Type: User
Company: CNRS-AIST JRL (Joint Robotics Laboratory), IRL
Bio: Msc. student in Computer Vision and Robotics at Université de Bourgogne 🇫🇷
BSc in Electronic Engineering at UNI 🇵🇪
Location: Tsukuba, Japan
Blog: gracesevillano.github.io
gracesevillano's Projects
Solutions for Advanced Image Analysis course assignments, featuring model designs for image summation and generation with MNIST, and style transfer using CycleGAN with MNIST and SVHN datasets.
Detailed solutions to three programming assignments from the Computer Vision course taught by Prof. Renato Martins, covering corner detection, object recognition, and epipolar geometry.
This repository presents exercises related to magnetic resonance imaging (MRI) and an introduction to quantitative magnetic resonance imaging (qMRI).
My personal website
Traditional Image Processing Techniques for Nailfold Capillary Detection: A project showcasing a non-ML/DL approach to detect and count nailfold capillaries, emphasizing the application of fundamental image analysis methods in medical diagnostics.
Proyecto demostrativo de cómo desarrollar y desplegar una página web estática utilizando HTML y GitHub Pages, ideal para principiantes en desarrollo web.
This is a repository for a robotics project
This project not only provides hands-on experience with VHDL but also offers insight into the fundamental concepts of CPU architecture and design. It bridges the gap between theoretical knowledge and practical application, using the Nexys4 DDR board as a testbed
detector de sacos
A collection of Tkinter GUI exercises from the VIBOT master's program, demonstrating basic to complex GUI applications in Python. These exercises showcase my hands-on experience with Tkinter, covering everything from user input forms to dynamic graphical simulations and a calculator.
This repository is dedicated to the collection of 10 laboratory reports from the "Scene Segmentation and Interpretation" course, a key component of the Master Degree in Vision and Robotics (VIBOT). Each lab focuses on a specific aspect of scene segmentation and interpretation, employing various techniques from edge detection to image restoration.
Classification project using Self-Organizing Maps (SOM) to differentiate patients and healthy subjects from marker data, encompassing network construction, training, and testing phases.