Modelling of ink-colour degradation on old printed documents
by Biswajit Halder; Abhoy Chand Mondal
International Journal of Computational Vision and Robotics (IJCVR), Vol. 7, No. 4, 2017

Abstract: Determination of ink age in documents is crucial for many applications including the forensic ones. The degradation in ink-colour has an important role for this purpose. This paper attempts to model the degradation of ink-colour in documents. Such a model is not only helpful for determination of ink age and it gives a better insight about how colour of a document changes over time. The mathematical foundation for the proposed model is borrowed from an optimisation technique called ant colony optimisation. From a set of 200 documents distributed over five decades (30s to 70s decades) the model, under certain assumptions, tries to find an optimised path through which the majority of documents starting at 30s pass through intermediate decades to reach at 70s. Estimation of the model parameters and use of this model for: 1) determination of ink age; 2) prediction of a document's condition after certain years are discussed in details. Two types of digitised old magazines cover pages are considered for our experiment. The first one is used for construct the model and the second one is used for verification.

Online publication date: Mon, 10-Jul-2017

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Vision and Robotics (IJCVR):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com