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
Proceedings of the 12th International Conference on Computer Systems and Technologies
Hi-index | 0.00 |
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.