# Research on Image Adaptive Enhancement Algorithm under Low Light in License Plate Recognition System

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Image Classification

#### 2.1. Image Analysis of Traffic Block Port

#### 2.2. Design of Image Classifier

## 3. Research on Image Enhancement Algorithm under Low Light Condition

#### 3.1. Research on Enhancement Algorithm under Low Light Condition by Night

#### 3.1.1. Enhancement Algorithm Based on Histogram

#### 3.1.2. Enhancement Algorithm Based on the Retina

#### 3.1.3. Image Enhancement Algorithm Based on White Balance

#### 3.2. Research on Enhancement Algorithm under Low Light Condition by Day

## 4. Mathematical Model of the Enhancement Algorithm

#### 4.1. Dynamic Threshold Method of White Balance

_{b}/M

_{r}of the Component C

_{b}/R

_{b}in each area is calculated.

_{b}/D

_{r}of the absolute difference of the Component C

_{b}/R

_{b}in each area is calculated according to the Equations (1) and (2):

_{b}/D

_{r}is small, then this area will be ignored because it shows that this area is evenly distributed, but such an area is not good for white balance.

_{b}/M

_{r}and D

_{b}/D

_{r}in all areas except the one in the previous step are counted as M

_{b}/M

_{r}and D

_{b}/D

_{r}of the whole image. Determine which points belong to the white reference points according to Equations (3) and (4):

#### 4.2. Adaptive Histogram Equalization Algorithm

_{0}refers to the total number of pixels (image area), D

_{max}is the maximum gradation value, and D

_{A}and D

_{B}are respectively the gradation values before and after conversion, and Hi is the number of pixels of the gradation at the Level i.

## 5. Image Quality Measurement Indexes

#### 5.1. Structural Similarity Measurement Algorithm

_{1}, C

_{2}and C

_{3}are constants, which maintain stability to keep the denominator from being 0. Usually, $\{{\mathrm{C}}_{\mathrm{i}}={\left({\mathrm{K}}_{\mathrm{i}}\times \mathrm{L}\right)}^{2},\mathrm{i}=1,2,3\}$ is taken, among which K

_{1}= 0.01, K

_{2}= 0.03m, and L = 255. The final SSIM index is shown in the Equation (13). When it is set so that ${\mathrm{C}}_{3}={\mathrm{C}}_{2}/2$, the equation can be reduced to Equation (14).

#### 5.2. Normalized Mutual Information Algorithm

#### 5.3. Perceptual Hash Algorithm

#### 5.4. Comprehensive Weighted Evaluation Indexes

_{1}= w

_{2}= w

_{3}= 3 represents the weights assigned to the three values. For the consistency of the trend of the three values, PHG index is inverted. The closer the final result is to 1, the smaller the image loss will be.

