A5086255063- Face and Expression Recognition
- Mechanical Circulatory Support Devices
- Cardiac Arrest and Resuscitation
- Face recognition and analysis
- Handwritten Text Recognition Techniques
- Identification and Quantification in Food
- Spectroscopy and Chemometric Analyses
- Image Retrieval and Classification Techniques
- Biometric Identification and Security
- Speech and Audio Processing
- Advanced Radiotherapy Techniques
- Banana Cultivation and Research
- Hydraulic Fracturing and Reservoir Analysis
- Medical Image Segmentation Techniques
- Oil and Gas Production Techniques
- Plant and animal studies
- Bee Products Chemical Analysis
- Genetic diversity and population structure
- Insect and Arachnid Ecology and Behavior
- Domain Adaptation and Few-Shot Learning
- Advanced Mathematical Theories and Applications
- Image Processing and 3D Reconstruction
- Elasticity and Material Modeling
- Neurobiology and Insect Physiology Research
- Leaf Properties and Growth Measurement
Weatherford (Norway)
2021-2023
Highland Community College - Illinois
2015
Philips (United States)
2015
Henry Ford Health System
2015
Universidad de Costa Rica
2005-2014
University of Beira Interior
2013-2014
Instituto de Telecomunicações
2013-2014
The University of Texas Health Science Center at San Antonio
2013
Universidad de Las Palmas de Gran Canaria
2003-2011
Universidad de Los Andes
2006
Biometrics systems based on lip shape recognition are of great interest, but have received little attention in the scientific literature. This is perhaps due to belief that they discriminative power. However, a careful study shows difference between outlines greater than shapes at different images same person. So, biometric identification by outline possible. In this paper obtained from color face picture: image transformed gray scale using transformation Chang et al. (1994) and binarized...
Conserving earth's biodiversity for future generations is a fundamental global task, where automated recognition of pollen species by means computer vision represents highly prioritized issue. This work focuses on analysis and classification stages. The morphological details the contour are proposed as grains discriminative features. approach has been developed robust identification based an HMM kernel. A Vector Support Machine was used classifier. principal contribution in this work, terms...
In biometrics research, the periocular region has been regarded as an interesting trade-off between face and iris, particularly in unconstrained data acquisition setups. As other biometric traits, current challenge is development of more robust recognition algorithms. Having investigated suitability ‘elastic graph matching’ (EGM) algorithm to handle non-linear distortions because facial expressions, authors observed that vertices locations often not correspond displacements biological...
This works presents a new proposal towards the development of an intelligent system for automatic detection and monitoring mite’s movement, being this major pest honey bees worldwide which attacks bee’s pupa during its growing stage. The is early life stage some insects undergoing transformation. presented only in certain type called holometabolous, are those that should undergo complete metamorphosis. We propose technique based on background subtraction frame by approach, keeping track...
In this paper we present a biometric approach, based on lip shape. We have performed an image preprocessing, in order to detect the face of person image. After this, enhanced lips using color transformation, and next do its detection. The parameterization is contour points. Those points been transformed by Hidden Markov Model (HMM) kernel, minimization Fisher Score. Finally, one-versus-all multiclass supervised approach Support Vector Machines (SVM) applied as classifier. A database with 50...
Sparse representations for classification (SRC) are considered a relevant advance to the biometrics field, but particularly sensitive data misalignments. In previous studies, such misalignments were compensated by finding appropriate geometric transforms between elements in dictionary and query image, which is costly terms of computational burden. This study describes an algorithm that compensates SRC implicit way, is, without finding/applying any transform at every recognition attempt. The...
The present work presents a biometric identification system for hand shape identification. different contours have been coded based on angular descriptions forming Markov chain descriptor. Discrete Hidden Models (DHMM), each representing target class, trained with such chains. Features calculated from kernel the HMM parameter descriptors. Finally, supervised Support Vector Machines were used to classify parameters DHMM kernel. First, was modelled using 60 users tune and DHMM_kernel+SVM...
In this work, a temperature predictor has been designed and implemented based on different series of meteorological data. The prediction is built by an artificial neural network multilayer perceptron, using 5 samples as window size Besides, the floating point algorithm was evaluated, reaching mean square error 0.35, meaning variation 0.28 Celsius degrees versus real temperature. Different approaches will be applied in order to show our best proposal.
Purpose: To evaluate the effect of planning CT slice thickness on SRS target localization accuracy Varian Edge treatment platform. Methods: A metal BB diameter 5 mm was inserted in a Rando head phantom. Planning CTs were scanned with 0.8, 2 and 3 respectively. The center setup as isocenter tattoos marked phantom surface. initially aligned using laser tattoos, then CBCT acquired 6‐degree freedom (DOF) image registration performed based bony anatomy. 6D couch correction applied. verification...
Briceño, J C; Rincón, I E; García, A; Castro, I; Arias, M; Anzola, M L; Matallana, Velasquez, C Author Information
Abstract Enhanced hydrocarbon production in a high-pressure/high-temperature (HP/HT) carbonate reservoir, involves generating highly conductive channels using efficient diversion techniques and custom-designed acid-based fluid systems. Advanced stimulation design includes injection of different reactive fluids, which challenges associated with controlling leak-off, implementing optimal techniques, acid reaction rates to withstand high-temperature conditions, designing appropriate pumping...
Abstract Stimulation fluids injected into a reservoir take the path of least resistance, leaving behind under-stimulated areas. As result, stimulation efficiency and effectiveness are reduced, affecting overall production potential. The placement treatment depends on maximizing contact in zone interest (good penetration) uniform distribution across section. To achieve distribution, existing higher permeability areas or natural fractures must be efficiently temporarily blocked, diverting...
Purpose: Accurate tumor motion characterization is critical for increasing the therapeutic ratio of radiation therapy. To accommodate divergent fan‐beam geometry scanner, current 4D‐CT algorithm utilizes a larger temporal window to ensure that pixel values are valid throughout entire FOV. minimize impact on resolution, cos 2 weighting employed. We propose novel exponential (“exponential”) 4DCT reconstruction has sharper slope and provides more optimal resolution. Methods: A respiratory...
Purpose: IMRT patient specific QA is often used across institutions to provide a quantitative measure of the accuracy by which treatment plan delivered. The aim this project evaluate performance four commercially available devices while varying acceptance criteria dose difference and distance agreement (DTA). Methods: Ten VMAT 10 static field plans were evaluated. All optimized using Pinnacle v9.2. Measurements performed on Varian 2100CD linac equipped with millennium 80MLC. gamma index was...