A segmentation and mixing strategy for retinex based image enhancement

Chun Yi Sung, Shih Yu Liu, Yan Min Chen, Chin-Hsing Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Based on the human visual system, the Retinex image enhancement algorithm offers a forceful improvement for nonuniformly illuminated images. By observing that the original nonuniformly illuminated image has good performance in the bright area and the Retinex improved image has outstanding performance in the dark area, algorithms aiming to integrate the merits from both images were proposed. In this paper, we proposed an algorithm which performs the wavelet transform (WT) before segmentation and mixing. The wavelet transform decomposes an image into the coarse component and the detail components. The segmentation is performed on the course component and the result is used to fuse the course and detail components from both sources. The proposed algorithm is first subjectively assessed by using the dynamic range independent image quality assessment metric (DRIM) and compared with three existing algorithms. Experimental results show that the improved images using our proposed algorithm reveal significant amplification of contrast in the dark areas and mild loss and reversal of contrast in other areas. The proposed algorithm is objectively assessed by using information entropy. Experimental results show that among the four methods compared the information entropy of our proposed algorithm is the highest.

Original languageEnglish
Title of host publicationProceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages46-49
Number of pages4
ISBN (Electronic)9781538670361
DOIs
Publication statusPublished - 2019 Feb 19
Event4th International Symposium on Computer, Consumer and Control, IS3C 2018 - Taichung, Taiwan
Duration: 2018 Dec 62018 Dec 8

Publication series

NameProceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

Conference

Conference4th International Symposium on Computer, Consumer and Control, IS3C 2018
CountryTaiwan
CityTaichung
Period18-12-0618-12-08

Fingerprint

Image Enhancement
Image enhancement
Segmentation
Information Entropy
Wavelet transforms
Wavelet Transform
Entropy
Image Quality Assessment
Human Visual System
Strategy
Experimental Results
Electric fuses
Dynamic Range
Reversal
Amplification
Image quality
Integrate
Decompose
Metric

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Control and Systems Engineering
  • Energy Engineering and Power Technology
  • Computer Science Applications
  • Control and Optimization
  • Signal Processing

Cite this

Sung, C. Y., Liu, S. Y., Chen, Y. M., & Chen, C-H. (2019). A segmentation and mixing strategy for retinex based image enhancement. In Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018 (pp. 46-49). [8644831] (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IS3C.2018.00020
Sung, Chun Yi ; Liu, Shih Yu ; Chen, Yan Min ; Chen, Chin-Hsing. / A segmentation and mixing strategy for retinex based image enhancement. Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 46-49 (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018).
@inproceedings{3dc577325c91481ca218fd525d7e483b,
title = "A segmentation and mixing strategy for retinex based image enhancement",
abstract = "Based on the human visual system, the Retinex image enhancement algorithm offers a forceful improvement for nonuniformly illuminated images. By observing that the original nonuniformly illuminated image has good performance in the bright area and the Retinex improved image has outstanding performance in the dark area, algorithms aiming to integrate the merits from both images were proposed. In this paper, we proposed an algorithm which performs the wavelet transform (WT) before segmentation and mixing. The wavelet transform decomposes an image into the coarse component and the detail components. The segmentation is performed on the course component and the result is used to fuse the course and detail components from both sources. The proposed algorithm is first subjectively assessed by using the dynamic range independent image quality assessment metric (DRIM) and compared with three existing algorithms. Experimental results show that the improved images using our proposed algorithm reveal significant amplification of contrast in the dark areas and mild loss and reversal of contrast in other areas. The proposed algorithm is objectively assessed by using information entropy. Experimental results show that among the four methods compared the information entropy of our proposed algorithm is the highest.",
author = "Sung, {Chun Yi} and Liu, {Shih Yu} and Chen, {Yan Min} and Chin-Hsing Chen",
year = "2019",
month = "2",
day = "19",
doi = "10.1109/IS3C.2018.00020",
language = "English",
series = "Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "46--49",
booktitle = "Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018",
address = "United States",

}

Sung, CY, Liu, SY, Chen, YM & Chen, C-H 2019, A segmentation and mixing strategy for retinex based image enhancement. in Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018., 8644831, Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018, Institute of Electrical and Electronics Engineers Inc., pp. 46-49, 4th International Symposium on Computer, Consumer and Control, IS3C 2018, Taichung, Taiwan, 18-12-06. https://doi.org/10.1109/IS3C.2018.00020

A segmentation and mixing strategy for retinex based image enhancement. / Sung, Chun Yi; Liu, Shih Yu; Chen, Yan Min; Chen, Chin-Hsing.

Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 46-49 8644831 (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A segmentation and mixing strategy for retinex based image enhancement

AU - Sung, Chun Yi

AU - Liu, Shih Yu

AU - Chen, Yan Min

AU - Chen, Chin-Hsing

PY - 2019/2/19

Y1 - 2019/2/19

N2 - Based on the human visual system, the Retinex image enhancement algorithm offers a forceful improvement for nonuniformly illuminated images. By observing that the original nonuniformly illuminated image has good performance in the bright area and the Retinex improved image has outstanding performance in the dark area, algorithms aiming to integrate the merits from both images were proposed. In this paper, we proposed an algorithm which performs the wavelet transform (WT) before segmentation and mixing. The wavelet transform decomposes an image into the coarse component and the detail components. The segmentation is performed on the course component and the result is used to fuse the course and detail components from both sources. The proposed algorithm is first subjectively assessed by using the dynamic range independent image quality assessment metric (DRIM) and compared with three existing algorithms. Experimental results show that the improved images using our proposed algorithm reveal significant amplification of contrast in the dark areas and mild loss and reversal of contrast in other areas. The proposed algorithm is objectively assessed by using information entropy. Experimental results show that among the four methods compared the information entropy of our proposed algorithm is the highest.

AB - Based on the human visual system, the Retinex image enhancement algorithm offers a forceful improvement for nonuniformly illuminated images. By observing that the original nonuniformly illuminated image has good performance in the bright area and the Retinex improved image has outstanding performance in the dark area, algorithms aiming to integrate the merits from both images were proposed. In this paper, we proposed an algorithm which performs the wavelet transform (WT) before segmentation and mixing. The wavelet transform decomposes an image into the coarse component and the detail components. The segmentation is performed on the course component and the result is used to fuse the course and detail components from both sources. The proposed algorithm is first subjectively assessed by using the dynamic range independent image quality assessment metric (DRIM) and compared with three existing algorithms. Experimental results show that the improved images using our proposed algorithm reveal significant amplification of contrast in the dark areas and mild loss and reversal of contrast in other areas. The proposed algorithm is objectively assessed by using information entropy. Experimental results show that among the four methods compared the information entropy of our proposed algorithm is the highest.

UR - http://www.scopus.com/inward/record.url?scp=85063225753&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063225753&partnerID=8YFLogxK

U2 - 10.1109/IS3C.2018.00020

DO - 10.1109/IS3C.2018.00020

M3 - Conference contribution

AN - SCOPUS:85063225753

T3 - Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

SP - 46

EP - 49

BT - Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Sung CY, Liu SY, Chen YM, Chen C-H. A segmentation and mixing strategy for retinex based image enhancement. In Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 46-49. 8644831. (Proceedings - 2018 International Symposium on Computer, Consumer and Control, IS3C 2018). https://doi.org/10.1109/IS3C.2018.00020