Research > Projects

Current Projects

Development for an Android Malware Detection Algorithm based on Deep Learning (Samsung Electronics)

2015/07/10~

Detection of Android Malware using Deep Learning Techniques

Deep Learning Research for Multiview Car Reidentification (Hanwha Techwin)

2015/07/01~

Multi-camera Car Reidentification

Deep Learning Research for Crowd Behavior Analysis System (Hanwha Techwin)

2015/07/01~

Group State Analysis in Crowd Scenes

Basic Research of Human-level Lifelong Machine Learning SW (Ministry of Science, ICT and Future Planning; Machine Learning Center)

2014/04/01~

Development of Human-level Lifelong Machine Learning Algorithm

Driver-Assistant Active Safety System: Intelligent driver assistance system based on irregular behavior detection and augmented reality (NCRC)

2010/09/01~

Development of low-power/high-performance vision algorithms of the active safety driver assistance systems

Multi-modal Emotion Recognition based on Speech and Facial Expression (Ministry of Trade, Industry and Energy)

2012/12/01~

Development of multi-modal emotion recognizer based on speech and facial expression

Automatic speech translation (ETRI)

2013/05/01~

Development of continuous speech recognition engine based on semi-Markov model

 

Completed Projects

Development of Analytical Techniques of Face Attribute (Samsung)

2014/05/10 ~ 2014/12/31

Development of Analytical Techniques of Face Attribute

Object Classification for Automatic Image Annotation (LG)

2014/03/24 ~ 2014/11/28

Development of object classification algorithm for Automatic Image Annotation

Acoustic user interface (Hyundai Motor)

2013/05/01 ~ 2014/08/31

Development of sound classification algorithm for acoustic human-car interface

Cognitive Multimedia Fingerprinting for Next Generation Fast Semantic Retrieval on the Large Scale Data (NRF)

2013/05/01 ~ 2014/04/30

Development of fast retrieval system based on cognitive fingerprinting for large scale multimedia database

Speech-based human-robot interaction system (Robot Center)

2013/05/01 ~ 2014/04/30

Development of speech based human-robot interaction system in noisy and reverberant environment

Intelligent behavior pattern analysis for surveillance system (KT)

2013/08/01 ~ 2013/12/31

Development of complex video scene analysis algorithm for Intelligent surveillance system

Object Recognition for automatic tagging (KT)

2013/05/10 ~ 2013/12/31

Development of scene segmentation, object detection and recognition system for media intelligence

High-level image representation for visual recognition (LG)

2013/03/25 ~ 2013/11/25

Development of  multi-class object recognition system in natural scene for high-level image representation

Research for Robot Intelligence Technology (Ministry of Knowledge Economy)

2009/05/01~2013/04/30

Development of a speech based interface for human robot interaction.

21C Frontier Intelligent Robotics (Ministry of Knowledge Economy)

2009/06/01~2013/03/31

Development of the emotion expression interface of the robot by humming for human robot interaction.

P3 DigiCar: Smart Sensing Technique for Active Safety (NCRC, NRF)

2010/09/01~2013/02/28

Development of smart cognition technique for active safety.

De-noising algorithm for KOMPSAT-3 (Korea Aerospace Research Institute)

2011/04/01~2012/06/30

Development of denoising algorithm in KOMPSAT-3 image using frequency domain mask filter

Copyright Protection for Multimedia Data (Ministry of Culture, Sports and Tourism)

2009/03/01~2012/02/29

Development of fast retrieval system based on cognitive fingerprinting for large scale multimedia database.

Multimedia Retrieval, Analysis and Transmission System in Wireless Internet (NRF)

2007/09/01~2010/08/31

Development of the multimedia retrieval system in wireless internet environment and the video analysis & retrieval system using speech recognition and speaker verification.

Image contents annotation, search/retrieval system (KT)

2009/12/28~2010/06/25

Development of the image contents annotation, search and retrieval system.

