Back to articles
Volume: 32 | Article ID: art00005
A Deep Learning-Based Approach for Defect Detection and Removing on Archival Photos
  DOI :  10.2352/ISSN.2470-1173.2020.10.IPAS-029  Published OnlineJanuary 2020

Many archival photos are unique, existed only in a single copy. Some of them are damaged due to improper archiving (e.g. affected by direct sunlight, humidity, insects, etc.) or have physical damage resulting in the appearance of cracks, scratches on photographs, non-necessary signs, spots, dust, and so on. This paper proposed a system for detection and removing image defects based on machine learning. The method for detecting damage to an image consists of two main steps: the first step is to use morphological filtering as a pre-processing, the second step is to use the machine learning method, which is necessary to classify pixels that have received a massive response in the preprocessing phase. The second part of the proposed method is based on the use of the adversarial convolutional neural network for the reconstruction of damages detected at the previous stage. The effectiveness of the proposed method in comparison with traditional methods of defects detection and removal was confirmed experimentally.

Subject Areas :
Views 31
Downloads 6
 articleview.views 31
 articleview.downloads 6
  Cite this article 

R. Sizyakin, V. Voronin, N. Gapon, A. Zelensky, A. Pižurica, "A Deep Learning-Based Approach for Defect Detection and Removing on Archival Photosin Proc. IS&T Int’l. Symp. on Electronic Imaging: Image Processing: Algorithms and Systems XVIII,  2020,  pp 29-1 - 29-7,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA