Presentation 2022-01-27
Introduction of auto-associative memory model to zero-watermarking method using hetero-associative memory model
Ryoto Kanegae, Masaki Kawamura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a method that introduces an auto-associative memory model to Shimana and Kawamura's method that utilizes a hetero-associative memory model to perform the zero-watermarking method. The zero-watermarking method is a watermarking method that preserves the original image by not embedding the watermark into the image. Since one image is associated with one watermark, it becomes difficult to manage the correspondence when handling a large number of images. Shimana and Kawamura's method is able to manage a large number of correspondences by using a hetero-associative memory model. However, when images are heavily attacked, the features of the images are also degraded. Therefore, the hetero-associative memory model cannot be correctly retrieved them. In this research, we propose a method that introduces an auto-associative memory model. Hence, even if the watermark cannot be correctly recalled by the hetero-associative memory model, the error can be successfully corrected by the auto-associative memory model. The proposed method was evaluated for the cases of JPEG compression and additive white Gaussian noise. As a result, the proposed method was able to reduce the errors of the watermark more effectively than the conventional method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Zero-Watermarking / auto-associative memory model / hetero-associative memory model
Paper # EMM2021-86
Date of Issue 2022-01-20 (EMM)

Conference Information
Committee EMM
Conference Date 2022/1/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Sense of Presence, Universal Media, Digital Entertainment, etc.
Chair Ryoichi Nishimura(NICT)
Vice Chair Masaaki Fujiyoshi(Tokyo Metropolitan Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.)
Secretary Masaaki Fujiyoshi(Utsunomiya Univ.) / Masatsugu Ichino(NICT)
Assistant Shoko Imaizumi(Chiba Univ.) / Youichi Takashima(Kaishi Professional Univ.)

Paper Information
Registration To Technical Committee on Enriched MultiMedia
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Introduction of auto-associative memory model to zero-watermarking method using hetero-associative memory model
Sub Title (in English)
Keyword(1) Zero-Watermarking
Keyword(2) auto-associative memory model
Keyword(3) hetero-associative memory model
1st Author's Name Ryoto Kanegae
1st Author's Affiliation Yamaguchi University(Yamaguchi Univ)
2nd Author's Name Masaki Kawamura
2nd Author's Affiliation Yamaguchi University(Yamaguchi Univ)
Date 2022-01-27
Paper # EMM2021-86
Volume (vol) vol.121
Number (no) EMM-362
Page pp.pp.13-18(EMM),
#Pages 6
Date of Issue 2022-01-20 (EMM)