Computer Vision - Machine learning engineer

Artificial Inteligence Engineer from Polytech’Nice-Sophia’s university graduated in Mathematics and Modeling in 2015.

Graduated from IAE as well in Business Administration.

MY experience


Work Experience

FEB 2016 - JUNE 2018

Research Engineer

CNRS - Sophia-Antipolis (France)

Part of the DigiArt project. 3D object recognition using Structure Sensor device. Evaluation of 3D detectors and descriptors. 3D object retrieval using Similarity Search, SVM and Interactive Learning. iOS application
Paper accepted ICIP 18 : An interactive Content-Based 3D Shape
Retrieval System for on-site Cultural Heritage Analysis 

MAR 2015 - SEPT 2016

Intern 
Engineer

Panasonic / Singapore

Visual Odometry for self-localization using a prior-map
Evaluation of the state of the art algorithm related to
SLAM/Visual Odometry
HD Map building
Annotation tool software for labelling frames
Modification of a SLAM algorithm in order to use it in our case 

SUMMER 2014

Intern 
Engineer

Samsamia / London

Logo retrieval using Bag of Words scheme
Implementation fo several 2D detectors and descriptors
Implementation of Support Vector Machine
Implementation of Bag of Words algorithm
Integration inside the main core library 

Projects

3D Shape Retrieval Engine for archeological artefacts


Based on the association of similarity search technique and active learning, this algorithm is designed to help non-expert users to make their way in the machine learning territory. Our Content-Based 3D shape Retrieval (CB3DR) solution aims at scanning an object on the fly with a low-cost 3D sensor and retrieving similar shapes or informations of similar objects from a database using the 3D point cloud acquired.

Gender and Age Estimation of Pelvis bones using Deep Learning


Archeological tool develped for estimate gender and age of a human pelvis bone acquired from a low cost 3D sensor. We decided to treat those problems distinctly for practical reasons. The gender can be easily estimated throught shape analysis of the bone. This was made using the PointNet network. On the other hand, the age is harder to retrieve because of the quality of the sensors we used so we used the DeepTEN network which was our best option at that time.

Analysis of video streams in drone


6 month Research project 

Writing of the specification
Writing of a systematic literature review
Stabilization of the video
Detection, tracking and recognition of different type of vehicles

Autonomous RC car guided by Computer Vision


Understanding of hardware and software (Servo-motors, Raspberry)
Use image processing with a motorized picamera and algorithms to find target and avoid obstacles.
Vanishing point approach 

Publications 

1.

An Interactive Content-Based 3D Shape Retrieval System for On-Site Cultural Heritage Analysis
2018 IEEE International Conference on Image Processing (ICIP)

Additional 

Online training - Python and Computer Vision

A 10 months training online (from November 2015 to August 2016).
"This project has only one goal — to make developers, programmers, researchers, and students become awesome at solving real-world computer vision problems."
It is a an actionable, real-world 10 month course on OpenCV and computer vision.

Topics covered:

- Computer Vision and OpenCV Basics

- Building your own custom object detector

- Content-Based Image Retrieval/Image Search Engines

- Face Recognition

- Automatic license plate recognition

- Hadoop + Big Data

- Deep Learning

- Raspberry Pi Projects

- Describing Images with Image Descriptors

- Computer Vision Case Studies
Face detection in images and photos
Eye tracking
Object tracking in video
Handwriting recognition
Plant classification
License plate recognition
Measuring distance from camera to object in image

>