Search results for "Pattern"
showing 10 items of 4203 documents
A tool for a first analysis of architectural façades
1997
Abstract This work presents a tool for analysing the figurative structure of architectural facades. The procedure begins by singling out the elementary shapes which make up the facade image; it detects and identifies them as “area objects”, even if present in combination in virtual or mental form and groups them into classes of equal objects. A second step is the analysis of the inner structure of the classes: equidistant, arithmetical and geometrical sequences, or alternate distances are distinguished. The procedure ends by singling out the symmetries which structure the facade image and displaying them, pointing out their implied hierarchy through a thickness differentiation.
Preventing Overlaps in Agglomerative Hierarchical Conceptual Clustering
2020
Hierarchical Clustering is an unsupervised learning task, whi-ch seeks to build a set of clusters ordered by the inclusion relation. It is usually assumed that the result is a tree-like structure with no overlapping clusters, i.e., where clusters are either disjoint or nested. In Hierarchical Conceptual Clustering (HCC), each cluster is provided with a conceptual description which belongs to a predefined set called the pattern language. Depending on the application domain, the elements in the pattern language can be of different nature: logical formulas, graphs, tests on the attributes, etc. In this paper, we tackle the issue of overlapping concepts in the agglomerative approach of HCC. We …
An In-Depth Experimental Comparison of RNTNs and CNNs for Sentence Modeling
2017
The goal of modeling sentences is to accurately represent their meaning for different tasks. A variety of deep learning architectures have been proposed to model sentences, however, little is known about their comparative performance on a common ground, across a variety of datasets, and on the same level of optimization. In this paper, we provide such a novel comparison for two popular architectures, Recursive Neural Tensor Networks (RNTNs) and Convolutional Neural Networks (CNNs). Although RNTNs have been shown to work well in many cases, they require intensive manual labeling due to the vanishing gradient problem. To enable an extensive comparison of the two architectures, this paper empl…
Using the fibre structure of paper to determine authenticity of the documents: analysis of transmitted light images of stamps and banknotes.
2014
A novel method is presented for distinguishing postal stamp forgeries and counterfeit banknotes from genuine samples. The method is based on analyzing differences in paper fibre networks. The main tool is a curvelet-based algorithm for measuring overall fibre orientation distribution and quantifying anisotropy. Using a couple of more appropriate parameters makes it possible to distinguish forgeries from genuine originals as concentrated point clouds in two- or three-dimensional parameter space.
Semi-supervised Hyperspectral Image Classification with Graphs
2006
This paper presents a semi-supervised graph-based method for the classification of hyperspectral images. The method is designed to exploit the spatial/contextual information in the im- ages through composite kernels. The proposed method produces smoother classifications with respect to the intrinsic structure collectively revealed by known labeled and unlabeled points. Good accuracy in high dimensional spaces and low number of labeled samples (ill-posed situations) are produced as compared to standard inductive support vector machines.
Including invariances in SVM remote sensing image classification
2012
This paper introduces a simple method to include invariances in support vector machine (SVM) for remote sensing image classification. We rely on the concept of virtual support vectors, by which the SVM is trained with both the selected support vectors and synthetic examples encoding the invariance of interest. The algorithm is very simple and effective, as demonstrated in two particularly interesting examples: invariance to the presence of shadows and to rotations in patchbased image segmentation. The improved accuracy (around +6% both in OA and Cohen's κ statistic), along with the simplicity of the approach encourage its use and extension to encode other invariances and other remote sensin…
Comparing fMRI inter-subject correlations between groups using permutation tests
2018
AbstractInter-subject correlation (ISC) based analysis is a conceptually simple approach to analyze functional magnetic resonance imaging (fMRI) data acquired under naturalistic stimuli such as a movie. We describe and validate the statistical approaches for comparing ISCs between two groups of subjects implemented in the ISC toolbox, which is an open source software package for ISC-based analysis of fMRI data. The approaches are based on permutation tests. We validated the approaches using five different data sets from the ICBM functional reference battery tasks. First, we created five null datasets (one for each task) by dividing the subjects into two matched groups and assumed that no gr…
Growth patterns of the topshell Phorcus lineatus (da Costa, 1778) in northern Iberia deduced from shell sclerochronology
2019
Combined shell growth pattern and oxygen isotope analysis has become a powerful approach in palaeoclimate and archaeological studies for reconstructing palaeoclimate conditions and littoral exploitation patterns, respectively. Recent investigations have shown that the gastropod Phorcus lineatus (da Costa, 1778) forms its shell in conditions of near equilibrium with the oxygen isotope signature of the seawater environment, demonstrating the utility of this species for reconstruction of sea surface temperature and determination of the season of harvest in archaeological studies. In contrast, the shell growth patterns of this species have received virtually no attention despite providing infor…
Neurobiologie und System-Theorie eines visuellen Muster-Erkennungsmechanismus bei Kröten
1973
Quantitative behavioral experiments have shown that the toad uses mainly two types of gestalt information in prey/enemy discrimination: pattern extension in the direction of movement promotes, in general, the signal value prey, while extension perpendicular to the direction of movement promotes that of enemy. Registrations from single fibers and single cells at different stages on the visual path showed that the object extension perpendicular to the direction of movement is chiefly analysed by means of the retinal and thalamus pretectal nerve nets, whereas the extension in the direction of movement is analysed mostly by certain tectal nerve nets. Further neurobiological findings indicated t…
Wound drainages in total hip arthroplasty: to use or not to use? Review of the literature on current practice.
2013
Aim of this study is to analyze data reported in literature concerning the efficacy of using wound low-vacuum suction drainages in orthopedic surgery after total hip arthroplasty. We analyzed studies concerning the use of drainages in prosthetic hip replacement surgery, performing our research through Pubmed, Cochrane database and Google Scholar, and selecting the ones evaluating the following parameters: bleeding, the need for blood transfusions, number or reinforcement of post-operative medications, length of hospitalization, functional results, periprosthetic and surgical wound infection, post-operative hematoma. Our review did not show any demonstrated advantage from the use of wound dr…