## 6. Experimental Results and Analysis

## 7. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- La, H.; Lim, R.; Du, J.; Zhang, S.; Yan, G.; Sheng, W. Development of a Small-Scale Research Platform for Intelligent Transportation Systems. IEEE Trans. Intell. Transp. Syst.
**2012**, 13, 1753–1762. [Google Scholar] [CrossRef] - Zhao, N.; Yuan, J.B.; Xu, H. Survey on Intelligent Transportation System. Comput. Sci.
**2014**, 41, 7–11. [Google Scholar] - Shi, C.H.; Wu, C.D. Vehicle Face Recognition Algorithm Based on Weighted Nonnegative Matrix Factorization with Double Regularization Terms. KSII Trans. Internet Inf. Syst.
**2020**, 14, 2171–2185. [Google Scholar] - Shi, C.H.; Wu, C.D. Vehicle Face Recognition Algorithm Based on Weighted and Sparse Nonnegative Matrix Factorization. J. Northeast. Univ. Nat. Sci.
**2019**, 10, 1376–1380. [Google Scholar] - Yang, S.; Zhang, J.; Bo, C.; Wang, M.; Chen, L. Fast vehicle logo detection in complex scenes. Opt. Laser Technol.
**2019**, 110, 196–201. [Google Scholar] [CrossRef] - Al-Shemarry, M.S.; Li, Y.; Abdulla, S. An Efficient Texture Descriptor for the Detection of License Plates From Vehicle Images in Difficult Conditions. IEEE Trans. Intell. Transp. Syst.
**2019**, 21, 553–564. [Google Scholar] [CrossRef] - Yonetsu, S.; Iwamoto, Y.; Chen, Y.W. Two-Stage YOLOv2 for Accurate License-Plate Detection in Complex Scenes. In Proceedings of the 2019 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 11–13 January 2019. [Google Scholar] [CrossRef]
- Salau, A.O.; Yesufu, T.K.; Ogundare, B. Vehicle plate number localization using a modified GrabCut algorithm. J. King Saud Univ. Comput. Inf. Sci.
**2019**, 1–99. [Google Scholar] [CrossRef] - Soon, F.C.; Khaw, H.Y.; Chuah, J.H.; Kanesan, J. Vehicle logo recognition using whitening transformation and deep learning. Signal Image Video Process.
**2019**, 13, 111–119. [Google Scholar] [CrossRef] - Meyer, H.K.; Roberts, E.M.; Rapp, H.T.; Davies, A.J. Spatial Patterns of Arctic Sponge Ground Fauna and Demersal Fish are Detectable in Autonomous Underwater Vehicle (AUV) Imagery. Deep Sea Res. Part I Oceanogr. Res. Pap.
**2019**, 153, 103137. [Google Scholar] [CrossRef] - Kim, J.B. Efficient Vehicle Detection and Distance Estimation Based on Aggregated Channel Features and Inverse Perspective Mapping from a Single Camera. Symmetry
**2019**, 11, 1205. [Google Scholar] [CrossRef] [Green Version] - Xiaochu, W.; Guijin, T.; Xiaohua, L.; Ziguan, C.; Suhuai, L. Low-light Color Image Enhancement Based on NSST. J. China Univ. Posts Telecommun.
**2019**, 5, 6. [Google Scholar] - Selmi, Z.; Halima, M.B.; Pal, U.; Alimi, A.M. DELP-DAR System for License Plate Detection and Recognition. Pattern Recognit. Lett.
**2020**, 129, 213–223. [Google Scholar] [CrossRef] - Zhou, F.Y.; Jin, L.P.; Dong, J. Review of Convolutional Neural Network. Chin. J. Comput.
**2017**, 40, 1229–1251. [Google Scholar] - Howard, A.G.; Zhu, M.; Chen, B.; Kalenichenko, D.; Wang, W.; Weyand, T.; Andreetto, M.; Adam, H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv
**2017**, arXiv:1704.04861. [Google Scholar] - Wang, X.F.; Ma, Z. Research on Freight Train Number Identification Based on Convolutional Neural Network Lenet-5. Mod. Electron. Technol.
**2016**, 39, 63–66. [Google Scholar] - Kim, J.-Y.; Kim, L.-S.; Hwang, S.-H. An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization. IEEE Trans. Circuits Syst. Video Technol.
**2001**, 11, 475–484. [Google Scholar] - Yoon, Y.H.; Marmor, M.F. Rapid Enhancement of Retinal Adhesion by Laser Photocoagulation. Ophthalmology
**1988**, 95, 1385–1388. [Google Scholar] [CrossRef] - Fayad, L.M.; Jin, Y.; Laine, A.F.; Berkmen, Y.M.; Pearson, G.D.; Freedman, B.; Van Heertum, R. Chest CT Window Settings with Multiscale Adaptive Histogram Equalization: Pilot Study. Radiology
**2002**, 223, 845–852. [Google Scholar] [CrossRef] - Yamashina, H.; Fukushima, K.; Kano, H. White balance in inspection systems with a neural network. Comput. Integr. Manuf. Syst.
**1996**, 9, 3–8. [Google Scholar] [CrossRef] - Li, J.; Wang, X.X.; Liu, H. Auto White Balance Algorithm in Digital Camera. Appl. Mech. Mater.
**2012**, 182, 2080–2084. [Google Scholar] [CrossRef] - Thejas, G.S.; Joshi, S.R.; Iyengar, S.S.; Sunitha, N.R.; Badrinath, P. Mini-Batch Normalized Mutual Information: A Hybrid Feature Selection Method. IEEE Access
**2019**, 7, 116875–116885. [Google Scholar] [CrossRef] - Estévez, P.A.; Tesmer, M.; Perez, C.A.; Zurada, J.M. Normalized Mutual Information Feature Selection. IEEE Trans. Neural Netw.
**2009**, 20, 189–201. [Google Scholar] [CrossRef] [PubMed] [Green Version]

