Dale-Jones, Ralph (1993) Contrast enhancement using grey scale transformation techniques. PhD thesis, University of Warwick.

Preview

PDF WRAP_Theses_Dale-Jones_1993.pdf - Unspecified Version - Requires a PDF viewer. Download (10Mb) | Preview

Request Changes to record.

Abstract

The object of this thesis has been to examine grey scale transformation techniques in order to incorporate them into a system for automatically selecting a technique to enhance the contrast in a given image.

In order to include existing techniques in the system it was necessary to examine each in detail, and to understand under what conditions it gave good results. It was found that a number of techniques had only a limited scope or suffered from some problem in its design. This led to the development of a new technique based on the display capabilities of a monitor; the adaptation of another technique, globed histogram equalisation, to make it applicable to a wider range of images and the modification of the local histogram equalisation algorithm to smooth different sized regions of the image to the same degree.

The resultant algorithms, together with those existing in the literature, were included in the system. The system provides an interactive environment for selecting grey scale transformation techniques. The usual method of choosing a contrast enhancement technique is to apply it, look at the result, discard it if the result is not suitable, or if there is a parameter value to be set, modify its value, and try the technique again. Here a more systematic approach is tried using ideas from Knowledge Based Systems and Object Oriented Systems. A model of the way contrast enhancement techniques are selected is encoded into the system and is used with information obtained by analysing the image (either automatic analysis done by the system, or interactive analysis done with the aid of the user) to select the most appropriate techniques. The techniques selected by the system have to fulfil three quite demanding criteria, ensuring that the system is a reliable and useful tool.

Item Type:	Thesis or Dissertation (PhD)
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) T Technology > TR Photography
Library of Congress Subject Headings (LCSH):	Images, Photographic -- Data processing, Images processing, Image analysis
Official Date:	March 1993
Dates:	Date Event March 1993 Submitted
Institution:	University of Warwick
Theses Department:	Department of Engineering
Thesis Type:	PhD
Publication Status:	Unpublished
Supervisor(s)/Advisor:	Tjahjadi, Tardi
Extent:	xvi, 210 leaves
Language:	eng

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads