Marcelo Nicolás Guzmán
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marcelo Nicolás Guzmán has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Gustavo Javier Meschino
Universidad Nacional de Mar del Plata-CONICET
5 shared publications - Ana Lucia Dai Pra
Universidad Nacional de Mar del Plata
2 shared publications Gustavo Javier Meschino
Universidad Nacional de Mar del Plata - CONICET
2 shared publicationsLucía I Passoni
Laboratorio de Bioingenieria, ICYTE (Instituto de Investigaciones Científicas y Tecnológicas en Electrónica, CONICET-UNMdP), UNMDP Av. J.B. Justo 4302, Mar del Plata B7608FDQ, Argentina
2 shared publicationsMelina Nisenbaum
Universidad Nacional de Mar del Plata – CIC - CONICET
2 shared publicationsSilvia Murialdo
Universidad Nacional de Mar del Plata – CIC - CONICET
2 shared publications
Latest Publications
- 1 July 2026
- Published by IOP Publishing in Journal of Optics
- Vol. 28 (7) , 075607
Feature extraction of dynamic speckle time series via sparse autoencoders for paint drying state classification
This study proposes a novel methodological framework for determining the drying stages of paint by analyzing the temporal dynamics of laser speckle patterns through Deep Learning. While traditional dynamic laser speckle analysis relies on manually engineered descriptors that often require experiment-specific tuning, we present an automated feature extraction framework that employs a stacked architecture of three sparse autoencoders (SAE). By processing the time series of individual pixels from speckle videos, the model autonomously learns representative features of the drying process. The proposed architecture, coupled with a Softmax classification layer, achieved 95.1% accuracy across four distinct drying states: dry, mid-dry, mid-wet, and wet. Furthermore, the model demonstrated promising transferability capabilities when applied to a textured surface (a coin) without retraining, outperforming well-known descriptors such as Fuzzy Granularity and Subtraction Average. These results highlight the potential of SAEs as a robust, self-adapting alternative for optical metrology, offering a foundation for future studies to address manual parameter optimization in complex dynamic phenomena.
- 1 July 2026
- Published by IOP Publishing in Journal of Optics
- Vol. 28 (7) , 075607
Feature extraction of dynamic speckle time series via sparse autoencoders for paint drying state classification
This study proposes a novel methodological framework for determining the drying stages of paint by analyzing the temporal dynamics of laser speckle patterns through Deep Learning. While traditional dynamic laser speckle analysis relies on manually engineered descriptors that often require experiment-specific tuning, we present an automated feature extraction framework that employs a stacked architecture of three sparse autoencoders (SAE). By processing the time series of individual pixels from speckle videos, the model autonomously learns representative features of the drying process. The proposed architecture, coupled with a Softmax classification layer, achieved 95.1% accuracy across four distinct drying states: dry, mid-dry, mid-wet, and wet. Furthermore, the model demonstrated promising transferability capabilities when applied to a textured surface (a coin) without retraining, outperforming well-known descriptors such as Fuzzy Granularity and Subtraction Average. These results highlight the potential of SAEs as a robust, self-adapting alternative for optical metrology, offering a foundation for future studies to address manual parameter optimization in complex dynamic phenomena.
- 16 October 2025
- Published by Springer Nature
- p. 729-740
Design, Construction, and Characterization of an Arterial Diameter Variation Acquisition System
- 16 October 2025
- Published by Springer Nature
- p. 729-740
Design, Construction, and Characterization of an Arterial Diameter Variation Acquisition System
- 7 March 2025
- Published by Springer Nature in Sensing and Imaging
- Vol. 26 (1) , 1-20
Enhancing Water Safety: Biospeckle Laser Approach for Bacterial Detection
- 7 March 2025
- Published by Springer Nature in Sensing and Imaging
- Vol. 26 (1) , 1-20
Enhancing Water Safety: Biospeckle Laser Approach for Bacterial Detection
- 15 February 2024
- Published by Springer Nature
- p. 455-460
Determination of Microbial Load in Water by Dynamic Speckle Pattern Analysis
- 15 February 2024
- Published by Springer Nature
- p. 455-460
Determination of Microbial Load in Water by Dynamic Speckle Pattern Analysis
- 19 December 2022
- Published by IOP Publishing in Journal of Optics
- Vol. 25 (2) , 024001
Improvement of activity level detection in dynamic speckle patterns with fuzzy logic operators
In this work, the design of a multi-descriptor model is proposed to improve the identification of activity levels in dynamic laser speckle (DLS) image sequences. Fuzzy predicates evaluated with operators of different logic systems were used. The model considers both temporal and spatial effects of the DLS phenomenon. Experiments were carried out to characterize the drying times of a sample painted with water-based paint, illuminated with a coherent light, whose image sequences were captured with a CCD camera. To assess the improvement of the proposed model with respect to single descriptors, the Kruskal–Wallis test and the silhouette index were used. The compensatory logic operators achieved the best results to improve the discrimination of the activity levels, according to the different drying times in the dynamic laser speckle sequences.
