#2623. Intelligent restoration of historical parametric geometric patterns by zernike moments and neural networks

April 2027publication date
Proposal available till 30-05-2025
5 total number of authors per manuscript6020 $

The title of the journal is available only for the authors who have already paid for
Journal’s subject area:
Conservation;
Archeology (arts and humanities);
Economics, Econometrics and Finance (all);
Materials Science (miscellaneous);
Chemistry (miscellaneous);
Computer Science Applications;
Spectroscopy;
Places in the authors’ list:
place 1place 2place 3place 4place 5
FreeFreeFreeFreeFree
2230 $1120 $1000 $890 $780 $
Contract №2623.1 Contract №2623.2 Contract №2623.3 Contract №2623.4 Contract №2623.5
1 place - free (for sale)
2 place - free (for sale)
3 place - free (for sale)
4 place - free (for sale)
5 place - free (for sale)

Abstract:
The article proposes a new method for intelligent restoration of parametric geometric patterns, in which, having access to an image of existing patterns, one could spontaneously reconstruct the disappeared parts. The approach is based on image processing by detecting degradation boundaries, finding each individual element, and extracting the features of the detected individual patterns using Zernike moments. The order of individual patterns starts from the farthest pattern to the deterioration detected. Then, having created a time series, the backpropagation neural network will be trained on the extracted functions, and the functions of the disappeared patterns can be predicted and reconstructed.
Keywords:
Artificial intelligence; image processing; Islamic geometric patterns; Nasereddin Mirza mansion; restoration

Contacts :
0