본문 바로가기 대메뉴 바로가기

한밭대학교컴퓨터공학과

HIGHHANBAT

AIM

Artificial Intelligence Media (AIM) Lab
AIM

About the Lab

  • The Artificial Intelligence Media Lab (AIM Lab) researches technologies that use AI to deal with media data
  • Media data refers to data from digital media in various forms, such as images, video, audio, 3D models, and more
  • Students are encouraged to participate in data science competitions such as Kaggle, DACON, etc. (research guidance, research environment support)
  • The lab is working on AI-based media data processing technologies with various companies and research institutes such as NAVER and ETRI.

Advisor: Han-Eol Jang

Thesis

  • Local-Source Enhanced Residual Network for Steganalysis of Digital Images,
    IEEE Access, July 2020
  • Feature Aggregation Networks for Image Steganalysis, ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec '20), June 2020
  • Exposing Digital Image Forgeries by Detecting Contextual Abnormality Using Convolutional Neural Networks, Sensors, April 2020
  • Finding robust domain from attacks: A learning framework for blind watermarking, Neurocomputing, April 2019
  • Robust Template-Based Watermarking for DIBR 3D Images, Applied Sciences, June 2018
  • Cropping-resilient 3D mesh watermarking based on consistent segmentation and mesh steganalysis, Multimedia Tools and Applications, March 2018
  • Median Filtered Image Restoration and Anti-Forensics Using Adversarial Networks, IEEE Signal Processing Letters, February 2018
  • DeepPore: Fingerprint Pore Extraction Using Deep Convolutional Neural Networks, IEEE Signal Processing Letters, December 2017
  • Blind 3D mesh watermarking based on cropping-resilient synchronization, Multimedia Tools and Applications, December 2017

Patents

  • Three-dimensional mesh model watermarking method using segmentation and apparatus thereof, US Patent 10,769,745
  • Watermark embedding apparatus and method, and watermark detecting apparatus and method for 3D printing environment, US Patent10,438,311
  • Template-based watermarking method for depth-image-based rendering based 3D image and apparatus thereof, US Patent 10,049,422