Research Activities |
|
VIPSAFE Automated Visual Monitoring for Improving Patient SAFEty - VIPSAFE is a R&D Project fruit of a collaboration between two research centers: Sabanci University and Kalrsruhe Institut of Technology, and two companies: Videmo and Vistek. This 36 month long project is co-funded by Tübitak and BMBF with the main goal of improving patients’ safety by means of automated visual monitoring. |
|
|
|
|
|
IronDB MR - based Analysis, Indexing, and Retrieval of Brain Iron Deposition in Basal Ganglia - This multi-disciplinary project targets to significantly improve the understanding of neurodegenerative diseases by developing automatic methods that enable relating the brain iron accumulation to various diseases and complications.
This project involves a multi-disciplinary research requiring novel solutions from medical image processing, pattern recognition, search and retrieval, and clinical science.
This is a joint project with Philips Research Eindhoven.
|
|
|
|
|
Slice Matching - The aim is to retrieve relevant slice from a 3D medical image data of a subject given a query image of another subject. Such a solution can aid the medical experts in diagnosing anatomical structure specific diseases, such as basal ganglia or hypocampus disorders. |
|
|
|
Patient Search - Patient-to-patient search, which can be defined as comparing multiple patients and retrieving relevant cases among them, should especially help the medical expert in diagnosis of diseases whose causes and progress have not yet been completely unraveled, and diseases that affect large number of patients such as Alzheimer’s and Parkinson’s.
|
|
|
|
Iron Quantification - Iron accumulation in the brain is a normal process that starts after age 20 and observed in every individual. However, in those developing neurodegenerative diseases deep gray matter structures of the brain accumulate abnormal (larger) amounts of iron. Here, our aim is to analyze and quantify iron deposited in the brain using image analysis techniques. |
|
|
|
|
|
NEDO International Research Coordination of Driving Behavior Signal Processing based on Large Scale Real World Database - The research team makes an endeavor on collecting in-car human behavioral signals, across cultures and social systems. The goal of the project is (1) corraborative data collection of in-car driving behavior signals under operation of in-car spoken dialogue systems at Japan, US and Europe (Turkey), (2) proposing a model of driving behavior and evaluate it through driver identification, (3) draft document for the international standard ISO TC22 related to the interaction between in-car speech communication and driving. |
|
|
|
|
|
|
CARIA Computer Aided Reconstruction in Archeology - The objective is to assist with the reconstruction of large archeological artifacts (such as pottery fragments, marble relief pieces or mosaics) using computational tools and to electronically disseminate such reconstructed artifacts (such as, through a virtual museum). |
|
|
|
Logo Recognition in Videos an Automated Brand Analysis System - A novel brand logo analysis system which uses shape-based matching and scale invariant feature transform (SIFT) based matching on graphics processing unit (GPU) is proposed developed and tested. The system is described for detection and retrieval of trademark logos appearing in commercial videos. |
|
|
|
Stereo Based 3D Head Pose Tracking - In this project a new stereo-based 3D head tracking technique, based on scale-invariant feature transform (SIFT) features, that is robust to illumination changes is proposed. |
|
|
|
Graphical Model Based Facial Feature Point Tracking - Feature point tracking is a challenging topic in case of arbitrary head movements and uncertain data because of noise and/or occlusions. With this motivation, a graphical model that incorporates not only temporal information about feature point movements, but also information about the spatial relationships between such points is built. |
|
|
|
|
Face Recognition from Video Using Superresolution Techniques - Performance of current face recognition algorithms reduces significantly when they are applied to low-resolution face images. To handle this problem, superresolution techniques can be applied either in the pixel domain or in the face subspace. |
|
|
|
|
|
|
|
|
|
Segmentation - In the framework of IronDB project, we provide results of brain Basal Ganglia organs segmentations, such as Caudate Nucleus and Putamen. |
|
|
|