Status: open
Supervisor: Markus Diem
nomacs – Image Lounge is a light-weight image viewer developed at CVL. It is written in C++ with Qt and OpenCV and published under GPL. Since two years, nomacs has a plugin system which allows for adding modules dedicated to specific tasks.
Task
A people search plugin will be implemented in this work. The workflow has three stages. First, faces are detected in images using state-of-the-art face detection from a 3rd party library such as OpenCV. Then, users can annotate faces. Faces with the same label (i.e. name) are used to train a model for face recognition. Having trained models, users can retrieve all images with a specific face. (<- that's the use case)
Objectives
The student gains profound knowledge of state-of-the-art face recognition algorithms. In addition, this work deepens programming skills in C++ with libraries such as Qt.
Requirements
- C++ knowledge
- Computer Vision knowledge (e.g. Machine Learning for Visual Computing)
- Experience in coding with Qt and/or OpenCV (nice to have)