collaborators

6 papers

cs.CV2019

J Regularization Improves Imbalanced Multiclass Segmentation

Fidel A. Guerrero Peña, Pedro D. Marrero Fernandez, Paul T. Tarr +3

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 im…

cs.CV2019

A Multiple Source Hourglass Deep Network for Multi-Focus Image Fusion

Fidel Alejandro Guerrero Peña, Pedro Diamel Marrero Fernández, Tsang Ing Ren +2

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 r…

cs.CV2019

A Weakly Supervised Method for Instance Segmentation of Biological Cells

Fidel A. Guerrero-Peña, Pedro D. Marrero Fernandez, Tsang Ing Ren +1

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…

cs.CV2019

FERAtt: Facial Expression Recognition with Attention Net

Pedro D. Marrero Fernandez, Fidel A. Guerrero Peña, Tsang Ing Ren +1

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 represe…

cs.CV2017

SEGMENT3D: A Web-based Application for Collaborative Segmentation of 3D images used in the Shoot Apical Meristem

Thiago V. Spina, Johannes Stegmaier, Alexandre X. Falcão +2

The quantitative analysis of 3D confocal microscopy images of the shoot apical meristem helps understanding the growth process of some plants. Cell segmentation in these images is…

cs.CV2017

Cell Segmentation in 3D Confocal Images using Supervoxel Merge-Forests with CNN-based Hypothesis Selection

Johannes Stegmaier, Thiago V. Spina, Alexandre X. Falcão +4

Automated segmentation approaches are crucial to quantitatively analyze large-scale 3D microscopy images. Particularly in deep tissue regions, automatic methods still fail to provi…