# Smart Image Enhancement Using CLAHE Based on an F-Shift Transformation during Decompression

^{1}

^{2}

^{3}

^{4}

^{5}

^{*}

^{†}

## Abstract

**:**

_{00}of the wavelet synopsis was used to adaptively adjust the global gray level of the reconstructed image. Next, the contrast-limited adaptive histogram equalization (CLAHE) was used to achieve the enhancement effect. To avoid a blocking effect, CLAHE was used when the synopsis was decompressed to the second-to-last level. At this time, we only enhanced the low-frequency component and did not change the high-frequency component. Lastly, we used CLAHE again after the image reconstruction. Through experiments, the effectiveness of our scheme was verified. Compared with the existing methods, the compression properties were preserved and the image details and contrast could also be enhanced. The experimental results showed that the image contrast, information entropy, and average gradient were greatly improved compared with the existing methods.

## 1. Introduction

## 2. Related Work

#### 2.1. F-Shift Transformation

#### 2.2. Two Dimensional F-Shift Transformation (TDFS)

#### 2.3. Contrast-Limited Adaptive Histogram Equalization (CLAHE)

_{1}, P

_{2}, P

_{3}, and P

_{4}, and the gray-level mappings of s are ${g}_{{P}_{1}}(s)$, ${g}_{{P}_{2}}(s)$, ${g}_{{P}_{3}}(s)$, and ${g}_{{P}_{4}}(s)$, respectively. For the pixels in the corners, the new gray value is equal to the gray-level mapping of s of this region. For example:

_{1}.

