Contour Detection Using Contrast Formulas in the Framework of Logarithmic Models
This work addresses edge detection in image processing, but it appears incremental as it builds on existing logarithmic models.
The authors tackled edge detection by applying a new logarithmic image representation model to compute pixel contrast, resulting in a contour image that maintains value ranges and performs well across both high and low luminosity regions, with comparisons to classical edge detection operators.
In this paper we use a new logarithmic model of image representation, developed in [1,2], for edge detection. In fact, in the framework of the new model we obtain the formulas for computing the "contrast of a pixel" and the "contrast" image is just the "contour" or edge image. In our setting the range of values is preserved and the quality of the contour is good for high as well as for low luminosity regions. We present the comparison of our results with the results using classical edge detection operators.