Computer Vision And Pattern Analysis Laboratory Home Page  Home
People  People
Publications  Publications
Publications  Databases
Contact Information  Contact
Supported Research Projects  Supported Research Projects
Research Activites  Research Activites
Research Groups
SPIS - Signal Processing and Information Systems Lab.SPIS - Signal Processing and Information Systems Lab.
Medical Vision and Analysis Group  Medical Research Activities
Biometrics Research Group  Biometrics Research Group
SPIS - Signal Processing and Information Systems Lab.MISAM - Machine Intelligence for Speech Audio and Multimedia.
Knowledge Base
  Paper Library
VPA Research where Aytul Ercil is Involved

Research Activities
Facial Expression Recognition - Facial Expression Analysis is an interdisciplinary research area that combines related areas such as psychological and behavioral studies and computer vision. The FER system has a number of application areas such as emotion communication, clinical psychology, psychiatry,pain assessment, lie detection and human computer interface.

Research Activities

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.

Tubitak 108E126
Kanser Tedavi Takibi icin Yeni Medikal Image Analizi Metotları
- Bu projede geliştirilecek olan medikal imge analizi metotları MR görüntülemeye seyir takip bilgisi saglayıp kanser tedavisi sürecinin klinik ortamda izlenmesine yardımcı olacaktır.

3D Scanning of Transparent Objects - The aim of this project is to develop a 3D scanner for transparent objects like glass.

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.

Development of Electroencephalography (EEG) Signal Analysis Techniques for Brain Computer Interface (BCI) Systems - Electroencephalography (EEG) based Brain-Computer Interface (BCI) systems are a new development in the field of applied neurophysiology. In this project, our objective is to develop new signal analysis and pattern recognition algorithms based on statistical graphical models, and to demonstrate the effectiveness of these algorithms both on standard data sets and on the data collection and BCI system we will set up.

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.

Signal Processing and Advanced Information Technologies for improving Driver/Driving Prudence and Accident Reduction
- In this initiative, we propose to create conditions for prudent driving on highways and roadways with the purposes of reducing accidents caused by driver behavior.

Coupled Non-Parametric Shape and Moment-Based Inter-Shape Pose Priors for Multiple Basal Ganglia Structure Segmentation - Brain tissue and structure segmentation in magnetic resonance (MR) images is a fundamental problem in clinical studies of brain structure and function. Due to limitations such as low contrast, partial volume effects, and field inhomogeneities, the delineation of subcortical (basal ganglia) structures such as caudate nucleus, putamen, and thalamus from white matter, gray matter and cerebrospinal fluid (CSF) is a very challenging problem.

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.

New Generation Information Processing Techniques for Imaging Sensors and Wireless Sensor Networks
- The objective of this project is to develop principled and practical new signal and information processing methods for a number of sensing systems including wide-angle radar, magnetic resonance brain imaging, and wireless micro-sensor networks.

Machine Learning Systems For Detecting Driver Drowsiness - In this project the development of machine learning systems for drowsy driver detection is proposed.

Signal, Image Processing and Pattern Recognition for Intelligent Automation CEnter
- The main goal of SPICE is to create links with other qualified, European institutions of higher education and research with a view to developing joint research projects, and enhance participation of Turkey in the EU FP programmes.

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.

Development of an Automated Glass Fragments (cullets) separation machine
- The proposed project aims to develop a system to perform the separation of glass from other materials like stone, ceramics, aluminum and porcelain.
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.

Online Handwritten Mathematical Expression Recognition
- We have developed a system for online handwritten mathematical expression recognition together with a user-interface for writing scientific articles.

Different Approaches on the Implementation of Implicit Polynomials in Visual Tracking - In this work, we are interested in tracking a free-form object whose boundary can be described by a planar algebraic curve.

Moulding on Demand - New flexible, eco efficient system for JIT Moulding Production
- The aim of this project Is to study, develop and produce a new flexible, eco-efficient system for JIT (Just-in-Time) moulding production.

NSF- IIS-0205477
ITR - 3D Form Models for the Representation, Manipulation, and Recovery of Shape with Applications to Archealogy and Virtual Sculpting
- The goal of this project is to investigate approaches to shape representation, analysis, manipulation, and estimation from unstructured sensor data in the context of tackling certain key problems in archaeology.

A Robust Object Recognition and Pose Estimation System for Robotic Applications
- The aim of the project is rapid and accurate identification of 2-D objects and pose estimation. This project received the Interpro best R&D project award in May 2003.

E! 2007 FACTORY PACK 2000
Flexible, Environment Friendly Packing System, Utilizing Advanced Vision Technology and Recyclable/Homogenous Materials
- EUREKA project E! 2007 FACTORY PACK 2000 developed a new recyclable plastic packaging material which can be used as beads or compacted into boards. PACK 2000 project has been selected as a EUREKA success story.

Segmentation - In the framework of IronDB project, we provide results of brain Basal Ganglia organs segmentations, such as Caudate Nucleus and Putamen.

Home Back