See my google schoolar profile for an updated list of my publications. Below you will find an overview of my main research interests. At the end of this page, I also share the PDF and source-code of my recent publications (I am doing my best to keep this list as updated as possible).
Computer vision and machine learning based modeling to improve medical outcomes
I am having the pleasure of working on an exciting project led by Geraldine Dawson and Guillermo Sapiro. We are developing a digital app to characterize and understand the behavior of young children diagnosed with autism [18-19,22]. The study was covered in multiple news outlets, such as CBS, NBC, Forbes, CTV (Canada), American Psychiatric Association News, and many others. With professors Nancy Zucker and Guillermo Sapiro, we are exploiting novel computer vision methods to characterize and help children with eating disorders  (in the news: usnews, earth.com). Professor Peterchev and I are developing modern computer vision tools to design a new generation of TMS neuronavegation trackerless tools (more info in Dr. Peterchev’s web). I work with Restor3d to develop novel technology for implant design and surgery plannig (see  for an example).
3D Face analysis
Our face contains an incredible amount of rich information about us. It can be used to identify or validate who we are, infer our emotions, identify what attracts our attention, and even be used to assist medical diagnosis and treatment. I am interested in enhancing face analysis by exploiting 3D geometrical properties, e.g. using light and non-traditional optical setups. Most of my work in this area is being pushed forward with Mauricio Delbracio, Qiang Qiu and Guillermo Sapiro [16-17, 21].
Fraud Detection and Energy Consumption Modeling
Alicia Fernandez, Pablo Massaferro, and I are studying how to detect electricity non-technical losses and typical patterns of customers’ power consumption. The technology we develop has scientific innovation [3, 15, 20] and is transferred to the industry as well. Particularly, we collaborate with the national power distribution company in Uruguay: UTE. One of the problems I am interested in, and also pertains to fraud detection, is the study of highly imbalanced classes [6-11,15,20,25].
Working on Image Processing is extremely exciting. Elegant math, variational methods, and partial differential equations can work together to achieve image processing tools beyond imagination. I have worked mostly with methods based on partial differential equations. In particular, different formulations of the Poisson Equations and their numerical solutions. This work was developed with Jean-Michel Morel, Gabriele Facciolo, and Enric Meinhardt-Llopis. Most of this research is published in IPOL.im [9,14]. If you don’t know what that is, take a look! It is a great journal with a strong emphasis on making research reproducible.
Optics is an interesting field of physics with many important practical applications. Fourier optics can be exploited to make transparent phase objects visible, to scan 3D information of a scene, and retrieve hyper-spectral properties of elements. It allows to push forward the boundaries of traditional photography, and open many exiting alternatives to classical image processing approaches. I have been working mainly in phase retrieval techniques and 3D sensing using active light (phase-shifting like algorithms). This work is being done primarily with Gaston Ayubi and Jose Ferrari [1,2,5,13].
 Pablo Massaferro, J. Matias Di Martino, and Alicia Fernandez. “Fraud detection on power grids while transitioning to smart meters by leveraging mulit-resolution consumption data.” IEEE Transactions on smart grid, 2022.
 Usamah N. Chaudhary, Cambre N. Kelly, Benjamin R. Wesorick, Cameron M. Reese, Ken Gall, Samuel B. Adams, Guillermo Sapiro, J. Matias Di Martino. “Computational and image processing methods for analysis and automation of anatomical alignment and joint spacing in recontstructive surgery.” International Journal of Computer Assisted Radiology and surgery, 2022. PDF
 Young Kyung Kim, J Matias Di Martino, Julia Nicholas, Alannah Rivera‐Cancel, Jennifer E Wildes, Marsha D Marcus, Guillermo Sapiro, Nancy Zucker. “Parent strategies for expanding food variety: Reflections of 19,239 adults with symptoms of Avoidant/Restrictive Food Intake Disorder.” International Journal of Eating Disorders, 2021.
 Pradeep Raj Krishnappababu, Matias Di Martino, Zhuoqing Chang, Sam Perochon Perochon, Kimberly LH Carpenter, Scott Compton, Steven Espinosa, Geraldine Dawson, Guillermo Sapiro. “Exploring Complexity of Facial Dynamics in Autism Spectrum Disorder.” IEEE Transactions on Affective Computing, 2021.
 Raphael Achddou, J. Matias Di Martino, and Guillermo Sapiro. “Nested Learning for Multi-Level Classification.” Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, (ICASSP 2021).
 Pablo Massaferro, J. Matias Di Martino, and Alicia Fernandez. “NTL Detection: Overview of Classic and DNN-Based Approached on a Labeled Dataset of 311k Customers.” Proceedings of the IEEE International Conference on Innovative Smart Grid Technologies, (ISGT 2021).
 Zhuoqing Chang, J. Matias Di Martino, Rachel Aiello, Jeffrey Baker, Kimberly Carpenter, Scott Compton, Naomi Davis, Brian Eichner, Steven Espinosa, Jacqueline Flowers, Lauren Franz, Adrianne Harris, Jill Howard, Sam Perochon, Eliana M. Perrin, Pradeep Raj Krishnappa Babu, Marina Spanos, Connor Sullivan, Barbara K. Walter, Scott H. Kollins, Geraldine Dawson, and Guillermo Sapiro. Computational Methods to Measure Patterns of Gaze in Toddlers With Autism Spectrum Disorder. JAMA Pediatrics, 2021.
