Notice

Recent Result for Deep Learning based Image Processing in IVY Lab

[Link]

Automatically masking face for privacy protection first and Recognizing enrolled face later

https://youtu.be/bNQnGWroobk

The paper "Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos" has been accepted to Pattern Recognition. This paper was written by Seung Ho Lee, Wissam J. Baddar, and Yong Man Ro.

Postdoc position is available in IVY lab: Link

The paper "Binocular symmetric hole filling with spatio-temporal consistency using global optimization for synthesized 3D video " has been accepted to IEEE Transactions on Circuits and Systems for Video Technology. This paper was written by Hak Gu Kim and Yong Man Ro.

https://youtu.be/0wp9GIWx28s

https://youtu.be/TwcLSpBG4-o

Yeoreum Choi, a master's in IVY lab under the supervision of Prof. Yong Man Ro, received the best paper award of the Korean Multimedia Society conference which was held in Nov. 2015. The title of the paper is " Local Feature Learning using Deep Canonical Correlation Analysis for NIR-VIS Heterogeneous Face Recognition"

Three papers written by first authors of Hak Gu Kim, Yeoreum Choi, Heountaek Limhave been accepted to IS&T International Symposium on Electronic Imaging 2016. The three papers are 'A new hole filling method based on 3D geometric transformation for synthesized image', 'Two-step Learning of Deep Convolutional Neural Network for Discriminative Face Recognition under Varying Illumination' and 'Learning based hole filling method using deep convolutional neural networks for view synthesis', respectively.

The paper "Detection of masses in digital breast tomosynthesis using complementary information of simulated projection" has been accepted to Medical Physics. This paper was written by Seong Tae Kim, Dae Hoe Kim, and Yong Man Ro.

The paper "Classifier Ensemble Generation and Selection with Multiple Feature Representations for Classification Applications in Computer-Aided Detection and Diagnosis on Mammography" has been accepted to Expert Systems With Applications. This paper was written by Jae Young Choi, Dae Hoe Kim, Konstantinos N Plataniotis, and Yong Man Ro.

The paper "Partial Matching of Facial Expression Sequence Using Over-complete Transition Dictionary for Emotion Recognition" has been accepted to IEEE Transactions on Affective Computing. This paper was written by Seung Ho Lee, and Yong Man Ro.

Dae Hoe Kim, a Ph.D. student in IVY Lab. under the supervision of Prof. Yong Man Ro, have received Top 10% paper award at IEEE International Conference on Image Processing (ICIP) 2015 that was held between the 27-30 of September 2015 in Quebec city, Canada. The title of his paper is "Feature extraction from bilateral dissimilarity in DBT reconstructed volume".

The paper "Improving mass detection using combined feature representations from projection views and reconstructed volume of DBT and boosting based classification with feature selection" has been accepted to Physics in Medicine and Biology. This paper was written by Dae Hoe Kim, Seong Tae Kim, and Yong Man Ro.

The paper written by IVY member of Hyoung-Il Kim (with a graduate Seo) has been accepted to IEEE ISM 2015. The paper is entitled by “Multi-task Deep Learning for Multi-view Face Recognition". He will also present his paper in IEEE International Ph.D. Workshop on Multimedia Computing Research, which is entitled by "Multispectral Texture Features from Visible and Near-infrared Synthetic Face Images for Face Recognition"

Hak Gu Kim, a Ph.D. student in IVY Lab. under the supervision of Prof. Yong Man Ro, have received an Best student paper award award at Pacific-Rim Conference on Multimedia (PCM) 2015 that was held between the 16-18 of September 2015. The title of his award winnig paper is "A sparse representation-based label pruning for image inpainting using global optimization".

2016년도 전기 국비장학생 박사과정 1명, 국비석사과정 2명, 산학장학생 (KEPSI, EPSS, LGenius) 등을 모집합니다 (http://admission.kaist.ac.kr/graduate/ )

모집 연구분야: Image processing (2D, 3D), Computer vision, Medical imaging, Visual recognition (visual data machine learning), Video representation/compression

현재 진행중인 연구과제: Deep feature analysis for visual recognition, High performance face/human recognition, Emotion recognition, 3D view rendering/processing, Computer aided diagnosis, Medical Image processing, Automatic object detection/recognition, High efficient visual recognition.

최근 연구실 연구결과 (Link) 및 연구실 연구원 생활 (Link)을 참고하세요.

연구실 들어오고자 하는 학생은 노용만 교수님(ymro@kaist.ac.kr) 께 이메일/면담 하기 바랍니다.

The paper "Image-based coin recognition using rotation-invariant region binary patterns based on gradient magnitudes" has been accepted to Journal of Visual Communication and Image Representation. This paper was written by Semin Kim, Seung Ho Lee, and Young Man Ro.

Automatic Privacy Protection in Surveillance (Face Masking) and Real application to ATM surveillance

https://youtu.be/OtZL5MiraeE