Archives: AI in Signal division

M.S student Ki-Hyun Kim (Advised by Yong-Man Ro)’s paper awarded the Best Paper Award – Silver Prize at ICCE-Asia 2018 in Jeju Island. ICCE-Asia is an international conference related to consumer electronics. This paper was selected as the Best Paper Award – Silver Prize. The title of the paper is “FSF-C Net: Face Spatial Frequency-Critical Network for Face Super Resolution”.

 

Congratulations to Ki-hyun Kim and Professor Yong-Man Ro.

 

Conference: ICCE-Asia 2018

Date: 2018.06.24 – 2018.06.26

Award: ICCE-Asia 2018, Best Paper Award – Silver Prize

Venue: Ramada Plaza Hotel, Jeju, Korea

Paper: FSF-C Net: Face Spatial Frequency-Critic Network for Face Super Resolution

Author: Ki-hyun Kim, Hak-Gu Kim, and Yong-Man Ro

Professor Dong-Eui Chang of our department has published a book on deep learning titled “Deep Neural Networks in a Mathematical Framework” with Anthony L. Caterni of Oxford University. (Springer; 2018) Detailed information about the book is on below. You can download eBooks through the link https://doi.org/10.1007/978-3-319-75304-1, and bound books are available in online/offline bookstores.

Title: Deep Neural Networks in a Mathematical Framework

Authors: Anthony L. Caterini and Dong Eui Chang

Publisher: Springer; 2018

ISBN 978-3-319-75303-4

ISBN 978-3-319-75304-1 (eBook)

https://doi.org/10.1007/978-3-319-75304-1

Book cover and Front Matter: in attachment

 

Summary:

This book describes how to build a rigorous end-to-end mathematical framework for deep neural networks. The authors provide tools to represent and describe neural networks, casting previous results in the field in a more natural light. In particular, the authors derive gradient descent algorithms in a unified way for several neural network structures, including multilayer perceptrons, convolutional neural networks, deep autoencoders and recurrent neural networks. Furthermore, the authors developed framework is both more concise and mathematically intuitive than previous representations of neural networks.

This book is one-step towards unlocking the black box of Deep Learning. The authors believe that this framework will help catalyze further discoveries regarding the mathematical properties of neural networks. This book is accessible not only to researchers, professionals and students working and studying in the field of deep learning, but also to those outside of the neutral network community.

Graduate of Professor Jong-Hwan Kim’s research group, Dr. Won-Hyung Lee awarded the Best Video Award at HRI 2018 Society hosted by ACM / IEEE in Chicago, USA. (3/5 ~ 3/8)

The paper is the result of the research that was made during his undergraduate course. The related video link is in the below.

<Video Link>

Free Talking: https://youtu.be/OltXzOc-zAw

Photo Shooting Scenario: https://youtu.be/BXpeLyxHst0

User Face Identification and Differentiated Reactions: https://youtu.be/LIe1yN_DjDk

 

<Social Relationship Development Between Human and Robot Through Real-Time Face Identification and Emotional Interaction>

Paper of Ph.D. student Seong-Tae Kim, Hak-min Lee, Hak-Gu Kim (Advised by Yong-Man Ro) awarded theRobert F. Wagner All-Conference Best Student Paper Award Finalist (Field of Computer-Aided Diagnosis Conference).

The SPIE Medical Imaging Conference is one of the world’s largest conferences on medical imaging. The title of the selected paper is “ICADx: Interpretable computer aided diagnosis of breast masses” as a result of “Interpretable Deep Learning” study.

 

Conference: SPIE Medical Imaging (http://spie.org/conferences-and-exhibitions/medical-imaging&nbsp;)

Date: 2018.02.10 – 2018.02.15

Award: Robert F. Wagner All-Conference Best Student Paper Award Finalist (First place in Computer-Aided Diagnosis Conference)

Place: Marriott Marquis Houston, Houston, Texas, United States

Title of the paper: ICADx: interpretable computer aided diagnosis of breast masses

Authors: Seong-Tae Kim, Hak-Min Lee, Hak-Gu Kim and Yong-Man Ro

 

M.S student Sung-Jun Yoon and Ph.D. student Yong-Woo Kim (Advised by Mun-Churl Kim) awarded the Gold Prize (Selected 2 first prize out of 280 published papers) at the “Workshop on Image Processing and Image Understanding (IPIU 2018)” conference held once a year as an academic event in the field of computer vision and image processing.

-Name of the Academic Event: Workshop on Image Processing and Image Understanding (IPIU 2018)

-Event Period: February 7th (Wed), 2018 – February 9th (Fri), 2018

-Place of Event: Maison Glad Jeju Hotel

-Title of Paper: A study on frame rate improvement using hierarchical convolution neural network

-Authors: Sung-Jun Yoon, Yong-Woo Kim, Mun-Churl Kim

Introduction:

In this paper, we propose a frame rate enhancement method using hierarchical convolution neural network. The convolutional neural network is constructed hierarchically, and the convolution operation is performed at the optimal position adaptively, so that the performance is robust against the interpolation of the fast moving object.

