Introduction

The goal of Intelligent Media Lab. is to study and develop a variety of intelligent systems with human-like intelligence.

For doing this, we are focused on studying several basic techniques such as 1) Digital Image and Video Processing, 2) Pattern Recognition, 3) Computer Vision, 4) Computational Intelligence, 5) Machine Learning, 6) Deep Learning and 7) Graphical Models.

Based on these basic techniques, we are developing a variety of algorithms for 1) Face Analysis (Face Detection, Eye Detection, Lip-reading, Facial Feature Detection, Gaze Tracking, Head Pose Tracking, Gender Classification, Age Estimation, Facial Expression Recognition, Face Recognition, Facial Disguise Discrimination), 2) Human Analysis (Pedestrian Detection, Body Part Detection, Human Pose Estimation, Human Tracking, Body Part Tracking, Gesture Recognition, Human Behavior Understanding), 3) Video Analysis (Visual Surveillance System, Object Recognition, Abandoned/Removed Object Classification, Business Card/Document Classification), and 4) ADAS(Traffic sign detection/recognition, Traffic light detection/recognition, Vehicle detection/recognition, lane detection).

The developed algorithms are applied to many applications such as Smart Phones/TVs/Glasses, Intelligent UI/UX, Human Computer Interaction/Human Robot Interaction, Video Surveillance/Security, Intelligent Vehicles/Safety Cars, Robotics, and many others.