Computer Vision and Biometrics

In the area of Computer Vision and Biometrics (CVB, also specialisation for EE/EMSYS), we have Master's assignments continuously on the following subjects:

Finger vein recognition (recognition methods and development of sensors)
Face morphing detection
Image manipulation detection (e.g. deepfake detection)
Embedded AI
Heritage biometrics (human traces on historic objects and works of art)
3D face recognition
Iris recognition
Forensic biometrics
Robust vision

If you are interested in any of these subjects, please contact l.j.spreeuwers@utwente.nl

Below follows a list of assignments with a concrete description.

[B] Morphing robust face recognition

[B] [M] FISWG AUTO: Automatic extraction and use of forensic facial features

Analyzing Visual and Identity-Level Differences Between Synthetic and Real Face Datasets

[B] Heritage biometrics – 3D acquisition design for fingerprints, scratches and toolmarks on works of art

[MB] Will it fail? Generating videos of actions fails

[MB] Deriving text descriptions from visual model's predictions

[B] Heritage Biometrics – Possibilities with AI in Furniture & Wood Conservation

[B] Heritage Biometrics: does every painter paint himself?

[B] Heritage biometrics – artist profiling from 3D fingerprints

[B] Temporal Surgical Video Segmentation for Medical Dataset Curation

[B] Surgical Phase Pattern Recognition from Video Data

[B] Driver Behavior Understanding for Monitoring Fatigue and Anomalous Behavior in Autonomous Driving

[B] Discovery of missing objects in predefined scene images

[B] Pose Estimation in Handball Videos for Personalized Training

[B] Egocentric vision for human behaviour understanding

[B] Understanding the Effect of Image Quality and Resolution on Skin Lesion Recognition

[B] Recognition of Crops Relevant for Food Security from Images – Dataset Compilation and Classification Framework Design

[B] Benchmarking Medical Class-OOD (aka Open Set Recognition) Detection

[B] OOD detection on MediCLIP

[B] Can Normalizing Disentangled Flows Detect OOD data?

[B] Medical OOD detection with an Exponentially Tilted Gaussian Prior for beta-Variational Autoencoders

[B] Can you find the Gorilla in the CT scan? (2 topics: Sample and Object level)

[B] Why can’t Vision-Language Models like CLIP find OOD data in medical images? Or can they? How?

[B] Can Normalizing Disentangled Flows Detect OOD data?

[B] Disentangled Flows for Face editing

[B] Disentangled Flows for Anomaly Detection

[B] Self-Supervised Out-of-Distribution Detection

[B] Unsupervised Anomaly Detection Under Domain Shifts

[B] [M] AUTO: Auto encoders in face recognition

[M] [B] Computer Vision & Machine Learning @ Lely

[B] [M] DIET: from obese data to sparse face models

[B] Evaluation of AI-driven interpretation on microscopic images in oncology

[M][B] Visual place recognition

[B] TURBULENCE: 2D gen – 3D pose pipeline – atmospheric turbulence