As a result, compared with the existing ICCV 2017 “Video Frame Interpolation via Adaptive Separable Convolution” algorithm, the improvement was 0.41dB in terms of peak signal-to-noise ratio (PSNR)

Professor Mun-churl Kim of our department developed a technology that can convert full HD video into super-high definition 4K UHD video using deep learning technology.

This technology has been implemented in hardware by Deep Convolution Neural Network (DNCC), which is a key technology in artificial intelligence. It is expected to contribute premium UHD TV, 360 VR, and 4K IPTV in the future by developing algorithms and hardware that can create ultra high resolution 4K UHD screen in 60 frames per second in real time.

This study was lead by Yong-woo Kim and Jae-Seok Choi Ph.D. students and they are preparing for patent application.

In recent years, efforts have been made to apply Deep Convolutional Neural Network (DNCC) on image quality improvement research. However, Deep Convolutional Neural Network (DNCC) technology has a high computational complexity, and there is a limit to real-time conversion to ultrahigh-resolution images through small hardware because it needs large memory.

In the conventional frame-by-frame image processing method, it is necessary to use external memory such as DRAM, which causes memory bottleneck and power consumption due to excessive external memory access when processing image data.

Professor Mun-churl Kim’s research group developed an efficient Deep Convolution Neural Network structure that can process data in units of lines instead of frames to implement 4K UHD super resolution at 60 frames per second on small hardware without using external memory.

His research group maintained a similar picture quality with only 65% of the filter parameters compared to the fast algorithm based on deep convolution neural networks and software.

This is the first example to implement 60 frames per second 4K UHD super resolution by using hardware.

Professor Kim said, “This research is a very important example of the Deep Convolutional Neural Network that is practically applicable to ultra-high-quality image processing in small hardware. Currently, it can be applied to premium UHD TV and UHD broadcast contents, 360 VR contents, 4K IPTV services.”  

This research was carried out with the support from the Institute for Information & communications Technology Promotion

The research paper carried out by our department professor Hyun-Wook Park’s laboratory was published as a front cover paper on December 13th in Medical Physics.

The subject of this paper is ‘Restoration method based on artificial neural network for shortening MRI image acquisition time’

The authors are Ki-Nam Kwon (1st author), Dr. Dong-Chan Kim (2nd author, Professor of Gachon Univ.), and Professor Hyun-Wook Park (correspondent author).

Journal: Medical Physics

Title of the Paper: A Parallel MR Imaging Method Using Multilayer Perceptron

Authors: Ki-Nam Kwon (1st Author), Dr. Dong-Chan Kim (2nd author, Professor of Gachon Univ), Professor Hyun-Wook Park (correspondent author)

Link of the Paper: http://onlinelibrary.wiley.com/doi/10.1002/mp.12600/full

Professor Chang-Ik Kim’s research group(Hyun-jun Eun, Jong-Hee Kim, Jin-Soo Kim) awarded the 1st prize at the 2017 Samsung Fire & Marine Machine Learning Challenge for graduate students.

This competition is a contest that compares recognition accuracy and speed by developing a model to detect and recognize Hangul on road signs. The 1st Prize was awarded to the KAIST CIL team, which achieved the highest accuracy and fastest speed among the 60 participating teams. The 2nd Prize and the 3rd Prize were awarded to Korea University and Seoul National University.

Task: Each participant / team must develop and submit a model for recognizing and extracting Hangul in images using the learning data provided for this project. The organizer will evaluate the recognition rate and speed of the submitted model for 10,000 unlisted test data.

Qualification: Graduate student (Korean nationals or overseas Koreans who are in master’s / Ph.D programs at Korean universities.)

Date: 2017.05.12~2017.11.09

Host: Samsung Fire & Marine Insurance

Operation: Samsung Fire & Marine Insurance Internet U & A Center – Analytics Lab

Award: 1st prize (10million won)

<Link>

http://alab.samsungfire.com/contest02.html

 

MS student Sang-Hyun Cho(Advisored by Jong-Hwan Kim, Dr. Won-Hyong Lee awarded the Best Student Paper Award from IEE Int’l Conf. on Systems, Man, and Cybernetics (SMC) held on 10/5~10/8 at Banff, Canada.

The title of the awarded paper is “Implementation of Human-Robot VQA Interaction System With Dynamic Memory Networks”

Congratulations!

Professor Su-Young Lee’s authentication system based on human orientation was broadcast on KBS News last Monday.

This system is based on the natural movements of the pupil, and have unique features as an authentication method

that it can not be stolen or duplicated in ever-increasing financial transactions. This research is published in

Nature Scientific Reports

<Related Links>

• 8/14 KBS1, KBS : http://news.kbs.co.kr/news/view.do?ncd=3533117 /  http://news.kbs.co.kr/news/view.do?ncd=3533086 
• Scientific Reports Papaer: http://www.nature.com/articles/s41598-017-07641-7