## 3. Proposed Method

#### 3.1. Adaptive Coefficient Adjustment

#### 3.2. Incomplete Decompression and Enhancing the Low-Frequency Component

#### 3.3. Complete Decompression and Further Enhancement

## 4. Experimental Results

#### 4.1. Impact of the Error Bound on the Enhancement and Compression Results

#### 4.2. Comparison of the Enhancement Effect of Different Methods

#### 4.3. Method Validation

## 5. Conclusions

## Author Contributions

## Funding

## Conflicts of Interest

## References

- Hsia, C.H.; Yang, J.H.; Chiang, J.S. Complexity reduction method for ultrasound imaging enhancement in tetrolet transform domain. J. Supercomput.
**2020**, 76, 1438–1449. [Google Scholar] [CrossRef] - Xia, K.J.; Wang, J.Q.; Cai, J. A novel medical image enhancement algorithm based on improvement correction strategy in wavelet transform domain. Cluster Comput.
**2019**, 22, 10969–10977. [Google Scholar] [CrossRef] - Pang, C.; Zhang, Q.; Zhou, X.; Hansen, D.; Wang, S.; Maeder, A. Computing unrestricted synopses under maximum error bound. Algorithmica
**2013**, 65, 1–42. [Google Scholar] [CrossRef] - Zhang, Q.; Pang, C.; Hansen, D. On multidimensional wavelet synopses for maximum error bounds. In International Conference on Database Systems for Advanced Applications; Springer: Berlin/Heidelberg, Germany, 2009; pp. 646–661. [Google Scholar]
- Rahman, S.; Rahman, M.M.; Abdullah-Al-Wadud, M.; Al-Quaderi, G.D.; Shoyaib, M. An adaptive gamma correction for image enhancement. EURASIP J. Image Video Process.
**2016**, 1, 1–13. [Google Scholar] [CrossRef] [Green Version] - Lim, S.H.; Isa, N.A.M.; Ooi, C.H.; Vin Toh, K.K. A new histogram equalization method for digital image enhancement and brightness preservation. Signal Image Video Process.
**2015**, 9, 675–689. [Google Scholar] [CrossRef] - Zhuang, L.; Guan, Y. Image enhancement via subimage histogram equalization based on mean and variance. Comput. Intell. Neurosci.
**2017**, 1–12. [Google Scholar] [CrossRef] [PubMed] [Green Version] - Arora, S.; Agarwal, M.; Kumar, V.; Gupta, D. Comparative study of image enhancement techniques using histogram equalization on degraded images. Int. J. Eng. Technol.
**2018**, 7, 468–471. [Google Scholar] [CrossRef] - Rahman, Z.U.; Jobson, D.J.; Woodell, G.A. Retinex processing for automatic image enhancement. J. Electron. Imaging.
**2004**, 13, 100–110. [Google Scholar] - Lee, S. An efficient content-based image enhancement in the compressed domain using retinex theory. IEEE Trans. Circuits Syst. Video Technol.
**2007**, 17, 199–213. [Google Scholar] [CrossRef] - Anand, S.; Gayathri, S. Mammogram image enhancement by two-stage adaptive histogram equalization. Optik
**2015**, 126, 3150–3152. [Google Scholar] [CrossRef] - Sargun, S.; Rana, S.B. Performance evaluation of HE, AHE and fuzzy image enhancement. Int. J. Comput. Appl.
**2015**, 122, 14–19. [Google Scholar] [CrossRef] - Zuiderveld, K. Contrast limited adaptive histogram equalization. Graph. Gems
**1994**, 474–485. [Google Scholar] - Singh, P.; Mukundan, R.; Ryke, R.D. Feature enhancement in medical ultrasound videos using contrast-limited adaptive histogram equalization. J. Digital Imaging
**2019**, 1–13. [Google Scholar] [CrossRef] - Wang, J.W.; Le, N.T.; Lee, J.S.; Wang, C.C. Color face image enhancement using adaptive singular value decomposition in fourier domain for face recognition. Pattern Recognit.
**2016**, 57, 31–49. [Google Scholar] [CrossRef] - Makandar, A.; Halalli, B. Image enhancement techniques using highpass and lowpass filters. Int. J. Comput. Appl.
**2015**, 109, 21–27. [Google Scholar] [CrossRef] - Kuo, C.M.; Yang, N.C.; Liu, C.S.; Tseng, P.Y.; Chang, C.K. An effective and flexible image enhancement algorithm in compressed domain. Multimed. Tools Appl.
**2016**, 75, 1177–1200. [Google Scholar] [CrossRef] - Sharma, A.; Khunteta, A. Satellite image enhancement using discrete wavelet transform, singular value decomposition and its noise performance analysis. In Proceedings of the 2016 International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE), Ghaziabad, India, 22–23 September 2016; pp. 594–599. [Google Scholar]
- Hsieh, C.T.; Lai, E.; Wang, Y.C. An effective algorithm for fingerprint image enhancement based on wavelet transform. Pattern Recognit.