- 19 December 2022
- Published by IOP Publishing in Journal of Optics
- Vol. 25 (2) , 024001
Improvement of activity level detection in dynamic speckle patterns with fuzzy logic operators
In this work, the design of a multi-descriptor model is proposed to improve the identification of activity levels in dynamic laser speckle (DLS) image sequences. Fuzzy predicates evaluated with operators of different logic systems were used. The model considers both temporal and spatial effects of the DLS phenomenon. Experiments were carried out to characterize the drying times of a sample painted with water-based paint, illuminated with a coherent light, whose image sequences were captured with a CCD camera. To assess the improvement of the proposed model with respect to single descriptors, the Kruskal–Wallis test and the silhouette index were used. The compensatory logic operators achieved the best results to improve the discrimination of the activity levels, according to the different drying times in the dynamic laser speckle sequences.
- 1 July 2016
- Published by IOP Publishing in Journal of Optics
- Vol. 18 (8) , 085606
Dynamic speckle image segmentation using self-organizing maps
The aim of this work is to build a computational model able to automatically identify, after training, dynamic speckle pattern regions with similar properties. The process is carried out using a set of descriptors applied to the intensity variations with time in every pixel of a speckle image sequence. An image obtained by projecting a self-organized map is converted into regions of similar activity that can be easily distinguished. We propose a general procedure that could be applied to numerous situations. As examples we show different situations: (a) an activity test in a simplified situation; (b) a non-biological example and (c) biological active specimens. The results obtained are encouraging; they significantly improve upon those obtained using a single descriptor and will eventually permit automatic quantitative assessment.
- 1 July 2016
- Published by IOP Publishing in Journal of Optics
- Vol. 18 (8) , 085606
Dynamic speckle image segmentation using self-organizing maps
The aim of this work is to build a computational model able to automatically identify, after training, dynamic speckle pattern regions with similar properties. The process is carried out using a set of descriptors applied to the intensity variations with time in every pixel of a speckle image sequence. An image obtained by projecting a self-organized map is converted into regions of similar activity that can be easily distinguished. We propose a general procedure that could be applied to numerous situations. As examples we show different situations: (a) an activity test in a simplified situation; (b) a non-biological example and (c) biological active specimens. The results obtained are encouraging; they significantly improve upon those obtained using a single descriptor and will eventually permit automatic quantitative assessment.
- Open Access
- 1 April 2016
- Published by Elsevier in Polymer Testing
- Vol. 50, 262-269
Measurement of shrinkage during photopolymerization of methacrylate resins by interferometric techniques: Local and global analyses
- 1 April 2016
- Published by Elsevier in Polymer Testing
- Vol. 50, 262-269
Open AccessMeasurement of shrinkage during photopolymerization of methacrylate resins by interferometric techniques: Local and global analyses
- Open Access
Unsupervised learning segmentation for dynamic speckle activity images
This paper proposes the design of decision models based on Computational Intelligence techniques applied to image sequences of dynamic laser speckle. These models aim to identify image regions of biological specimens illuminated by a coherent beam coming from a laser. The field image is pseudo colored using a Self Organizing Map projection. This process is carried out using a set of descriptors applied to the intensity variations along time in every pixel of an image sequence. The models use descriptors selected to improve effectiveness, depending on the specific application. We present two examples of the application of the proposed techniques to assess biological tissues. The results obtained are encouraging and significantly improve those obtained using a single descriptor.
Open AccessUnsupervised learning segmentation for dynamic speckle activity images
This paper proposes the design of decision models based on Computational Intelligence techniques applied to image sequences of dynamic laser speckle. These models aim to identify image regions of biological specimens illuminated by a coherent beam coming from a laser. The field image is pseudo colored using a Self Organizing Map projection. This process is carried out using a set of descriptors applied to the intensity variations along time in every pixel of an image sequence. The models use descriptors selected to improve effectiveness, depending on the specific application. We present two examples of the application of the proposed techniques to assess biological tissues. The results obtained are encouraging and significantly improve those obtained using a single descriptor.