Profile image of tfreitas23
@tfreitas23
Member since August 4, 2016
0 Recommendations

tfreitas23

Online Offline
I have an Integrated Master in Bioengineering (MIB), Faculty of Engineering of Porto (FEUP), branch of Biomedical Engineering. I did my master thesis in Multimodal Facial Recognition using low-cost sensors (Kinect and Intel RealSense). Vision Computing, Image processing and Machine Learning have been one of my passions, developed mainly in my time in FEUP. My main technical competences include Image Processing, Pattern Recognition, Visual Computing and Machine Learning. I am fluent in languages like Matlab, C, C++ (including OpenCV and PCL). I still have some familiarity and knowledge in Android and Python and some basic knowledge in LabView and SQL.
0 reviews
0.0
  • N/AJobs Completed
  • N/AOn Budget
  • N/AOn Time
  • N/ARepeat Hire Rate

Portfolio

Recent Reviews

No reviews.

Experience

MSc Student

Nov 2015 - Jul 2016 (8 months)

Masther Thesis Student in 3D Face Recognition Under Unconstrained Settings Using Low-Cost Sensors

Scholarship Researcher

Apr 2015 - Sep 2015 (5 months)

Research work in CT Lung images, where I worked on juxta-vascular nodule detection.

Education

Integreated Master in Bioengineering - Biomedical Engineering

2011 - 2016 (5 years)

Publications

An improved method for juxta-vascular nodule candidate detection

In this paper we propose a new 3D Hessian based medialness filter for the candidate detection phase in order to improve the quality of the juxta-vascular nodules that were identified as a problem in some recent approaches. Our approach shows a significant improvement for the juxta-vascular cases, by having a considerable reduction onthe number of false positives (FP) when comparing with other methods.

Multimodal Hierarchical Face Recognition using Information from 2.5D Images

In this paper we propose a multimodal extension of a previous work, based on SIFT descriptors of RGB images, integrated with LBP information obtained from depth scans, modeled by an hierarchical framework motivated by principles of human cognition. The framework was tested on EURECOM dataset and proved that the inclusion of depth information improved significantly the results in all the tested conditions, compared to independent unimodal approaches.

A Comparative analysis of deep and shallow features for multimodal face recognition

We propose a new RGB-depth-infrared (RGB-D-IR) dataset, RealFace, acquired with the novel Intel RealSense collection of sensors, and characterized by multiple variations in pose, lighting and disguise. We conclude that our dataset presents some relevant challenges and that deep feature descriptors present both higher robustness in RGB images, as well as an interesting margin for improvement in alternative sources, such as depth and IR.

Verifications

  • Facebook Connected
  • Preferred Freelancer
  • Payment Verified
  • Phone Verified
  • Identity Verified
  • Email Verified

Browse Similar Freelancers