Felipe Santibáñez-Leal

Dr. Felipe Santibáñez-Leal

Advanced laboratory for geostatistical Supercomputing, Alges - AMTC, Universidad de Chile
orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 December 2020 in Minerals
Verified
Journal Article
Open access
PDF file
AEAlvaro Egaña
Alvaro Egaña
Felipe Santibáñez-LealFelipe Santibáñez-Leal
Felipe Santibáñez-Leal
Christian VidalChristian Vidal
Christian Vidal
GDGonzalo Díaz
Gonzalo Díaz
SLSergio Liberman
Sergio Liberman
AEAlejandro Ehrenfeld
Alejandro Ehrenfeld
Most mining companies have registered important amounts of drill core composite spectra using different acquisition equipment and by following diverse protocols. These companies have used classic spectrography based on the detection of absorption features to perform semi-quantitative mineralogy. This methodology requires ideal laboratory conditions in order to obtain normalized spectra to compare. However, the inherent variability of spectral features—due to environmental conditions and geological context, among others—is unavoidable and needs to be managed. This work presents a novel methodology for geometallurgical sample characterization consisting of a heterogeneous, multi-pixel processing pipeline which addresses the effects of ambient conditions and geological context variability to estimate critical geological and geometallurgical variables. It relies on the assumptions that the acquisition of hyperspectral images is an inherently stochastic process and that ore sample information is deployed in the whole spectrum. The proposed framework is basically composed of: (a) a new hyperspectral image segmentation algorithm, (b) a preserving-information dimensionality reduction scheme and (c) a stochastic hierarchical regression model. A set of experiments considering white reference spectral characterization and geometallurgical variable estimation is presented to show promising results for the proposed approach.

1 February 2014 in Current Molecular Medicine
Verified
Journal Article
Closed access
PDF file
VCV. Castaneda
V. Castaneda
MCMauricio Cerda
Mauricio Cerda
Felipe Santibáñez-LealFelipe Santibáñez-Leal
Felipe Santibáñez-Leal
JJJ. Jara
J. Jara
EPE. Pulgar
E. Pulgar
SHS. Hartel
S. Hartel
Cell migration is a complex biological process that involves changes in shape and organization at the sub-cellular, cellular, and supra-cellular levels. Individual and collective cell migration can be assessed in vitro and in vivo starting from the flagellar driven movement of single sperm cells or bacteria, bacterial gliding and swarming, and amoeboid movement to the orchestrated movement of collective cell migration. One key technology to access migration phenomena is the combination of optical microscopy with image processing algorithms. This approach resolves simple motion estimation (e.g. preferred direction of migrating cells or path characteristics), but can also reveal more complex descriptors (e.g. protrusions or cellular deformations). In order to ensure an accurate quantification, the phenomena under study, their complexity, and the required level of description need to be addressed by an adequate experimental setup and processing pipeline. Here, we review typical workflows for processing starting with image acquisition, restoration (noise and artifact removal, signal enhancement), registration, analysis (object detection, segmentation and characterization) and interpretation (high level understanding). Image processing approaches for quantitative description of cell migration in 2- and 3-dimensional image series, including registration, segmentation, shape and topology description, tracking and motion fields are presented. We discuss advantages, limitations and suitability for different approaches and levels of description.

23 March 2023 in Scientific Data
Verified
Journal Article
Open access
PDF file
AEAlejandro Ehrenfeld
Alejandro Ehrenfeld
ÁEÁlvaro F. Egaña
Álvaro F. Egaña
Felipe Santibáñez-LealFelipe Santibáñez-Leal
Felipe Santibáñez-Leal
FGFelipe Garrido
Felipe Garrido
MOMarcia Ojeda
Marcia Ojeda
Felipe NavarroFelipe Navarro
Felipe Navarro
Supervised analysis using spectral data requires a well-informed characterisation of the response variables and abundant spectral data points. The presented hyperspectral dataset comes from five sets of geometallurgical samples, each characterised by different methods. To provide the spectral data, all mineral samples were scanned with SPECIM VNIR and SWIR hyperspectral cameras. For each subset the following data are provided 1) hyperspectral reflectance images in the VNIR spectral range (400–1000 nm wavelength); 2) hyperspectral reflectance images in the SWIR spectral range (900–2500 nm wavelength); 3) hyperspectral reflectance images in the VNIR-SWIR range (merged to SWIR spatial resolution); 4) RGB images constructed from hyperspectral data using a Bilateral Filter based sensor fusion method; 5) response variables representing mineral sample characterisation results, provided as training and validation data. This dataset is intended for use in general regression and classification research and experiments. All subsets were validated using machine learning models with satisfactory results.

8 February 2020 in Natural Resources Research
Verified
Journal Article
Closed access
PDF file
Felipe Santibáñez-LealFelipe Santibáñez-Leal
Felipe Santibáñez-Leal
JOJulian Ortiz
Julian Ortiz
JSJorge F. Silva
Jorge F. Silva


19 September 2016
Verified
Conference Paper
Closed access
HCHernan Calderon
Hernan Calderon
Felipe Santibáñez-LealFelipe Santibáñez-Leal
Felipe Santibáñez-Leal
JSJorge F. Silva
Jorge F. Silva
JOJulian Ortiz
Julian Ortiz
AEAlvaro Egana
Alvaro Egana
A new image reconstruction algorithm is proposed based on weighted compressed sensing (WCS) for the problem of channelized facies recovery from pixel-based measurements. This algorithm integrates information from: (1) signal structure dependencies in a transform domain (the discrete cosine transform); and (2) multiple-point statistics obtained from a training image. In the experimental side, excellent results are reported showing that the WCS scheme provides good reconstruction for geological facies models even in the [0.3%-1%] range of data. Experiments show that the proposed solution outperforms methods based on CS and MPS, when reconstruction performance is measured in terms of similarity perceptual indicators (MSSIM).