim of this study was to evaluate the diagnostic agreement of conventional panoramic radiographs and their inverted scanned images in the detection of the mandibular canal and mental foramen. A total of 77 panoramic radiographs obtained from the files of totally edentulous patients were used. Digitization was done by means of a scanner with brightness and contrast adjustment, as well as image inversion. The extension of mandibular canal was divided into anterior, middle, and posterior regions, and the presence of a radiopaque line that characterized the mandibular canal was classified according to a 5-point confidence scale. The mental foramen was classified in 4 types: continuous, separated, diffuse, and unidentified. Both conventional and inverted scanned panoramic radiographs were evaluated by 3 calibrated implantologists at 2 distinct moments with a minimum interval of 10 days between them. Intraexaminer agreement was evaluated by Kappa statistics by point and by 95% confidence interval. Because the intraexaminer level of agreement was low, interexaminer agreements could not be carried out. The results showed a substantial (in 2 situations), moderate (in 16 situations), and fair (in 18 situations) intraexaminer agreement for mandibular canal and a substantial (in 1 situation), fair (in 1 situation), and moderate (in 10 situations) intraeaminer agreement for mental foramen. There were no statistically significant differences in most instances. In conclusion, the diagnostic agreement of conventional and inverted scanned panoramic radiographs for detection of mandibular canal and mental foramen was low.

Detection of highways in high resolution images using Mathematical Morphology techniques

This paper seeks to apply a routine for highways detection through the mathematical morphology tools in high resolution image. The Mathematical Morphology theory consists of describing structures geometric presents quantitatively in the image (targets or features). This explains the use of the Mathematical Morphology in this work. As high resolution images will be used, the largest difficulty in the highways detection process is the presence of trees and automobiles in the borders tracks. Like this, for the obtaining of good results through the use of morphologic tools was necessary to choose the structuring element appropriately to be used in the functions. Through the appropriate choice of the morphologic operators and structuring elements it was possible to detect the highways tracks. The linear feature detection using mathematical morphology techniques, can contribute in cartographic applications, as cartographic products updating.

Video target tracking by using competitive neural networks

A target tracking algorithm able to identify the position and to pursuit moving targets in video digital sequences is proposed in this paper. The proposed approach aims to track moving targets inside the vision field of a digital camera. The position and trajectory of the target are identified by using a neural network presenting competitive learning technique. The winning neuron is trained to approximate to the target and, then, pursuit it. A digital camera provides a sequence of images and the algorithm process those frames in real time tracking the moving target. The algorithm is performed both with black and white and multi-colored images to simulate real world situations. Results show the effectiveness of the proposed algorithm, since the neurons tracked the moving targets even if there is no pre-processing image analysis. Single and multiple moving targets are followed in real time.

Influence of anatomical location on CT numbers in cone beam computed tomography

Objective: To assess the influence of anatomical location on computed tomography (CT) numbers in mid- and full field of view (FOV) cone beam computed tomography (CBCT) scans. Study Design: Polypropylene tubes with varying concentrations of dipotassium hydrogen phosphate (K2HPO4) solutions (50-1200 mg/mL) were imaged within the incisor, premolar, and molar dental sockets of a human skull phantom. CBCT scans were acquired using the NewTom 3G and NewTom 5G units. The CT numbers of the K2HPO 4 phantoms were measured, and the relationship between CT numbers and K2HPO4 concentration was examined. The measured CT numbers of the K2HPO4 phantoms were compared between anatomical sites. Results: At all six anatomical locations, there was a strong linear relationship between CT numbers and K2HPO4 concentration (R 2 > 0.93). However, the absolute CT numbers varied considerably with the anatomical location. Conclusion: The relationship between CT numbers and object density is not uniform through the dental arch on CBCT scans. © 2013 Elsevier Inc.

Desenvolvimento de um programa computacional para classificação do uso da terra em imagens CBERS 2

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Ridge-based fingerprint matching using hough transform

Despite the efficacy of minutia-based fingerprint matching techniques for good-quality images captured by optical sensors, minutia-based techniques do not often perform so well on poor-quality images or fingerprint images captured by small solid-state sensors. Solid-state fingerprint sensors are being increasingly deployed in a wide range of applications for user authentication purposes. Therefore, it is necessary to develop new fingerprint-matching techniques that utilize other features to deal with fingerprint images captured by solid-state sensors. This paper presents a new fingerprint matching technique based on fingerprint ridge features. This technique was assessed on the MSU-VERIDICOM database, which consists of fingerprint impressions obtained from 160 users (4 impressions per finger) using a solid-state sensor. The combination of ridge-based matching scores computed by the proposed ridge-based technique with minutia-based matching scores leads to a reduction of the false non-match rate by approximately 1.7% at a false match rate of 0.1%. © 2005 IEEE.

EDGE-PRESERVING SPECKLE TEXTURE REMOVAL BY INTERFERENCE-BASED SPECKLE FILTERING FOLLOWED BY ANISOTROPIC DIFFUSION

Ultrasonography has an inherent noise pattern, called speckle, which is known to hamper object recognition for both humans and computers. Speckle noise is produced by the mutual interference of a set of scattered wavefronts. Depending on the phase of the wavefronts, the interference may be constructive or destructive, which results in brighter or darker pixels, respectively. We propose a filter that minimizes noise fluctuation while simultaneously preserving local gray level information. It is based on steps to attenuate the destructive and constructive interference present in ultrasound images. This filter, called interference-based speckle filter followed by anisotropic diffusion (ISFAD), was developed to remove speckle texture from B-mode ultrasound images, while preserving the edges and the gray level of the region. The ISFAD performance was compared with 10 other filters. The evaluation was based on their application to images simulated by Field II (developed by Jensen et al.) and the proposed filter presented the greatest structural similarity, 0.95. Functional improvement of the segmentation task was also measured, comparing rates of true positive, false positive and accuracy. Using three different segmentation techniques, ISFAD also presented the best accuracy rate (greater than 90% for structures with well-defined borders). (E-mail: fernando.okara@gmail.com) (C) 2012 World Federation for Ultrasound in Medicine & Biology.