Data driven approach to binarization of astronomical images

Authors:
Dimo Dimov;Aleksandar Dimov
Affiliations:
Institute of Information Technologies at Bulgarian Academy of Sciences (IIT-BAS);Sofia University "St. Kliment Ohridski"
Venue:
Proceedings of the 11th International Conference on Computer Systems and Technologies and Workshop for PhD Students in Computing on International Conference on Computer Systems and Technologies
Year:
2010

Citing 3
Cited 1

Distance transformations in digital images

Computer Vision, Graphics, and Image Processing
A Comparison of Binarization Methods for Historical Archive Documents

ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
A multi-scale framework for adaptive binarization of degraded document images

Pattern Recognition

Cumulative approach using Hough transform to segmentation of star chains in multi-exposures wide-field plate images

Proceedings of the 12th International Conference on Computer Systems and Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper considers the problem of astronomical images binarization. The problem arises with the idea for effective application of Hough transform to the identification of stars in chain plate images. The astronomical methods based on chain plates are rather old, but the plates processing is an important task because of the large number of archives (and therefore priceless from an astronomical viewpoint) of chain plates in Bulgaria, Europe and across the world. After a brief analysis of the state-of-the art, the paper proposes a locally adaptive binary-tree method for binarization of wide photo plate images, as a modification and extension of a similar one that is the authors' former development. Theoretical and experimental approaches of the proposal are also discussed in the paper.