{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T12:46:02Z","timestamp":1789217162732,"version":"build-2803163510"},"reference-count":27,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T00:00:00Z","timestamp":1696636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Spectricity and EPSRC","award":["EP\/S028730"],"award-info":[{"award-number":["EP\/S028730"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Colour correction is the process of converting RAW RGB pixel values of digital cameras to a standard colour space such as CIE XYZ. A range of regression methods including linear, polynomial and root-polynomial least-squares have been deployed. However, in recent years, various neural network (NN) models have also started to appear in the literature as an alternative to classical methods. In the first part of this paper, a leading neural network approach is compared and contrasted with regression methods. We find that, although the neural network model supports improved colour correction compared with simple least-squares regression, it performs less well than the more advanced root-polynomial regression. Moreover, the relative improvement afforded by NNs, compared to linear least-squares, is diminished when the regression methods are adapted to minimise a perceptual colour error. Problematically, unlike linear and root-polynomial regressions, the NN approach is tied to a fixed exposure (and when exposure changes, the afforded colour correction can be quite poor). We explore two solutions that make NNs more exposure-invariant. First, we use data augmentation to train the NN for a range of typical exposures and second, we propose a new NN architecture which, by construction, is exposure-invariant. Finally, we look into how the performance of these algorithms is influenced when models are trained and tested on different datasets. As expected, the performance of all methods drops when tested with completely different datasets. However, we noticed that the regression methods still outperform the NNs in terms of colour correction, even though the relative performance of the regression methods does change based on the train and test datasets.<\/jats:p>","DOI":"10.3390\/jimaging9100214","type":"journal-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T14:17:26Z","timestamp":1696688246000},"page":"214","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Performance Comparison of Classical Methods and Neural Networks for Colour Correction"],"prefix":"10.3390","volume":"9","author":[{"given":"Abdullah","family":"Kucuk","sequence":"first","affiliation":[{"name":"School of Computing Sciences, University of East Anglia, Norwich NR4 7TJ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4040-0554","authenticated-orcid":false,"given":"Graham D.","family":"Finlayson","sequence":"additional","affiliation":[{"name":"School of Computing Sciences, University of East Anglia, Norwich NR4 7TJ, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rafal","family":"Mantiuk","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8142-5611","authenticated-orcid":false,"given":"Maliha","family":"Ashraf","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"238","DOI":"10.2352\/CIC.1996.4.1.art00061","article-title":"Proposal for a Standard Default Color Space for The Internet\u2014sRGB","volume":"1","author":"Anderson","year":"1996","journal-title":"Color Imaging Conf."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Hunt, R.W.G., and Pointer, M.R. (2011). Measuring Colour, John Wiley & Sons. [4th ed.].","DOI":"10.1002\/9781119975595"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2359","DOI":"10.1364\/JOSAA.23.002359","article-title":"Frequency of Metamerism in Natural Scenes","volume":"23","author":"Foster","year":"2006","journal-title":"J. Opt. Soc. Am. A"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1117\/12.278080","article-title":"Constrained Least-Squares Regression in Color Spaces","volume":"6","author":"Finlayson","year":"1997","journal-title":"J. Electron. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.1109\/TIP.2015.2405336","article-title":"Color Correction Using Root-Polynomial Regression","volume":"24","author":"Finlayson","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1076","DOI":"10.1177\/0040517515569525","article-title":"Development of a Color Matching Algorithm for Digital Transfer Textile Printing Using an Artificial Neural Network and Multiple Regression","volume":"85","author":"Hwang","year":"2015","journal-title":"Text. Res. J."},{"key":"ref_7","unstructured":"Fdhal, N., Kyan, M., Androutsos, D., and Sharma, A. (2009). Advances in Multimedia Information Processing\u2014PCM 2009, Springer."