Media analysis, summary, and management system (Pandora)

2009/06/01~2010/01/31

Developement of the melody transcription system

Underdetermined Blind Source Separation (ETRI)

2009/05/01~2010/01/31

Developement of blind source separation algorithm

Basic Research Program (Korea Research Foundation)

2008/07/15~2009/07/14

Development of feature extraction and indexing for content-based video identification

Content Based Audio Retrievel/Classification System (Pandora)

2008/07/15~2009/02/28

Developement of the query by humming system for audio identification

Speaker Recognition System (ETRI)

2008/09/01~2009/02/28

Development of Speaker Recognition in u-robot

21C Frontier Intelligent Robotics (The Ministry of Commerce, Industry and Energy)

2007/04/01~2009/03/31

Development of the speech & music based human emotion recognition system for intelligent robotics.

Real-time multiview video coding (ETRI)

2007/06/22~2007/11/30

Development of the real-time multiview video coding system.

Development of content-based music recommendation system (Pandora TV)

2007/06/15~2008/11/30

Development of the music recommendation system using the content-based similarity, genre, mood, and tempo.

Development of fingerprinting system supporting high speed search for large volume video/audio contents (Hanmaro)

2006/04/01~2006/11/15

Development of the system supporting real-time search for video/audio contents based on large volume fingerprint database. 

DSP implementation of MPEG-4 ER-BSAC (TI)

2005/12/01~2006/11/30

Development of real-time BSAC decoder on TI OMAP 2430. 

Research of future video coding(ETRI)

2006/06/01~2006/11/30

Acquriement of future video coding technique 

Recognition based on multimodal and integral processing method and 3-D audio Research (KOSEF)

2003/09/01~2006/08/31

Based on various techniques such as acoustic signal processing, auditory and visual information processing and multimodal information processing, the integrated system for recognition and 3D stereo sound is to be exploited that utilize the real-world services of man-machine interface.

Development of IT-based robot system for intelligent services (ITRC)

2003/08/01~2006/07/31

The goal of this project is to develop IT-based robot system that provides human being with various types of services any time and anywhere.

Audio and video fingerprinting systems for copyright protection (ETRI)

2005/05/20~2005/12/10

Development of audio and video fingerprinting systems for the protection of intellectual property, management of large database and indexation of content .

Multiple description coding (MDC) for audio/video codec (ETRI)

2005/11/01~2005/12/10

Development of multiple description coding (MDC) schemes for audio/video codec.

Development of acoustic echo cancellation algorithm (ETRI)

2004/06/23~2004/12/31

The goal of this project is to develop acoustic echo canceller that has good performance with low compexity for speech communication using a soft-phone of personal computer in a real environment.

Surveillance Real-Time MPEG4 Encoder for DVR

2004/06/01~2004/12/31

Development of fast audio codec for multichannel DVR system.

Audio fingerprinting system for copyright protection (ETRI)

2004/02/01~2004/12/03

Development of the multimedia retrieval system in wireless internet environment and the video analysis & retrieval system using speech recognition and speaker verification. 

Effecient Signal Processing Methods for Multimedia Communications (KOSEF)

2000/09/01~2003/08/31

Research the essential technology to improve the efficiency of the speech codec and speech rocognition system for multimedia communications

Tandemless transcoding algorithm for SMV and VoIP system (ETRI)

2002/04/12~2003/1/20

Develop the tandemless transcoding algorithm for SMV and VoIP system using the speech coding technology 

Development of remote speech recognition system (ETRI)

2002/01/21~2002/10/20

Build speech DB and develop the remote speech recognition system 

Voiced Speech Extraction and Recognition System (SAIT)

2001/03/01~2002/02/28

Research the technology to extract and recognize the voiced speech 

Speech Recognition System for Television Set (LG)

2000/11/01~2002/01/31

Development of speech recognition system to control TV set by voice command remotely 

Tandemless transcoding between AMR and EVRC (SAIT)

2001/02/12~2001/11/30

Research the algorithm for the tandemless transcoding between AMR and EVRC using the speech coding technology 

Echo Cancellation for Mobile Communication (LG)

2000/08/01~2001/07/31

Research the acoustic echo cancellation technology to improve the speech quality in mobile communication

Speech Recognition for Hurosot Robot (Hurosot)

2000/06/01~2001/06/31

Development of speech recognition system that is robust in the noisy environment of robot soccer field

Video Watermarking for HDVDP (LG)

2000/04/01~2001/03/31

Development of Video Watermarking algorithm to prevent the illegal copy in next generation HDVDP

DSP Implementation of Speech Coding (Dacom)

1999/12/01~2000/11/30

Implementation of speech codec on TeakLite DSP core