 Sam Perochon, J. Matias Di Martino, Rachel Aiello, Jeffrey Baker, Kimberly Car- penter, Zhuoqing Chang, Scott Compton, Naomi Davis, Brian Eichner, Steven Espino- sa, Jacqueline Flowers, Lauren Franz, Martha Gagliano, Adrianne Harris, Jill Howard, Scott H. Kollins, Eliana M. Perrin, Pradeep Raj, Marina Spanos, Barbara Walter, Guillermo Sapiro, and Geraldine Dawson. A Scalable Computational Approach to Assessing Response to Name in Toddlers with Autism. Journal of Child Psychology and Psychiatry, 2020.
 J. Matias Di Martino, Qiang Qiu, and Guillermo Sapiro. Rethinking Shape from Shading for Spoofing Detection. IEEE Transactions on Image Processing, 2020.
 J. Matias Di Martino, Fernando Suzacq, Mauricio Delbracio, Qiang Qiu, and Guillermo Sapiro. Differential 3D Facial Recognition: Adding 3D to your State-of-the-Art 2D Method. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
 Pablo. Massaferro, J. Matias Di Martino, and Alicia Ferna ́ndez. “Fraud Detection in Electric Power Distribution: An Approach that Maximizes the Economic Return”. IEEE Transactions on Power Systems, (2019).
 J. Matias Di Martino and Gabriele Facciolo. An Analysis and Implementation of Multigrid Poisson Solvers With Verified Linear Complexity. Image Processing On Line, Vol. 8, 2018. PDF+CODE+DEMO
 J. Matias Di Martino, Jorge Flores, Jose A. Ferrari. One-shot 3D scanning by combining sparse landmarks with dense gradient information. Optics and Lasers in Engineering, Vol. 105, 2018. PDF
 Mercedes Marzoa Tanco, Gonzalo Tejera and J. Matias Di Martino. Computer vision based system for apple detection in crops. International Conference on Computer Vision Theory and Applications (VISAPP), Portugal, 2018. [PDF](http://www.fing.edu.uy/~matiasdm/AdInf/2018_VISAPP_Computer vision based system for apple detection in crops.pdf)
 Pablo Massaferro, Henry Marichal, J. Matias Di Martino, Fernando Santomouro, Juan Pablo Kosut and Alicia Fernandez. Improving electricity non technical losses detection including neighborhood information. IEEE Power & Energy Society General Meeting, Portland US, 2018. [PDF](http://www.fing.edu.uy/~matiasdm/AdInf/2018_PESGM_Improving electricity non technical losses detection including neighborhood information.pdf)
 Gastón A. Ayubi, César D. Perciante, J. Matías Di Martino, Jorge L. Flores and José Ferrari. Generalized phase-shifting algorithms: error analysis and minimization of noise propagation. Applied Optics, Vol. 55, No. 6, 2016. PDF CODE
 J. Matías Di Martino, Gabriele Facciolo, Enric Meinhardt-Llopis. Poisson Image Editing, Image Processing On Line, Vol 6., 2016. PDF+CODE+DEMO
 Marcelo Fiori, J. Matias Di Martino, and Alicia Fernandez. An optimal multiclass classifier design. 23rd International Conference on Pattern Recognition (ICPR), 2016. PDF
 J. Matías Di Martino, Alicia Fernández, Gastón Ayubi and José Ferrari. One-shot 3D gradient field scanning. Optics and Lasers in Engineering, Vol. 72, 2015. PDF
 J. Matías Di Martino, Guzman Hernández, Marcelo Fiori, Alicia Fernández. A new framework for optimal classifier design. Pattern Recognition, Vol. 46, 2013. PDF CODE DEMO
 J. Matías Di Martino, Gastón Ayubi, Enrique Dalchiele, Julia R. Alonso, Ariel Fernández, Jorge L. Flores, César D. Perciante, and José A. Ferrari. Single-shot phase recovery using two laterally separated defocused images. Optics Communications, Vol. 293, 2013.
 J. Matías Di Martino, Alicia Fernández, Pablo Iturralde and Federico Lecumberry. Novel Classifier Scheme for Imbalanced Problems. Pattern Recognition Letters, Vol. 34, 2013.
 J. Matías Di Martino, Federico Decia, Juan Molinelli and Alicia Fernández. A novel framework for nontechnical losses detection in electricity companies. Pattern Recognition - Applications and Methods, Vol. 204, 2013.
 J. Matías Di Martino, Jorge L. Flores, Gastón A. Ayubi, Julia R. Alonso, Ariel Fernández, and José A. Ferrari. Edge enhancement of color images using a digital micro-mirror device. Applied Optics, Vol 51, 2012.
 Gastón A. Ayubi, Jaime A. Ayubi, J. Matías Di Martino, and José A. Ferrari. Pulse-width modulation in defocused three-dimensional fringe projection. Optics Letters, Vol 21, 2010.