Fidel Alejandro Guerrero Peña

Fidel Alejandro Guerrero Peña
École de Technologie Supérieure · Laboratory for Imagery Vision and Artificial Intelligence (LIVIA)

PhD in Computer Science

About

34
Publications
7,856
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
523
Citations
Introduction
Fidel has a Bachelor degree in Computer Science from the Universidad de Oriente, Cuba (2013) and a Master Degree in Computer Science from the Informatic Center of the Federal University of Pernambuco, Brazil (2017). In the period 2013-2015 worked as lecturer in Artificial Intelligence at Universidad de Oriente, Cuba. Since November 2016 works as a Computer Vision and Image Processing researcher in Motorola LLC/CIn partnership, Brazil. Currently is a Ph.D Student in Computer Science at the Federal University of Pernambuco and a Special Visiting Ph.D. Student in the Biology and Biological Engineering division of the California Institute of Technology, USA.
Additional affiliations
May 2020 - May 2021
California Institute of Technology
Position
  • Consultant
January 2017 - November 2019
Federal University of Pernambuco
Position
  • Researcher
September 2013 - March 2015
Universidad de Oriente
Position
  • Lecturer
Education
November 2018 - November 2019
California Institute of Technology
Field of study
  • Biology and Biomedical Engineer
March 2017 - November 2019
Federal University of Pernambuco
Field of study
  • Computer Science
March 2015 - February 2017
Federal University of Pernambuco
Field of study
  • Computer Science

