Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System

Computational color constancy (CCC) is a fundamental prerequisite for many computer vision tasks. The key of CCC is to estimate illuminant color so that the image of a scene under varying illumination can be normalized to an image under the canonical illumination. As a type of solution, combination...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yunhui Luo, Xingguang Wang, Qing Wang, Yehong Chen
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	color constancy illumination estimation adaptive neuro-network fuzzy inference system (ANFIS) clustering image enhancement Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/9880f6f9579d44e2b1d5190e441542fd
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9880f6f9579d44e2b1d5190e441542fd
record_format	dspace
spelling	oai:doaj.org-article:9880f6f9579d44e2b1d5190e441542fd2021-11-11T15:01:59ZIlluminant Estimation Using Adaptive Neuro-Fuzzy Inference System10.3390/app112199362076-3417https://doaj.org/article/9880f6f9579d44e2b1d5190e441542fd2021-10-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/21/9936https://doaj.org/toc/2076-3417Computational color constancy (CCC) is a fundamental prerequisite for many computer vision tasks. The key of CCC is to estimate illuminant color so that the image of a scene under varying illumination can be normalized to an image under the canonical illumination. As a type of solution, combination algorithms generally try to reach better illuminant estimation by weighting other unitary algorithms for a given image. However, due to the diversity of image features, applying the same weighting combination strategy to different images might result in unsound illuminant estimation. To address this problem, this study provides an effective option. A two-step strategy is first employed to cluster the training images, then for each cluster, ANFIS (adaptive neuro-network fuzzy inference system) models are effectively trained to map image features to illuminant color. While giving a test image, the fuzzy weights measuring what degrees the image belonging to each cluster are calculated, thus a reliable illuminant estimation will be obtained by weighting all ANFIS predictions. The proposed method allows illuminant estimation to be dynamic combinations of initial illumination estimates from some unitary algorithms, relying on the powerful learning and reasoning capabilities of ANFIS. Extensive experiments on typical benchmark datasets demonstrate the effectiveness of the proposed approach. In addition, although there is an initial observation that some learning-based methods outperform even the most carefully designed and tested combinations of statistical and fuzzy inference systems, the proposed method is good practice for illuminant estimation considering fuzzy inference eases to implement in imaging signal processors with if-then rules and low computation efforts.Yunhui LuoXingguang WangQing WangYehong ChenMDPI AGarticlecolor constancyillumination estimationadaptive neuro-network fuzzy inference system (ANFIS)clusteringimage enhancementTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 9936, p 9936 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	color constancy illumination estimation adaptive neuro-network fuzzy inference system (ANFIS) clustering image enhancement Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	color constancy illumination estimation adaptive neuro-network fuzzy inference system (ANFIS) clustering image enhancement Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Yunhui Luo Xingguang Wang Qing Wang Yehong Chen Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System
description	Computational color constancy (CCC) is a fundamental prerequisite for many computer vision tasks. The key of CCC is to estimate illuminant color so that the image of a scene under varying illumination can be normalized to an image under the canonical illumination. As a type of solution, combination algorithms generally try to reach better illuminant estimation by weighting other unitary algorithms for a given image. However, due to the diversity of image features, applying the same weighting combination strategy to different images might result in unsound illuminant estimation. To address this problem, this study provides an effective option. A two-step strategy is first employed to cluster the training images, then for each cluster, ANFIS (adaptive neuro-network fuzzy inference system) models are effectively trained to map image features to illuminant color. While giving a test image, the fuzzy weights measuring what degrees the image belonging to each cluster are calculated, thus a reliable illuminant estimation will be obtained by weighting all ANFIS predictions. The proposed method allows illuminant estimation to be dynamic combinations of initial illumination estimates from some unitary algorithms, relying on the powerful learning and reasoning capabilities of ANFIS. Extensive experiments on typical benchmark datasets demonstrate the effectiveness of the proposed approach. In addition, although there is an initial observation that some learning-based methods outperform even the most carefully designed and tested combinations of statistical and fuzzy inference systems, the proposed method is good practice for illuminant estimation considering fuzzy inference eases to implement in imaging signal processors with if-then rules and low computation efforts.
format	article
author	Yunhui Luo Xingguang Wang Qing Wang Yehong Chen
author_facet	Yunhui Luo Xingguang Wang Qing Wang Yehong Chen
author_sort	Yunhui Luo
title	Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System
title_short	Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System
title_full	Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System
title_fullStr	Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System
title_full_unstemmed	Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System
title_sort	illuminant estimation using adaptive neuro-fuzzy inference system
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/9880f6f9579d44e2b1d5190e441542fd
work_keys_str_mv	AT yunhuiluo illuminantestimationusingadaptiveneurofuzzyinferencesystem AT xingguangwang illuminantestimationusingadaptiveneurofuzzyinferencesystem AT qingwang illuminantestimationusingadaptiveneurofuzzyinferencesystem AT yehongchen illuminantestimationusingadaptiveneurofuzzyinferencesystem
_version_	1718437622662037504

Illuminant Estimation Using Adaptive Neuro-Fuzzy Inference System

Ejemplares similares