Presentation 2022-09-16
An image restoration method for lecture videos with projected lecture slides
Yuma Ito, Masato Kikuchi, Tadachika Ozono,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The lecturers can use their body movements and gestures in the lectures with slides displayed using a projector in the real world. However, recording these slides with a video camera has issues with the visibility of the slides. Our previous study improves the quality of the lecture slides in videos by overlapping the digital slides in the virtual space with the projected slides in the real space. In addition, we realized writing on the virtual slides with real stationery. However, there was room for improvement in the visibility of the handwritten content. The purpose of this paper is to restore the projected slides to the original slides to improve the image quality. We propose a method to improve the image quality by adjusting pixel values of projected slides based on white color. In evaluation experiment, out method verified an improvement in the image quality by comparing original projected slides with the restored slides.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Processing / Convolutional Neural Network / Lecture Video Making Support / High Resolution
Paper # AI2022-32
Date of Issue 2022-09-08 (AI)

Conference Information
Committee AI
Conference Date 2022/9/15(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yuichi Sei(Univ. of Electro-Comm.)
Vice Chair Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.)
Secretary Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.)
Assistant Kazutaka Matsuzaki(Chuo Univ.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An image restoration method for lecture videos with projected lecture slides
Sub Title (in English)
Keyword(1) Image Processing
Keyword(2) Convolutional Neural Network
Keyword(3) Lecture Video Making Support
Keyword(4) High Resolution
1st Author's Name Yuma Ito
1st Author's Affiliation Nagoya Institute of Technology(NIT)
2nd Author's Name Masato Kikuchi
2nd Author's Affiliation Nagoya Institute of Technology(NIT)
3rd Author's Name Tadachika Ozono
3rd Author's Affiliation Nagoya Institute of Technology(NIT)
Date 2022-09-16
Paper # AI2022-32
Volume (vol) vol.122
Number (no) AI-186
Page pp.pp.79-84(AI),
#Pages 6
Date of Issue 2022-09-08 (AI)