},{"key":"ref_8","unstructured":"Adkins, D., Cherkassky, V.S., and Olson, E.S. (1993). London Imaging Meeting, Society for Imaging Science and Technology."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"107038","DOI":"10.1016\/j.patcog.2019.107038","article-title":"Underwater Scene Prior Inspired Deep Underwater Image and Video Enhancement","volume":"98","author":"Li","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vlachos, M., and Skarlatos, D. (2021). An Extensive Literature Review on Underwater Image Colour Correction. Sensors, 21.","DOI":"10.3390\/s21175690"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"115892","DOI":"10.1016\/j.image.2020.115892","article-title":"Underwater Image Enhancement with Global\u2013Local Networks and Compressed-Histogram Equalization","volume":"86","author":"Fu","year":"2020","journal-title":"Signal Process. Image Commun."},{"key":"ref_12","unstructured":"MacDonald, L., and Mayer, K. (2021). London Imaging Meeting, Society for Imaging Science and Technology."},{"key":"ref_13","unstructured":"Kucuk, A., Finlayson, G.D., Mantiuk, R., and Ashraf, M. (2022). London Imaging Meeting, Society for Imaging Science and Technology."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kucuk, A., Finlayson, G.D., Mantiuk, R., and Ashraf, M. (2022, January 13\u201317). An Exposure Invariant Neural Network for Colour Correction. Proceedings of the Colour and Imaging Conference (CIC30), Scottsdale, AZ, USA.","DOI":"10.2352\/CIC.2022.30.1.31"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1002\/1520-6378(200102)26:1<76::AID-COL8>3.0.CO;2-3","article-title":"A Study of Digital Camera Colorimetric Characterization Based on Polynomial Modeling","volume":"26","author":"Hong","year":"2001","journal-title":"Color Res. Appl."},{"key":"ref_16","unstructured":"Hordley, S., Finlayson, G.D., and Morovic, P. (2004, January 18\u201320). A Multi-Spectral Image Database and Its Application to Image Rendering Across Illumination. Proceedings of the Third International Conference on Image and Graphics (ICIG\u201904), Hongkong, China."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1002\/col.10049","article-title":"A Data Set for Colour Research","volume":"27","author":"Barnard","year":"2002","journal-title":"Color Res. Appl."},{"key":"ref_18","unstructured":"Horn, R.A., and Johnson, C.R. (1990). Matrix Analysis, Cambridge University Press."},{"key":"ref_19","unstructured":"Penrose, R. (1955). Mathematical Proceedings of the Cambridge Philosophical Society, Cambridge University Press."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/col.20070","article-title":"The CIEDE2000 Color-Difference Formula: Implementation Notes, Supplementary Test Data, and Mathematical Observations","volume":"30","author":"Sharma","year":"2005","journal-title":"Color Res. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1137\/S1052623496303470","article-title":"Convergence Properties of the Nelder-Mead Simplex Method in Low Dimensions","volume":"9","author":"Lagarias","year":"1998","journal-title":"SIAM J. Optim."},{"key":"ref_22","unstructured":"Boaz, A., and Ohad, B.S. (2016, January 11\u201314). Sparse Recovery of Hyperspectral Signal from Natural RGB Images. Proceedings of the Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands."},{"key":"ref_23","unstructured":"Yasume, F., Mitsunaga, T., Iso, D., and Nayar, S.K. (2008). Generalized Assorted Pixel Camera: Post-Capture Control of Resolution, Dynamic Range and Spectrum, Department of Computer Science, Columbia University. Technical Report."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1364\/JOSAA.32.000381","article-title":"Reference Data Set for Camera Spectral Sensitivity Estimation","volume":"32","author":"Darrodi","year":"2015","journal-title":"J. Opt. Soc. Am. A"},{"key":"ref_25","unstructured":"Noboru, O., and Robertson, A.R. (2005). Colorimetry, Wiley."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1080\/00031305.1998.10480559","article-title":"Violin Plots: A Box Plot-Density Trace Synergism","volume":"52","author":"Hintze","year":"1998","journal-title":"Am. Stat."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1364\/JOSAA.23.001008","article-title":"Re-evaluation of Color Constancy Algorithm Performance","volume":"23","author":"Hordley","year":"2006","journal-title":"J. Opt. Soc. Am. A"}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/9\/10\/214\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:02:32Z","timestamp":1760130152000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/9\/10\/214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,7]]},"references-count":27,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["jimaging9100214"],"URL":"https:\/\/doi.org\/10.3390\/jimaging9100214","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,7]]}}}