Search results for "LAB"
showing 10 items of 7932 documents
Multimodal Images Classification using Dense SURF, Spectral Information and Support Vector Machine
2019
International audience; The multimodal image classification is a challenging area of image processing which can be used to examine the wall painting in the cultural heritage domain. In such classification, a common space of representation is important. In this paper, we present a new method for multimodal representation learning, by using a pixel-wise feature descriptor named dense Speed Up Robust Features (SURF) combined with the spectral information carried by the pixel. For classification of extracted features we have used support vector machine (SVM). Our database was extracted from acquisition on cultural heritage wall paintings that contain four modalities UV, Visible, IRR and fluores…
Automatic skull stripping in MRI based on morphological filters and fuzzy c-means segmentation
2012
In this paper a new automatic skull stripping method for T1-weighted MR image of human brain is presented. Skull stripping is a process that allows to separate the brain from the rest of tissues. The proposed method is based on a 2D brain extraction making use of fuzzy c-means segmentation and morphological operators applied on transversal slices. The approach is extended to the 3D case, taking into account the result obtained from the preceding slice to solve the organ splitting problem. The proposed approach is compared with BET (Brain Extraction Tool) implemented in MRIcro software.
A Novel Symmetrical Boost Modulation Method for qZS-based CHB Inverters
2020
Quasi-Z-source cascaded H-bridge (qZS-CHB) inverters are arising as an innovation in the field of the electrical conversion for PV applications. This type of converters inherit the advantages of multilevel inverters and single-stage configuration. In this context, this paper proposes a novel symmetrical boost modulation strategy for qZS CHB multilevel inverters to increase the performance in terms of voltage stresses and power quality. The novelty lies in the adoption of a different concept to generate the shoot-through states compared to the traditional methods. Simulation analysis in a grid connected application to evaluate the benefits of this boost method is performed in the MATLAB/PLEC…
Tuning a Mamdani Fuzzy Controller with an Imperialist Competitive Algorithm
2021
We have implemented a fuzzy controller with a view to regulating a single-input and single-output second-order linear system. The fuzzy controller was a Mamdami proportional-derivative controller. To determine the parameters of the fuzzy controller we have used an imperialist competitive algorithm. This type of algorithm has a long running time so we implemented also a parallel version of the algorithm that we run on HPC Zamolxes located at the Engineering Faculty of “Lucian Blaga” University from Sibiu. Because we did not have on this computer a version of MATLAB allowing to write parallel algorithms, we implemented the entire application in the C language using the MPI library.
Exudates as Landmarks Identified through FCM Clustering in Retinal Images
2020
The aim of this work was to develop a method for the automatic identification of exudates, using an unsupervised clustering approach. The ability to classify each pixel as belonging to an eventual exudate, as a warning of disease, allows for the tracking of a patient&rsquo
Efficient cluster-based routing algorithm for body sensor networks
2018
International audience; Body Sensor Networks have gained a lot of research interest lately for the variety of applications they can serve. In such networks where nodes might hold critical information about people's lives, designing efficient routing schemes is very important to guarantee data delivery with the lowest delay and energy consumption. Even though some cluster-based routing schemes were proposed in the literature, none of them offer a complete solution that guarantees energy and delay efficient routing in BSN. In this paper, we propose a robust cluster- based algorithm that increases the routing efficiency through every step of the routing process: cluster formation, cluster head…
A Case Study on Agriture: Distributed HLA-Based Architecture for Agricultural Robotics
2011
In agricultural robotics, as in other robotic systems, one of the most important parts is the control architecture. This paper describes the definition of a new control architecture specially designed for groups of robots in charge of doing maintenance tasks in agricultural environments. This architecture has been developed having in mind principles as scalability, code reuse, abstraction hardware and data distribution. Moreover, it is important that the control architecture can allow coordination and cooperation among the different elements in the system. The architecture presented in this paper implements all these concepts by means of the integration of different systems, such as Player,…
Numerical implementation of active power flow tracing methods: Practical implications on transmission networks and DR programs support
2015
The goal of this paper is to demonstrate the powerful contribution of the electric active power flow tracing methods on studying the electric transmission systems operating conditions. The tracing methods allow to impute to every generation unit and/or load the responsibility of the power flows of all the elements connected to the network. This study propose the numerical implementation of two different tracing methods on two transmission networks through Matlab® scripts developed on purpose; then the analysis is focused on identifying the loads which mostly affect the power line flows of the system. The results of this analysis point out the loads on which the application of the Demand Res…
Advancing Deep Learning for Earth Sciences: From Hybrid Modeling to Interpretability
2020
Machine learning and deep learning in particular have made a huge impact in many fields of science and engineering. In the last decade, advanced deep learning methods have been developed and applied to remote sensing and geoscientific data problems extensively. Applications on classification and parameter retrieval are making a difference: methods are very accurate, can handle large amounts of data, and can deal with spatial and temporal data structures efficiently. Nevertheless, several important challenges need still to be addressed. First, current standard deep architectures cannot deal with long-range dependencies so distant driving processes (in space or time) are not captured, and the…
Experiencing with electronic image stabilization and PRNU through scene content image registration
2021
Abstract This paper explores content-based image registration as a means of dealing with and understanding better Electronic Image Stabilization (EIS) in the context of Photo Response Non-Uniformity (PRNU) alignment. A novel and robust solution to extrapolate the transformation relating the different image output formats for a given device model is proposed. This general approach can be adapted to specifically extract the scale factor (and, when appropriate, the translation) so as to align native resolution images to video frames, with or without EIS on, and proceed to compare PRNU patterns. Comparative evaluations show that the proposed approach outperforms those based on brute-force and p…