**2003**, 36, 303–312. [Google Scholar] [CrossRef] - Kim, S.; Kang, W.; Lee, E.; Paik, J. Wavelet-domain color image enhancement using filtered directional bases and frequency-adaptive shrinkage. IEEE Trans. Consum. Electron.
**2010**, 56, 1063–1070. [Google Scholar] [CrossRef] - Uhring, W.; Jung, M.; Summ, P. Image processing provides low-frequency jitter correction for synchroscan streak camera temporal resolution enhancement. Opt. Metrol. Prod. Eng.
**2004**, 5457, 245–252. [Google Scholar] - Yang, J.; Wang, Y.; Xu, W.; Dai, Q. Image and video denoising using adaptive dual-tree discrete wavelet packets. IEEE Trans. Circuits Syst. Video Technol.
**2009**, 19, 642–655. [Google Scholar] [CrossRef] - Shahane, P.R.; Mule, S.B.; Ganorkar, S.R. Color image enhancement using discrete wavelet transform. Digital Image Process.
**2012**, 4, 1–5. [Google Scholar] - Zhang, C.; Ma, L.N.; Jing, L.N. Mixed frequency domain and spatial of enhancement algorithm for infrared image. In Proceedings of the 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery, Sichuan, China, 29–31 May 2012; pp. 2706–2710. [Google Scholar]
- Huang, L.; Zhao, W.; Wang, J.; Sun, Z. Combination of contrast limited adaptive histogram equalisation and discrete wavelet transform for image enhancement. IET Image Process.
**2015**, 9, 908–915. [Google Scholar] - Fan, R.; Li, X.; Zhao, H.; Zhang, H.; Pang, C.; Wang, J. Image enhancement method in decompression based on F-shift transformation. In Communications in Computer and Information Science, Proceedings of the 6th International Conference, ICDS 2019, Ningbo, China, 15–20 May 2019; Springer: Berlin/Heidelberg, Germany, 2020; Volume 1179, pp. 232–241. [Google Scholar]
- Li, X.; Fan, R.; Zhang, H.; Li, T.; Pang, C. Two-dimensional wavelet synopses with maximum error bound and its application in parallel compression. J. Intell. Fuzzy Syst.
**2019**, 37, 3499–3511. [Google Scholar] [CrossRef] - Abdullah-Al-Wadud, M.; Kabir, M.H.; Dewan, M.A.A.; Chae, O. A dynamic histogram equalization for image contrast enhancement. IEEE Trans. Consum. Electron.
**2007**, 53, 593–600. [Google Scholar] [CrossRef] - Li, X.; Li, T.; Zhao, H.; Dou, Y.; Pang, C. Medical image enhancement in F-shift transformation domain. Health Inf. Sci. Syst.
**2019**, 7, 1–8. [Google Scholar] [CrossRef] - Lee, H.S.; Moon, S.W.; Eom, I.K. Underwater image enhancement using successive color correction and superpixel dark channel prior. Symmetry
**2020**, 12, 1220. [Google Scholar] [CrossRef] - Li, B.; Xie, W. Image denoising and enhancement based on adaptive fractional calculus of small probability strategy. Neurocomputing
**2016**, 175, 704–714. [Google Scholar] [CrossRef] - Qu, Z.; Xing, Y.; Song, Y. Image enhancement based on pulse coupled neural network in the nonsubsample shearlet transform domain. Math. Prob. Eng.
**2019**, 2019, 1–11. [Google Scholar] [CrossRef] [Green Version] - Chang, D.C.; Wu, W.R. Image contrast enhancement based on a Histogram transformation of local standard deviation. IEEE Trans. Med. Imaging
**1998**, 17, 518–531. [Google Scholar] [CrossRef] [Green Version] - Zhuang, L.; Guan, Y. Adaptive Image enhancement using entropy-based subhistogram equalization. Comput. Intell. Neurosci.
**2018**. [Google Scholar] [CrossRef] [Green Version]

