Hello, welcome to the Intelligent Computer Vision Research (iCV) group website.

iCV is a research group at Technology Institute of University of Tartu, Estonia. We conduct research for various application of image processing and computer vision. Our team is composed of several highly motivated BS, MS, PhD students and is lead by Assoc. Prof. Gholamreza Anbarjafari (Shahab). We are happy to introduce you to our work and activities in this website!

Here's all the stuff we do

Image processing

Watermarking, Image illumination & contrast enchantment, Image and video SR, coding and compression, HDR and TM, Video coding

Human-Computer interaction

Multimodal emotion recognition, Gesture recognition, Soccer NAO robots vision system

Machine Learning

Late and early fusion, Supervised and semi-supervised learning, Deep learning

Computer Graphics

3D image modelling, Visualization, Retexturing, Virtual reality

iCV current members

Honorary Members

Anastasia Bolotnikova

iCV member 2014-2017

Lembit
Valgma

iCV member 2016-2017

Previous and affiliated members: Ozan Bilici, Aygül Salahli, Ikechukwu Chinonso Ofodile, Siim Schults, Jonathan Griffin, Fatemeh Noroozi, Kristaps Dreija, Andres Traumann, Rainer Keerdo, Kadri Samuel, Suman Sarkar, Pejman Rasti*, Christer Loob

*iCV declares that there is no further tie with this candidate since 25th of May 2017 due to ethical concerns.

Projects in progress

  • TAR16013 (EXCITE) "Estonian Centre of Ecellence in ICT Research (1.09.2016−31.08.2023)", Maarja Kruusmaa, Tallinn University of Technology , School of Information Technologies, Centre for Biorobotics, University of Tartu, Faculty of Science and Technology, Institute of Computer Science, University of Tartu, Faculty of Science and Technology, Institute of Technology, Cybernetica AS.
  • PUT638 "Enhancing Human-Computer Interaction using Multimodal Emotion Recognition based on Gesture, Face, and Speech (1.01.2015−31.12.2018)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.
  • LLTTI16056 "Retexturing of images and garment 3D model creation (1.02.2016−31.12.2017)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.

Completed projects

  • LLTTI17043 "Application for creating a 3D model of a room based on the RGB images taken in a sequence (15.01.2017−15.02.2017)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.
  • LLTTI16396 "3D Head Scan Using Mobile Phones (1.11.2016−31.01.2017)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.
  • LLTTI16378 "HTC VIVE VR (1.10.2016−31.12.2016)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.
  • LLTTI16306 "RFID enabled precise location detector (1.09.2016−1.11.2016)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.
  • VLTTI16119 "Age and Gender estimation (11.04.2016−15.07.2016)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology, Institute of Technology.
  • VLOTI15115 "Automatic drawing (1.10.2015−30.04.2016)", Gholamreza Anbarjafari, University of Tartu, Faculty of Science and Technology (old), Institute of Technology, University of Tartu, University of Tartu, Faculty of Science and Technology, Institute of Technology.

iCV Databases

Here you can find all the databases collected by our group. To obtain any of them, please write to shb[at]icv.tuit.ut.ee.

iCV-F Database

Database was initially created for the development of face recognition algorithm for Human Robot Interaction scenario. NAO V4 robot was used as a platform for collecting the images. Database includes faces with almost uniform lighting and background

Kinect-2 3D Objects Database

Database contains Kinect-2 recordings of various objects from different perspectives (360 deg). Corresponding RGB and Depth information is available for each object and angle. Database is used for reconstructing 3D model of an object from the point cloud of depth information.

iCV MEFED Database

We have developed a new huge facial expression database called iCV Multi-Emotion Facial Expression Dataset (iCV-MEFED), designed for multi-emotion recognition. The database includes 31250 facial faces with different emotions of 125 subjects whose gender distribution is almost uniform. Each subject acts 50 different emotions and for each of these emotions 5 samples have been taken by Canon 60D camera under uniform lightening condition with relatively unchanged background and resolution of 5184x3456 per sample. The images are taken and labelled under supervision of psychologists and the subjects have been trained about the acting emotions that they posed.

iCV SASE Database

We have compiled a 3D head pose database of 50 subjects with varying poses and respective labels, called SASE. The data has been collected using Kinect2 from 50 subjects. The subjects changed their head-poses in front of the sensor and the captured sequences consist of RGB frames, depth frames and corresponding labels.

iCV Partners

HuPBA

Human Pose Recovery and Behavior Analysis Research Group in University of Barcelona

EMU

Department of Electrical and Electronic Engineering - Eastern Mediterranean University

VAPL

Visual Analysis of People Laboratory

Top collaborators: Sergio Escalera, Kamal Nasroullahi, Cagri Ozcinar, Hasan Demirel, Dorota Kaminska, Marina Marjanovic, Jüri Allik, Thomas B Moeslund

Wish to contact us?