Search results for " ANN"

Automatic Image Annotation Using Random Projection in a Conceptual Space Induced from Data

2018

The main drawback of a detailed representation of visual content, whatever is its origin, is that significant features are very high dimensional. To keep the problem tractable while preserving the semantic content, a dimen- sionality reduction of the data is needed. We propose the Random Projection techniques to reduce the dimensionality. Even though this technique is sub-optimal with respect to Singular Value Decomposition its much lower computational cost make it more suitable for this problem and in par- ticular when computational resources are limited such as in mobile terminals. In this paper we present the use of a "conceptual" space, automatically induced from data, to perform automa…

Three-domain image representation for personal photo album management

2010

In this paper we present a novel approach for personal photo album management. Pictures are analyzed and described in three representation spaces, namely, faces, background and time of capture. Faces are automatically detected and rectified using a probabilistic feature extraction technique. Face representation is then produced by computing PCA (Principal Component Analysis). Backgrounds are represented with low-level visual features based on RGB histogram and Gabor filter bank. Temporal data is obtained through the extraction of EXIF (Exchangeable image file format) data. Each image in the collection is then automatically organized using a mean-shift clustering technique. While many system…

Image Recognition through Incremental Discriminative Common Vectors

2010

An incremental approach to the discriminative common vector (DCV) method for image recognition is presented. Two different but equivalent ways of computing both common vectors and corresponding subspace projections have been considered in the particular context in which new training data becomes available and learned subspaces may need continuous updating. The two algorithms are based on either scatter matrix eigendecomposition or difference subspace orthonormalization as with the original DCV method. The proposed incremental methods keep the same good properties than the original one but with a dramatic decrease in computational burden when used in this kind of dynamic scenario. Extensive …

ChiLab4It system in the QA4FAQ competition

2017

ChiLab4It is the Question Answering system (QA) for Frequently Asked Questions (FAQ) developed by the Computer-Human Interaction Laboratory (ChiLab) at the University of Palermo for participating to the QA4FAQ task at EVALITA 2016 competition. The system is the versioning of the QuASIt framework developed by the same authors, which has been customized to address the particular task. This technical report describes the strategies that have been imported from QuASIt for implementing ChiLab4It, the actual system implementation, and the comparative evaluations with the results of the other participant tools, as provided by the organizers of the task. ChiLab4It was the only system whose score re…

Speeding up of microstructure reconstruction: II. Application to patterns of poly-dispersed islands

2015

We report a fast, efficient and credible statistical reconstruction of any two-phase patterns of islands of miscellaneous shapes and poly-dispersed in sizes. In the proposed multi-scale approach called a weighted doubly-hybrid, two different pairs of hybrid descriptors are used. As the first pair, we employ entropic quantifiers, while correlation functions are the second pair. Their competition allows considering a wider spectrum of morphological features. Instead of a standard random initial configuration, a synthetic one with the same number of islands as that of the target is created by a cellular automaton. This is the key point for speeding-up of microstructure reconstruction, making u…

Statistical Reconstruction of Microstructures Using Entropic Descriptors

2018

We report a multiscale approach of broad applicability to stochastic reconstruction of multiphase materials, including porous ones. The approach devised uses an optimization method, such as the simulated annealing (SA) and the so-called entropic descriptors (EDs). For a binary pattern, they quantify spatial inhomogeneity or statistical complexity at discrete length-scales. The EDs extract dissimilar structural information to that given by two-point correlation functions (CFs). Within the SA, we use an appropriate cost function consisting of EDs or comprised of EDs and CFs. It was found that the stochastic reconstruction is computationally efficient when we begin with a preliminary synthetic…

Positron Annihilation in Polycrystalline Metals Deformed by Uniaxial Tension

2005

Angular distributions of the positron annihilation quanta were measured for polycrystalline samples deformed by uniaxial tension up to difierent deformation degrees. The S parameter as a function of the W parameter was determined. The data obtained for samples elongated up to difierent elongation degrees indicate that in the proportionality and limited proportionality regions the changes in the physical properties of samples are governed mainly by generation of vacancies and formation and kinetics of transformations of vacancy clusters occurring flrst of all on the grains of monocrystallites. In the region of plastic deformations the dominant defects are dislocations and vacancies and their…

Searches for neutral Higgs bosons in e+e− collisions at centre-of-mass energies from 192 to 202 GeV

2000

Searches for neutral Higgs bosons are performed with the 237 pb-1 of data collected in 1999 by the ALEPH detector at LEP, for centre-of-mass energies between 191.6 and 201.6 GeV. These searches apply to Higgs bosons within the context of the Standard Model and its minimal supersymmetric extension (MSSM) as well as to invisibly decaying Higgs bosons. No evidence of a signal is seen. A lower limit on the mass of the Standard Model Higgs boson of 107.7 GeV/c2 at 95% confidence level is set. In the MSSM, lower limits of 91.2 and 91.6 GeV/c2 are derived for the masses of the neutral Higgs bosons h and A, respectively. For a Higgs boson decaying invisibly and produced with the Standard Model cros…

Sa1611 Computer-Assisted Diagnosis of Confocal Laser Endomicroscopy (CLE) by a Novel Image Analysis and Semantic Annotation Method

2012

Packing a trunk - Now with a twist!

2005

In an industry project with a German car manufacturer we are faced with the challenge of placing a maximum number of uniform rigid rectangular boxes in the interior of a car trunk. The problem is of practical importance due to a European industry norm which requires car manufacturers to state the trunk volume according to this measure. No really satisfactory automated solution for this problem has been known in the past. In spite of its NP hardness, combinatorial optimization techniques, which consider only grid-aligned placements, produce solutions which are very close to the one achievable by a human expert in several hours of tedious work. The remaining gap is mostly due to the constrain…