Publications

Publications (34)
Preprint
Full-text available
Object detection models are commonly used for people counting (and localization) in many applications but require a dataset with costly bounding box annotations for training. Given the importance of privacy in people counting , these models rely more and more on infrared images, making the task even harder. In this paper, we explore how weaker leve...
Preprint
Full-text available
Data augmentation is one of the most effective techniques for regularizing deep learning models and improving their recognition performance in a variety of tasks and domains. However, this holds for standard in-domain settings , in which the training and test data follow the same distribution. For the out-of-domain case, where the test data follow...
Preprint
Full-text available
A powerful way to adapt a visual recognition model to a new domain is through image translation. However, common image translation approaches only focus on generating data from the same distribution of the target domain. In visual recognition tasks with complex images, such as pedestrian detection on aerial images with a large cross-modal shift in...
Conference Paper
Full-text available
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces and some promising properties like mode connectivity. However, finding the permutation that minimizes some ob-jectives is challenging, and current optimization techniques are...
Article
Full-text available
The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present a significant number of improvements introduced in the challenge since our 2017 report. These include the creation of a new segmentation-only benchmark, the enrichment of the dataset...
Chapter
In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with reduced costs and improved comfort. This is typically achieved by detecting people using compact embedded devices that are installed on the room’s ceiling, and that integra...
Preprint
Full-text available
The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces, and some promising properties like mode connectivity. However, finding the right permutation is challenging, and current optimization techniques are not differentiable, which...
Preprint
Full-text available
In intelligent building management, knowing the number of people and their location in a room are important for better control of its illumination, ventilation, and heating with reduced costs and improved comfort. This is typically achieved by detecting people using compact embedded devices that are installed on the room's ceiling, and that integra...
Conference Paper
We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. When adding a Youden's J statistic regularization term to the cross entropy loss we improve the separation of touching and immediate cells, obtaining sharp segmentation boundaries with high adequacy. This regulariz...
Preprint
We propose a deep metric learning model to create embedded sub-spaces with a well defined structure. A new loss function that imposes Gaussian structures on the output space is introduced to create these sub-spaces thus shaping the distribution of the data. Having a mixture of Gaussians solution space is advantageous given its simplified and well e...
Preprint
Full-text available
We propose a new loss formulation to further advance the multiclass segmentation of cluttered cells under weakly supervised conditions. We improve the separation of touching and immediate cells, obtaining sharp segmentation boundaries with high adequacy, when we add Youden's $J$ statistic regularization term to the cross entropy loss. This regulari...
Chapter
Full-text available
We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when supervised learning is used for image analysis as the discriminative power of a learning model might be compromised...
Article
We propose a new incremental aggregation algorithm for multi-image deblurring with automatic image selection. The primary motivation is that current burst deblurring methods do not handle well situations in which misalignment or out-of-context frames are present in the burst. These real-life situations result in poor reconstructions or manual selec...
Preprint
Full-text available
Multi-Focus Image Fusion seeks to improve the quality of an acquired burst of images with different focus planes. For solving the task, an activity level measurement and a fusion rule are typically established to select and fuse the most relevant information from the sources. However, the design of this kind of method by hand is really hard and som...
Preprint
Full-text available
We present a weakly supervised deep learning method to perform instance segmentation of cells present in microscopy images. Annotation of biomedical images in the lab can be scarce, incomplete, and inaccurate. This is of concern when supervised learning is used for image analysis as the discriminative power of a learning model might be compromised...
Conference Paper
We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space representation for expression recognition. We devise this architecture based on two fundamental complementary components: (1) facial image correction and attention and (2) facia...
Preprint
We present a new end-to-end network architecture for facial expression recognition with an attention model. It focuses attention in the human face and uses a Gaussian space representation for expression recognition. We devise this architecture based on two fundamental complementary components: (1) facial image correction and attention and (2) facia...
Article
ColorCheckers are reference standards that professional photographers and filmmakers use to ensure predictable results under every lighting condition. The objective of this work is to propose a new fast and robust method for automatic ColorChecker detection. The process is divided into two steps: (1) ColorCheckers localization and (2) ColorChecker...
Preprint
Full-text available
We propose a new incremental aggregation algorithm for multi-image deblurring with automatic image selection. The primary motivation is that current bursts deblurring methods do not handle well situations in which misalignment or out-of-context frames are present in the burst. These real-life situations result in poor reconstructions or manual sele...
Preprint
Full-text available
ColorCheckers are reference standards that professional photographers and filmmakers use to ensure predictable results under every lighting condition. The objective of this work is to propose a new fast and robust method for automatic ColorChecker detection. The process is divided into two steps: (1) ColorCheckers localization and (2) ColorChecker...
Conference Paper
We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. We are primarily motivated by the need of developmental biologists to quantify and model the behavior of blood T -cells which might help us in understanding their regulation mechanisms and ultimately help researchers in their quest for developing an eff...
Preprint
Full-text available
We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. We are primarily motivated by the need of developmental biologists to quantify and model the behavior of blood T-cells which might help us in understanding their regulation mechanisms and ultimately help researchers in their quest for developing an effe...
Article
Full-text available
This paper proposes a method to recognize occluded objects in digital images. It provides a new approach to the use of Hidden Markov Models for segmentation of overlapping objects. To validate the proposed method several experiments were executed with different databases. In all cases high levels of effectiveness were obtained.
Article
Full-text available
People detection and tracking is of vital interest for its many applications, such as video surveillance, driver assisted systems, evaluation tools in the medicine, human-computer interaction. In this work is presented an application to carry out tasks of video surveillance with low resolution cameras. This application is based on video sequences c...
Article
Shape classification has multiple applications. In real scenes, shapes may contain severe occlusions, hardening the identification of objects. In this paper, a method for object recognition under severe occlusion is proposed. Occlusion is dealt with separating shapes into parts through high curvature points, then tangent angle signature is found fo...
Conference Paper
A method based on hidden Markov models is described capable of dealing with severe part occlusions in different object recognition situations. Occlusion is dealt with separating shapes into parts through high curvature points, tangent angle signatures for each part and continuous wavelet transform for signatures. A hidden Markov model is created fo...
Article
Full-text available
Digital image processing and computer vision are frequently used in medicine at present and the proposals of new methods of automatic analysis of digital images or the efficiency improvement of the existing are of great interest. In this work new methods to computationally study sickle cell disease through blood samples images are developed, an ill...
Article
The study of cell morphology is an important aspect of the diagnosis of some diseases, such as sickle cell disease, because red blood cell deformation is caused by these diseases. Due to the elongated shape of the erythrocyte, ellipse adjustment and concave point detection are applied widely to images of peripheral blood samples, including during t...

Network

Cited By