**Figure 5.**Low-light image by night and gradation histogram of low-light image by night. (

**a**) Low-light image by night; (

**b**) gradation histogram of low-light image by night.

**Figure 6.**Global and adaptive histogram equalization processing renderings. (

**a**) Global histogram equalization; (

**b**) adaptive histogram equalization.

**Figure 7.**Enhancement algorithm based on retina processing renderings processing renderings. (

**a**) original image; (

**b**) multiscale retinal enhancement algorithm; (

**c**) color gain weighting; and (

**d**) color restores multiple scales.

**Figure 8.**Image enhancement algorithm based on white balance processing rendering. (

**a**) Original image; (

**b**) averaging method; (

**c**) perfect reflection method; (

**d**) gradation world hypothesis method; (

**e**) color correction method of color cast detection; and (

**f**) dynamic threshold method.

**Figure 11.**Low-light image by day and gradation histogram. (

**a**) Low-light image by day; (

**b**) gradation histogram.

**Figure 12.**Different enhancement algorithms in low light by day processing rendering. (

**a**) Original image; (

**b**) global histogram equalization; (

**c**) adaptive histogram equalization; (

**d**) gamma transformation; (

**e**) averaging method; (

**f**) perfect reflection method; (

**g**) gradation world hypothesis method; (

**h**) color cast detection method; (

**i**) dynamic threshold method; and (

**j**) retinal enhancement algorithm.

**Figure 14.**Low-light treatment results by night: (

**a**) original image; (

**b**) first enhancement; (

**c**) second enhancement.

Classifier | Lenet5 | Deep Separable Convolution | SVM | Random Forest | Logic Regression |
---|---|---|---|---|---|

Train accuracy | 99.30% | 98.90% | 90.60% | 94.50% | 93.70% |

Test accuracy | 98.20% | 97.70% | 89.30% | 91.90% | 91.20% |

Class | SSIM | NMI | PHG | Weighted Comprehensive |
---|---|---|---|---|

Low light by night | 0.872 | 0.857 | 1.27 | 0.838 |

Low light by night | 0.853 | 0.882 | 1.18 | 0.861 |

© 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**

Shi, C.; Wu, C.; Gao, Y.
Research on Image Adaptive Enhancement Algorithm under Low Light in License Plate Recognition System. *Symmetry* **2020**, *12*, 1552.
https://doi.org/10.3390/sym12091552

**AMA Style**

Shi C, Wu C, Gao Y.
Research on Image Adaptive Enhancement Algorithm under Low Light in License Plate Recognition System. *Symmetry*. 2020; 12(9):1552.
https://doi.org/10.3390/sym12091552

**Chicago/Turabian Style**

Shi, Chunhe, Chengdong Wu, and Yuan Gao.
2020. "Research on Image Adaptive Enhancement Algorithm under Low Light in License Plate Recognition System" *Symmetry* 12, no. 9: 1552.
https://doi.org/10.3390/sym12091552