**Figure 2.**An example of a two–dimensional F-shift transformation (TDFS): (

**a**) original data array, (

**b**) first-level TDFS, (

**c**) second-level TDFS, and (

**d**) computing the approximation.

**Figure 4.**The compression process before the enhancement: (

**a**) original data array, (

**b**) first-level TDFS, (

**c**) compute the approximation, and (

**d**) non-standard two-dimensional wavelet transform (NSTW) for the approximation.

**Figure 5.**The steps of our enhancement method. CLAHE: Contrast-limited adaptive histogram equalization.

**Figure 6.**The enhanced image under different error bounds: (

**a**) original image, (

**b**) Δ = 0, (

**c**) Δ = 2, (

**d**) Δ = 5, and (

**e**) Δ = 8.

**Figure 7.**The enhanced image under different error bounds: (

**a**) original image, (

**b**) Δ = 0, (

**c**) Δ = 2, (

**d**) Δ = 5, and (

**e**) Δ = 8.

**Figure 8.**The enhanced image under different error bounds: (

**a**) original image, (

**b**) $\Delta =0$, (

**c**) $\Delta =2$, (

**d**) $\Delta =5$, and (

**e**) $\Delta =8$.

**Figure 16.**Comparison results of different schemes: (

**a**) original image, (

**b**) CLAHE, (

**c**) scheme 1, (

**d**) scheme 2, (

**e**) scheme 3, (

**f**) scheme 4, (

**g**) scheme 5, and (

**h**) our method.

**Figure 17.**Comparison results of different schemes: (

**a**) original image, (

**b**) CLAHE, (

**c**) scheme 1, (

**d**) scheme 2, (

**e**) scheme 3, (

**f**) scheme 4, (

**g**) scheme 5, and (

**h**) our method.

**Figure 18.**Comparison results of different schemes: (

**a**) original image, (

**b**) CLAHE, (

**c**) scheme 1, (

**d**) scheme 2, (

**e**) scheme 3, (

**f**) scheme 4, (

**g**) scheme 5, and (

**h**) our method.

**Figure 19.**Comparison results of different schemes: (

**a**) original image, (

**b**) CLAHE, (

**c**) scheme 1, (

**d**) scheme 2, (

**e**) scheme 3, (

**f**) scheme 4, (

**g**) scheme 5, and (

**h**) our method.

Resolution | Low-Frequency Component | High-Frequency Component |
---|---|---|

8 | {[5,9], [4,8], [−1,3], [6,10],[3,7], [2,6], [0,4], [8,12]} | ------ |

4 | {[5,8], [2.5,6.5], [3,6], [4,8]} | {0,3.5,0,−4} |

2 | {[5,6.5], [4,6]} | {0,0} |

1 | {[5,6]} | {0} |

Images | Methods | Mean | SD | Entropy | AG |
---|---|---|---|---|---|

Figure 10 | Original | 175.33 | 22.12 | 4.00 | 2.32 |

CLAHE [13] | 177.31 | 24.00 | 5.73 | 3.66 | |

CLAHE_DWT [25] | 174.04 | 25.08 | 5.74 | 3.36 | |

Our method | 145.53 | 38.75 | 7.23 | 10.42 | |

Figure 11 | Original | 172.16 | 55.83 | 6.98 | 15.25 |

CLAHE [13] | 156.15 | 67.02 | 7.71 | 21.90 | |

CLAHE_DWT [25] | 161.73 | 69.02 | 7.32 | 18.99 | |

Our method | 134.30 | 71.25 | 7.95 | 22.90 | |

Figure 12 | Original | 132.38 | 27.06 | 5.50 | 5.00 |

CLAHE [13] | 145.48 | 39.08 | 7.16 | 10.15 | |

CLAHE_DWT [25] | 165.83 | 49.75 | 7.53 | 12.25 | |

Our method | 131.32 | 70.14 | 7.98 | 20.10 | |

Figure 13 | Original | 95.39 | 53.78 | 6.12 | 7.01 |

CLAHE [13] | 107.27 | 59.31 | 7.76 | 9.79 | |

CLAHE_DWT [25] | 127.63 | 67.71 | 7.95 | 12.38 | |

Our method | 125.44 | 71.51 | 7.99 | 14.92 | |

Figure 14 | Original | 32.52 | 25.11 | 5.43 | 2.55 |

CLAHE [13] | 55.16 | 39.74 | 6.52 | 7.12 | |

CLAHE_DWT [25] | 94.57 | 53.48 | 7.02 | 8.68 | |

Our method | 93.92 | 48.86 | 7.48 | 12.95 | |

Figure 15 | Original | 20.12 | 19.68 | 5.63 | 1.67 |

CLAHE [13] | 51.67 | 42.00 | 6.95 | 4.40 | |

CLAHE_DWT [25] | 75.26 | 55.24 | 7.39 | 5.61 | |

Our method | 92.60 | 61.72 | 7.72 | 7.90 |

Images | Methods | Mean | SD | Entropy | AG |
---|---|---|---|---|---|

Figure 16 | Original | 175.33 | 22.12 | 4.00 | 2.32 |

CLAHE [13] | 177.31 | 24.00 | 5.73 | 3.66 | |

Scheme 1 | 146.86 | 25.65 | 6.18 | 4.44 | |

Scheme 2 | 147.15 | 22.85 | 5.81 | 3.68 | |

Scheme 3 | 167.66 | 32.51 | 6.72 | 8.64 | |

Scheme 4 | 145.00 | 40.17 | 7.29 | 10.84 | |

Scheme 5 | 145.73 | 31.82 | 6.79 | 8.92 | |

Our method | 141.50 | 40.67 | 7.34 | 11.60 | |

Figure 17 | Original | 132.38 | 27.06 | 5.50 | 5.00 |

CLAHE [13] | 145.48 | 39.08 | 7.16 | 10.15 | |

Scheme 1 | 143.29 | 45.90 | 7.48 | 11.05 | |

Scheme 2 | 140.98 | 46.34 | 7.51 | 13.70 | |

Scheme 3 | 136.79 | 63.18 | 7.91 | 20.96 | |

Scheme 4 | 132.65 | 69.80 | 7.97 | 19.77 | |

Scheme 5 | 130.49 | 70.87 | 7.98 | 24.66 | |

Our method | 130.35 | 70.88 | 7.99 | 20.52 | |

Figure 18 | Original | 20.12 | 19.68 | 5.63 | 1.65 |

CLAHE [13] | 51.67 | 42.00 | 6.95 | 4.39 | |

Scheme 1 | 57.31 | 40.57 | 6.91 | 4.09 | |

Scheme 2 | 57.70 | 40.72 | 6.92 | 4.24 | |

Scheme 3 | 91.16 | 62.22 | 7.74 | 7.98 | |

Scheme 4 | 94.04 | 61.13 | 7.73 | 7.94 | |

Scheme 5 | 94.10 | 61.05 | 7.73 | 8.17 | |

Our method | 93.67 | 60.88 | 7.74 | 8.32 | |

Figure 19 | Original | 14.07 | 39.75 | 4.13 | 2.28 |

CLAHE [13] | 29.25 | 47.36 | 5.20 | 4.43 | |

Scheme 1 | 33.52 | 47.21 | 4.91 | 3.90 | |

Scheme 2 | 33.85 | 46.75 | 5.13 | 4.15 | |

Scheme 3 | 45.20 | 55.36 | 6.24 | 5.83 | |

Scheme 4 | 47.63 | 56.94 | 6.12 | 6.00 | |

Scheme 5 | 48.04 | 55.58 | 6.29 | 6.30 | |

Our method | 48.24 | 57.09 | 6.35 | 6.10 |

© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Fan, R.; Li, X.; Lee, S.; Li, T.; Zhang, H.L.
Smart Image Enhancement Using CLAHE Based on an F-Shift Transformation during Decompression. *Electronics* **2020**, *9*, 1374.
https://doi.org/10.3390/electronics9091374

**AMA Style**

Fan R, Li X, Lee S, Li T, Zhang HL.
Smart Image Enhancement Using CLAHE Based on an F-Shift Transformation during Decompression. *Electronics*. 2020; 9(9):1374.
https://doi.org/10.3390/electronics9091374

**Chicago/Turabian Style**

Fan, Ruiqin, Xiaoyun Li, Sanghyuk Lee, Tongliang Li, and Hao Lan Zhang.
2020. "Smart Image Enhancement Using CLAHE Based on an F-Shift Transformation during Decompression" *Electronics* 9, no. 9: 1374.
https://doi.org/10.3390/electronics9091374