H
Humberto Loaiza
Researcher at University of Valle
Publications - 34
Citations - 287
Humberto Loaiza is an academic researcher from University of Valle. The author has contributed to research in topics: Gesture & Artificial neural network. The author has an hindex of 7, co-authored 34 publications receiving 267 citations.
Papers
More filters
Journal ArticleDOI
Definition of a new thermal contrast and pulse correction for defect quantification in pulsed thermography
Hernán D. Benítez,Clemente Ibarra-Castanedo,Abdelhakim Bendada,Xavier Maldague,Humberto Loaiza,Eduardo Caicedo +5 more
TL;DR: In this paper, the authors proposed a new DAC version by explicitly introducing the sample thickness using the thermal quadrupoles theory and showed that the new DAC range of validity increases for long times while preserving the validity for short times.
Proceedings ArticleDOI
Modified Differential Absolute Contrast using Thermal Quadrupoles for the Nondestructive Testing of Finite Thickness Specimens by Infrared Thermography
Hernán D. Benítez,Clemente Ibarra-Castanedo,Abdelhakim Bendada,Xavier Maldague,Humberto Loaiza,Eduardo Caicedo +5 more
TL;DR: A modified DAC version is proposed by explicitly introducing the sample thickness using the thermal quadrupoles theory, demonstrating that taking into account the sample Thickness, the DAC validity range considerably extends for long times after excitation while preserving its performance for short times.
Journal ArticleDOI
Defect characterization in infrared non-destructive testing with learning machines
Hernán D. Benítez,Humberto Loaiza,Eduardo Caicedo,Clemente Ibarra-Castanedo,Abdelhakim Bendada,Xavier Maldague +5 more
TL;DR: In this article, the authors proposed a reference-free thermal contrast by using the thermal quadrupoles theory and evaluated the limits of defect detection in composite samples by using dynamic principal components analysis (DPCA) and k-nearest neighbor algorithm.
Journal ArticleDOI
Phase contrast using a differentiated absolute contrast method
Mirela Suša,Hernán D. Benítez,Clemente Ibarra-Castanedo,Humberto Loaiza,Hakim Bendada,Xavier Maldague +5 more
TL;DR: The differentiated absolute contrast (DAC) method is proposed to eliminate the need of defining a sound area by subtracting the ideal phase value of a pixel from its measured phase.
Journal ArticleDOI
Matching segments in stereoscopic vision
TL;DR: After an exhaustive study, it is shown that it's possible to realize a stereoscopic sensor with poor cameras and to combine two methods, Bayesian and neural, to construct an efficient classifier.