Nearest Neighbor based Digital Restoration of Damaged Ancient Chinese Paintings

Zeng Y(曾媛); Yi Gong

10.1109/icdsp.2018.8631553

2018

1546-1874

978-1-5386-6812-2

IEEE 23rd International Conference on Digital Signal Processing (DSP)

2018-November

1-5

19-21 Nov. 2018

Shanghai, China

中国

345 E 47TH ST, NEW YORK, NY 10017 USA

Institute of Electrical and Electronics Engineers Inc.

Most ancient artworks have structure damage problems, such as tears, flakes and cracks. This work gives an initial study of digital restoration of damaged ancient Chinese paintings via nearest neighboring method, which is an effective non-parameter machine learning algorithm. We first present a damage detection method to estimate the mask, and then a patch based image inpainting algorithm is performed to reconstruct the damaged paintings. Our experiments illustrate the restoration performance of the proposed method by using ancient Chinese paintings. Moreover, we also provide discussion on the future research topics about automatic damage detection and image inpainting via deep learning algorithms.
© 2018 IEEE.

Damage detection digital restoration nearest neighboring algorithm ancient Chinese paintings

第一

英语

CPCI-S ; EI

Engineering

Engineering, Electrical & Electronic

WOS:000458909600015

20191106629324

Damage detection ; Deep learning ; Historic preservation ; Image processing ; Learning algorithms ; Machine learning ; Restoration

Ergonomics and Human Factors Engineering:461.4 ; Data Processing and Image Processing:723.2 ; Machine Learning:723.4.2 ; Coating Techniques:813.1

Web of Science

Southern University of Science and Technology

Zeng Y,Yi Gong. Nearest Neighbor based Digital Restoration of Damaged Ancient Chinese Paintings[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:Institute of Electrical and Electronics Engineers Inc.,2018:1-5.