Search results for "computer vision"
showing 10 items of 2353 documents
A novel dynamic multi-model relevance feedback procedure for content-based image retrieval
2016
This paper deals with the problem of image retrieval in large databases with a big semantic gap by a relevance feedback procedure. We present a novel algorithm for modelling the users's preferences in the content-based image retrieval system.The proposed algorithm considers the probability of an image belonging to the set of those sought by the user, and estimates the parameters of several local logistic regression models whose inputs are the low-level image features. A Principal Component Analysis method is applied to the original vector to reduce its high dimensionality. The relevance probabilities predicted by these local models are combined by means of a weighted average. These weights …
Regularization Method in Infrared Image Processing
2003
Abstract Infrared images often present distortions induced by the measurement system. Thus, image processing is a vital part of infrared measurements. A distortion model based on a convolution product is presented. Image restoration is an ill-posed problem and its solution can be obtained using regularization methods. In this paper, image restoration is performed using a variation of Tikhonov regularization that makes use of the particular form of the convolution kernel matrix, which is built as a block-circulant matrix that admits a diagonal form in the two-dimensional Fourier space. The restoration procedure is used to restore a knife-edge infrared source image.
Comparison of basis functions for 3D PET reconstruction using a Monte Carlo system matrix.
2012
In emission tomography, iterative statistical methods are accepted as the reconstruction algorithms that achieve the best image quality. The accuracy of these methods relies partly on the quality of the system response matrix (SRM) that characterizes the scanner. The more physical phenomena included in the SRM, the higher the SRM quality, and therefore higher image quality is obtained from the reconstruction process. High-resolution small animal scanners contain as many as 103?104 small crystal pairs, while the field of view (FOV) is divided into hundreds of thousands of small voxels. These two characteristics have a significant impact on the number of elements to be calculated in the SRM. …
Stiffness-Adaptive Taylor method for the integration of non-stiff and stiff kinetic models
1992
A systematic derivation procedure that greatly facilitates the application of the Taylor method to the integration of kinetic models is developed. In addition, an algorithm that gives the integration step as a function of the required level of accuracy is proposed. Using the Taylor method, application of this algorithm is immediate and largely reduces the integration time. In addition, a new method of integration of kinetic models, whose most important feature is the self-adaptability to the stiffness of the system along the integration process, is developed. This “stiffness-adaptive” Taylor method (SAT method) makes use of several algorithms, combining them to meet the particular requireme…
Color memory matching: Time effect and other factors
1998
The methods of simultaneous and successive, or memory, color matching have been compared for 10 color reference samples distributed in two groups each performed by 50 observers (25 men and 25 women). Our results, obtained with a total of two hundred Munsell color chips arrayed on ten gray cardboard panels, indicate that: (a) while by simultaneous matching the mean color differences obtained are, in most cases, lower than 1 CIELAB unit, those obtained by memory are generally higher; (b) the worst remembered colors are yellow, light green, blue, and pink, and the best remembered color is orange; (c) the influence of the delay time (15 s, 15 min, and 24 h) is significant for the remembered mea…
<title>Electronic eye occluder with time-counting and reflection control</title>
2008
ABSTRACT In pediatric ophthalmology 2 3 % of all the children are impacted by a visual pathology amblyopia. It develops if a clear image isnt presented to the retina during an early stage of the developmen t of the visual system. A common way of treating this pathology is to cover the better-seeing eye to force the lazy eye to learn seeing. However, children are often reluctant to wear such an occluder because they are as hamed or simply because they find it inconvenient. This fact requires to find a way how to track the regi me of occlusion because results of occlus ion is a hint that the actual regime of occlusion isnt that what the optometrist has recommended. We design an electr…
Sensor Fusion Combining 3-D and 2-D for Depth Data Enhancement
2012
Time-of-Flight (ToF) cameras are known to be cost-efficient 3-D sensing systems capable of providing full scene depth information at a high frame rate. Among many other advantages, ToF cameras are able to provide distance information regardless of the illumination conditions and with no texture dependency, which makes them very suitable for computer vision and robotic applications where reliable distance measurements are required. However, the resolution of the given depth maps is far below the resolution given by standard 2-D video cameras which, indeed, restricts the use of ToF cameras in real applications such as those for safety and surveillance. In this thesis, we therefore investigate…
Global flow impacts time-to-passage judgments based on local motion cues
2011
AbstractWe assessed the effect of the coherence of optic flow on time-to-passage judgments in order to investigate the strategies that observers use when local expansion information is reduced or lacking. In the standard display, we presented a cloud of dots whose image expanded consistent with constant observer motion. The dots themselves, however, did not expand and were thus devoid of object expansion cues. Only the separations between the dots expanded. Subjects had to judge which of two colored target dots, presented at different simulated depths and lateral displacements would pass them first. Image velocities of the target dots were chosen so as to correlate with time-to-passage only…
An Automated Visual Inspection System for the Classification of the Phases of Ti-6Al-4V Titanium Alloy
2013
Metallography is the science of studying the physical properties of metal microstructures, by means of microscopes. While traditional approaches involve the direct observation of the acquired images by human experts, Com-puter Vision techniques may help experts in the analysis of the inspected mate-rials. In this paper we present an automated system to classify the phases of a Titanium alloy, Ti-6Al-4V. Our system has been tested to analyze the final products of a Friction Stir Welding process, to study the states of the micro-structures of the welded material.
Discrete Tomography Reconstruction Through a New Memetic Algorithm
2008
Discrete tomography is a particular case of computerized tomography that deals with the reconstruction of objects made of just one homogeneous material, where it is sometimes possible to reduce the number of projections to no more than four. Most methods for standard computerized tomography cannot be applied in the former case and ad hoc techniques must be developed to handle so few projections.