Abstract
Binarization is often recognized to be one of the most important steps in most high-level image analysis systems, particularly for object recognition. However, from passed decades the most common way of arriving to a binarization of image was through a threshold, many times in a supervised way. In this work, a new algorithm is introduced for the no-supervised binarization, where the step of the parametric logarithm is of vital importance.
Original language | English |
---|---|
Article number | 7459631 |
Pages (from-to) | 1434-1439 |
Number of pages | 6 |
Journal | IEEE Latin America Transactions |
Volume | 14 |
Issue number | 3 |
DOIs | |
State | Published - Mar 2016 |
Keywords
- Binarization
- Image segmentation
- Parametric Logarithm
- Threshold