Soft Thresholding for Visual Image Enhancement
This work addresses the issue of reduced readability in document images for human viewers, particularly in online facsimile repositories, but is incremental as it builds on existing fuzzy thresholding concepts.
The paper tackles the problem of thresholding negatively affecting document image legibility by introducing a method to 'smear out' the threshold, transforming greyscale images into enhanced greyscale versions. It presents a simple formula for automatically determining the threshold spread width, aimed at improving visual presentation in online repositories.
Thresholding converts a greyscale image into a binary image, and is thus often a necessary segmentation step in image processing. For a human viewer however, thresholding usually has a negative impact on the legibility of document images. This report describes a simple method for "smearing out" the threshold and transforming the greyscale image into a different greyscale image. The method is similar to fuzzy thresholding, but is discussed here in the simpler context of greyscale transformations and, unlike fuzzy thresholding, it is independent from the method for finding the threshold. A simple formula is presented for automatically determining the width of the threshold spread. The method can be used, e.g., for enhancing images for the presentation in online facsimile repositories.