This article presents the development of an active thermography algorithm capable of detecting defects in materials, based on the techniques of Thermographic Signal Reconstruction (TSR), Thermal Contrast (TC) and the ...
详细信息
This article presents the development of an active thermography algorithm capable of detecting defects in materials, based on the techniques of Thermographic Signal Reconstruction (TSR), Thermal Contrast (TC) and the physical principles of heat transfer. The results obtained from this algorithm are compared to the TSR technique and the raw thermogram obtained by stepped thermography inspection. Experimentally, a short thermal pulse is used and the surface temperature of the sample is monitored over time with an infrared camera. Due to the volume of data, the first step is data compression. Newton's law of cooling was used to store the normalized temperature data pixel-by-pixel over time and a compression ratio of 99% was obtained. The main contributions of the developed algorithm are: only four parameters for data compression and the concept of change in the direction of the heat flow to delimit the edges of the defects, where the borders are identified with a remarkable accuracy. Some well known image processing technique are also integrated to improve the thermal analysis: edge detection/interface between the sample and the image background;consolidation in a single image by aggregating the indicators referring to the concept of cooling/heating time constant, maximum thermal amplitude and contrast.
Matching of heterogeneous knowledge sources is of increasing importance in areas such as scientific knowledge management, e-commerce, enterprise application integration, and many emerging Semantic Web applications. Wi...
详细信息
Matching of heterogeneous knowledge sources is of increasing importance in areas such as scientific knowledge management, e-commerce, enterprise application integration, and many emerging Semantic Web applications. With the desire of knowledge sharing and reuse in these fields, it is common that the knowledge coming from different organizations from the same domain is to be matched. We propose a knowledge matching method based on our previously developed tree mining algorithms for extracting frequently occurring subtrees from a tree structured database such as XML. Using the method the common structure among the different representations can be automatically extracted. Our focus is on knowledge matching at the structural level and we use a set of example XML schema documents from the same domain to evaluate the method. We discuss some important issues that arise when applying tree mining algorithms for detection of common document structures. The experiments demonstrate the usefulness of the approach.
This paper presents a framework to generate multi-shaped detectors with valued negative selection algorithms (NSA). In particular, detectors can take the form of hyper-rectangles, hyper-spheres and hyper-ellipses in t...
详细信息
This paper presents a framework to generate multi-shaped detectors with valued negative selection algorithms (NSA). In particular, detectors can take the form of hyper-rectangles, hyper-spheres and hyper-ellipses in the non-self space. These novel pattern detectors (in the complement space) are evolved using a genetic search (the structured genetic algorithm), which uses hierarchical genomic structures and a gene activation mechanism to encode multiple detector shapes. This genetic search (the structured GA) allows in maintaining diverse shapes while contributing to the proliferation of best suited detector shapes in expressed phenotype. The results showed that a significant coverage of the non-self space could be achieved with fewer detectors compared to other NSA approaches (using only single-shaped detectors). The uniform representation scheme and the evolutionary mechanism used in this work can serve as a baseline for further extension to use several shapes, providing an efficient coverage of non-self space.
A new nonparametric algorithm of radar signal disorder detection is considered. The algorithm is based on spectral estimation of a few signal samples of some close windows and application of a nonparametric Wilkockson...
详细信息
A new nonparametric algorithm of radar signal disorder detection is considered. The algorithm is based on spectral estimation of a few signal samples of some close windows and application of a nonparametric Wilkockson's test to compare them. The algorithm can be used for radar signal detection specifically in the tasks of turbulence detection in clouds and precipitation as well as for moving target detection. The efficiency of the new algorithm is analyzed.
Glaucoma, the second leading cause of blindness worldwide, is an optic neuropthy characterized by distinctive changes in the optic nerve head (ONH) and visual field. In this context, the Heidelberg Retina Tomograph (H...
详细信息
ISBN:
(纸本)9781467364560
Glaucoma, the second leading cause of blindness worldwide, is an optic neuropthy characterized by distinctive changes in the optic nerve head (ONH) and visual field. In this context, the Heidelberg Retina Tomograph (HRT), a confocal scanning laser technology, has been commonly used to detect glaucoma and monitor its progression. In this paper, we present a new framework for detection of glaucomatour progression using the HRT images. In contrast to previous works that do not integrate a priori knowledge available on the images and particularly the spatial pixel dependency in the changedetection map, we propose the use of the Markov Random Field to handle a such dependency. To our knowledge, the task of inferring the glaucomatous changes with a Variational Expectation Maximization VEM algorithm will be used for the first time in the glaucoma diagnosis framework. We then compared the diagnostic performance of the proposed framework to existing methods of progression detection.
The classification of multispectral satellite images is a challenging problem and has a number of applications such as feature identification, changedetection, etc. We apply modified neural network algorithms: GA-BP ...
详细信息
The classification of multispectral satellite images is a challenging problem and has a number of applications such as feature identification, changedetection, etc. We apply modified neural network algorithms: GA-BP (genetic algorithm as precursor to the back propagation) and modular artificial neural network (MNN) to classify the LISS-3 image of Allahabad area. We also classify the resolution merged image (USS-3 with PAN) using the same algorithms. By using genetic algorithm as a precursor to ANN, we increase the probability of reaching to the global minimum, thus reducing the problem of a stuck neural network in the local minimum. MNN models the human brain more closely to apply task decomposition to the satellite images as well. The output of the above techniques are generated and analyzed.
Automatic analysis of digital video scenes often requires the segmentation of moving objects from the background. Historically, algorithms developed for this purpose have been restricted to small frame sizes, low fram...
详细信息
Automatic analysis of digital video scenes often requires the segmentation of moving objects from the background. Historically, algorithms developed for this purpose have been restricted to small frame sizes, low frame rates or offline processing. The simplest approach involves subtracting the current frame from the known background. However, as the background is unknown, the key is how to learn and model it. This paper proposes a new algorithm that represents each pixel in the frame by a group of clusters. The clusters are ordered according the likelihood they model the background and are adapted to deal with background and lighting variations. Incoming pixels are matched against the corresponding cluster group and are classified according to whether the matching cluster is considered part of the background. The algorithm has been subjectively evaluated against three other techniques. It demonstrated equal or better segmentation than the other techniques and proved capable of processing 320 /spl times/ 240 video at 28 fps, excluding post-processing.
In this letter a new power-based digital algorithm is introduced to provide protection for the generators against unbalanced faults. The algorithm measures the generator's three-phase power output and monitors the...
详细信息
In this letter a new power-based digital algorithm is introduced to provide protection for the generators against unbalanced faults. The algorithm measures the generator's three-phase power output and monitors the sinusoidal component of the instantaneous power. When the magnitude of the sinusoidal component exceeds a predefined value, the algorithm checks the direction of the negative sequence-reactive power flow to discriminate between internal and external faults. The proposed algorithm initiates fast tripping for internal asymmetrical faults, and provides back up protection for external unbalanced conditions.
暂无评论