Search results for "Image."

Unsupervised low-key image segmentation using curve evolution approach

2013

Low-key images widely exist in imaging-based systems such as space telescopes, medical imaging equipment, machine vision systems. Unsupervised low-key image segmentation is an important process for image analysis or digital measurement in these applications. In this paper, a novel active contour model with the probability density function (PDF) of gamma distribution for image segmentation is proposed. The flexible gamma distribution is used to describe both of the heterogeneous foreground and dark background in a low-key image. Besides, an unsupervised curve initialization method is also designed in this paper, which helps to accelerate the convergence speed of curve evolution. The effectiv…

Remote sensing image segmentation by active queries

2012

Active learning deals with developing methods that select examples that may express data characteristics in a compact way. For remote sensing image segmentation, the selected samples are the most informative pixels in the image so that classifiers trained with reduced active datasets become faster and more robust. Strategies for intelligent sampling have been proposed with model-based heuristics aiming at the search of the most informative pixels to optimize model's performance. Unlike standard methods that concentrate on model optimization, here we propose a method inspired in the cluster assumption that holds in most of the remote sensing data. Starting from a complete hierarchical descri…

Improving active learning methods using spatial information

2011

Active learning process represents an interesting solution to the problem of training sample collection for the classification of remote sensing images. In this work, we propose a criterion based on the spatial information that can be used in combination with a spectral criterion in order to improve the selection of training samples. Experimental results obtained on a very high resolution image show the effectiveness of regularization in spatial domain and open challenging perspectives for terrain campaigns planning. © 2011 IEEE.

Recognition of Falls and Daily Living Activities Using Machine Learning

2018

A robust fall detection system is essential to support the independent living of elderlies. In this context, we develop a machine learning framework for fall detection and daily living activity recognition. Using acceleration data from public databases, we test the performance of two algorithms to classify seven different activities including falls and activities of daily living. We extract new features from the acceleration signal and demonstrate their effect on improving the accuracy and the precision of the classifier. Our analysis reveals that the quadratic support vector machine classifier achieves an overall accuracy of 93.2% and outperforms the artificial neural network algorithm. Re…

An approximation to the diachronic analysis of mitigation and face in dialogues between mother and child in the nineteenth and twentieth centuries

2018

Este artículo aborda la evolución del uso de la atenuación en los diálogos madre-hijo y sus efectos en la imagen sociocultural en los siglos XIX y XX. Para ello, utilizando como corpus cuatro obras de teatro de este periodo, se analiza cualitativa y cuantitativamente el empleo de la atenuación como estrategia pragmática en los actos directivos realizados en la proyección de estas relaciones. Los resultados de este estudio apuntan a que se ha producido una evolución desde la jerarquía hacia una progresiva solidaridad. This paper aims to analyse the evolution of the use of mitigation in dialogues between mother and child and their effects on sociocultural face in the nineteenth and twentieth …

Spatial sharpening of land surface temperature for daily energy balance applications

2008

ABSTRACT Daily high spatial resolution assessment of actual evapotranspiration is essential for water management and crop water requirement estimation under stress conditions. The application of energy balance models usually requires satellite observations of radiometric surface temperat ure with high geometrical and temporal resolutions. By now, however, high spatial resolution (~ 100 m) is available with low time fre quency (approximately every two weeks); at the opposite daily acquisition are characterised by poor spatial resolution. The analysis of vegetation index (VI) and land surface temperature (LST) spatial relationship, shows in substance a scale invariant behaviour [1] ; this con…

Applications of a remote sensing-based two-source energy balance algorithm for mapping surface fluxes without in situ air temperature observations

2012

Abstract The two-source energy balance (TSEB) model uses remotely sensed maps of land–surface temperature (LST) along with local air temperature estimates at a nominal blending height to model heat and water fluxes across a landscape, partitioned between dual sources of canopy and soil. For operational implementation of TSEB, however, it is often difficult to obtain representative air temperature data that are compatible with the LST retrievals, which may themselves have residual errors due to atmospheric and emissivity corrections. To address this issue, two different strategies in applying the TSEB model without requiring local air temperature data were tested over a typical Mediterranean…

Combining Benford's Law and machine learning to detect money laundering. An actual Spanish court case.

2017

Abstract Objectives This paper is based on the analysis of the database of operations from a macro-case on money laundering orchestrated between a core company and a group of its suppliers, 26 of which had already been identified by the police as fraudulent companies. In the face of a well-founded suspicion that more companies have perpetrated criminal acts and in order to make better use of what are very limited police resources, we aim to construct a tool to detect money laundering criminals. Methods We combine Benford’s Law and machine learning algorithms (logistic regression, decision trees, neural networks, and random forests) to find patterns of money laundering criminals in the conte…

Two ways to metaphor comprehension in comparison: towards a bidimensional account of metaphor comprehension - poster

In this paper we will discuss the role of literal meaning and mental imagery in metaphor comprehension, showing their link and the problematic nature of these notions in pragmatics (Wilson & Carston 2019). We will try to overcome these problems by putting in dialogue the typology of metaphors offered by Carston (2010, 2018), based on the parameter of literal meaning, and the typology offered by Green (2017) based on the parameter of mental imagery. Carston (2018) recognizes the existence of two kinds of metaphors: (1) local metaphors such as “Giulio is a professor” in which a single lexical item - PROFESSOR - is modulated pragmatically; (2) metaphors such as “The yellow fog that rubs it…

A Hierarchical Detection and Response System to Enhance Security Against Lethal Cyber-Attacks in UAV Networks

2018

International audience; Unmanned aerial vehicles (UAVs) networks have not yet received considerable research attention. Specifically, security issues are a major concern because such networks, which carry vital information, are prone to various attacks. In this paper, we design and implement a novel intrusion detection and response scheme, which operates at the UAV and ground station levels, to detect malicious anomalies that threaten the network. In this scheme, a set of detection and response techniques are proposed to monitor the UAV behaviors and categorize them into the appropriate list (normal, abnormal, suspect, and malicious) according to the detected cyber-attack. We focus on the m…