A MDV - Based approach for appearance enhancement of historical images

Mohammad Alfraheed, Ahmed Alamouri and Sabina Jeschke ()
Additional contact information
Sabina Jeschke: RWTH Aachen University, IMA/ZLW

A chapter in Automation, Communication and Cybernetics in Science and Engineering 2011/2012, 2013, pp 545-557 from Springer

Abstract: Abstract The approach based on the Mahalanobis Distance Value (MDV) is introduced for appearance enhancement of objects included in images; and especially for study cases dealing with historical images. In those cases, this approach allows an automatically reducing of the noise pixels and distortion parameters associated with an image. First of all, an image is divided into Seed Regions (SRs) based on watershed transformation. Each SR created is divided into non-overlapping subregions based on the Intensity Values (IVs) associated with (MDV). Subregions which have the same MDV and different intensity values have to be separated. Therefore, the subregion with the minimum MDV is considered as Reference Partition (RP) used for the separation process. IVs of a final generated subregion are replaced by the IV which has the largest frequency associated with. As a result, each subregion takes a new color which is relatively close to its original color but more clear and low gradient. The performance of the MDV-based approach is expressed through a comparison to other approaches used for appearance enhancement of images (like: Gaussian filter).

Keywords: Noise Intensity; Seed Region; Aerial Image; Regional Minimum; Catchment Basin (search for similar items in EconPapers)
Date: 2013
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-642-33389-7_43

Ordering information: This item can be ordered from
http://www.springer.com/9783642333897

DOI: 10.1007/978-3-642-33389-7_43

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().