Optimisation of convolution-based image lightness processing

Rowlands, D. Andrew and Finlayson, Graham D. (2024) Optimisation of convolution-based image lightness processing. Journal of Imaging, 10 (8). ISSN 2313-433X

Preview

PDF (jimaging-10-00204-v2) - Published Version Available under License Creative Commons Attribution. Download (4MB) | Preview

Abstract

In the convolutional retinex approach to image lightness processing, an image is filtered by a centre/surround operator that is designed to mitigate the effects of shading (illumination gradients), which in turn compresses the dynamic range. Typically, the parameters that define the shape and extent of the filter are tuned to provide visually pleasing results, and a mapping function such as a logarithm is included for further image enhancement. In contrast, a statistical approach to convolutional retinex has recently been introduced, which is based upon known or estimated autocorrelation statistics of the image albedo and shading components. By introducing models for the autocorrelation matrices and solving a linear regression, the optimal filter is obtained in closed form. Unlike existing methods, the aim is simply to objectively mitigate shading, and so image enhancement components such as a logarithmic mapping function are not included. Here, the full mathematical details of the method are provided, along with implementation details. Significantly, it is shown that the shapes of the autocorrelation matrices directly impact the shape of the optimal filter. To investigate the performance of the method, we address the problem of shading removal from text documents. Further experiments on a challenging image dataset validate the method.

Item Type:	Article
Additional Information:	Data Availability Statement: The dataset used in this article is not readily available because copyrighted text documents were used. However, any set of text documents can be used to generate a filter. The numerical values of the particular filter used in Figure 10 and Figure 11 can be obtained from the authors upon request. Funding information: This work was funded by the University of East Anglia and EPSRC (UK) grant EP/S028730/1.
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Colour and Imaging Lab
Related URLs:	https://www.mdpi.com/2313-433X/10/8/204
Depositing User:	LivePure Connector
Date Deposited:	22 Nov 2024 11:30
Last Modified:	22 Nov 2024 11:30
URI:	https://ueaeprints.uea.ac.uk/id/eprint/97755
DOI:	10.3390/jimaging10080204

Downloads

Actions (login required)

View Item