Luis A. Figueroa

Hello there! I'm a Research Engineer in the Research Engineering and Design Lab at Adobe Research. Previously, I was a GEM Full Fellow in the Biomedical Engineering Department at Carnegie Mellon University.


My main research interests are in computer vision, machine learning, and deep learning. I have broader interests in applied mathematics, cognitive science, health, and medicine.


I earned my BA in Computer Science and Mathematics from Occidental College where I was advised by Dr. Celia Chen and Dr. Kathryn Leonard in the Department of Computer Science and by Dr. Jay Daigle in the Department of Mathematics.


I'm always happy to chat about anything and everything, feel free to connect with me to grab a cup of coffee!


[GitHub] [Google Scholar] [CV] [LinkedIn]

My picture


[Jun.  2021] Returning to Adobe Research as a Research Engineer
[May  2021] Graduating from Carnegie Mellon University
[May  2020] Returning to Adobe Research as a Computer Vision Research Intern, Summer 2020
[Sep.  2019] Joining Dr. Robert Murphy at the CMU Computational Biology Department
[Aug.  2019] Starting my MS in Biomedical Engineering at Carnegie Mellon University in Pittsburgh, PA
[May  2019] Graduating from Occidental College and named a 2019 GEM Full Fellow by The National GEM Consortium
[Apr.  2019] Joining Adobe Research as a Computer Vision Research Intern, Summer 2019



Deep neural network for precision multi-band infrared image segmentation
Thomas Lu, Alexander Huyen, Kevin Payumo, Luis Figueroa, Edward Chow, and Gil Torres
SPIE, 2018
PDF   Abstract   Bibtex  

Image segmentation is one of the fundamental steps in computer vision. Separating targets from background clutter with high precision is a challenging operation for both humans and computers. Currently, segmenting objects from IR images is done by tedious manual work. The implementation of a Deep Neural Network (DNN) to perform precision segmentation of multi-band IR video images is presented. A customized pix2pix DNN with multiple layers of generative encoder/decoder and discriminator architecture is used in the IR image segmentation process. Real and synthetic images and ground truths are employed to train the DNN. Iterative training is performed to achieve optimum accuracy of segmentation using a minimal number of training data. Special training images are created to enhance the missing features and to increase the segmentation accuracy of the objects. Retraining strategies are developed to minimize the DNN training time. Single pixel accuracy has been achieved in IR target boundary segmentation using DNNs. The segmentation accuracy between the customized pix2pix DNN and simple thresholding, GraphCut, simple neural network and ResNet models are compared.

  		  title={Deep neural network for precision multi-band infrared image segmentation},
  		  author={Lu, Thomas and Huyen, Alexander and Payumo, Kevin and Figueroa, Luis and Chow, Edward and Torres, Gilbert},
  		  booktitle={Pattern Recognition and Tracking XXIX},
  		  organization={International Society for Optics and Photonics}


Anomaly Network for Detecting Brain Aneurysms
Final Project, Methods in (Bio)Medical Image Analysis
Carnegie Mellon University, Spring 2020

Part-of-Speech Tagger for Non-Natural Language
Senior Comprehensive Project, Department of Computer Science
Occidental College, Spring 2019

Image Processing Methods for Detection of Regions of Interest in Mammograms
Research Project, Department of Computer Science
Occidental College, Spring 2018

Teaching Experience

Data Structures (COMP 229)
Lead Teaching Assistant, Spring 2019

Data Structures (COMP 229)
Teaching Assistant, Fall 2018

Mathematical Foundations of Computer Science (COMP 149)
Teaching Assistant, Spring 2018