Underwater Image Enhancement Based on Adaptive Color Balance and Contrast Optimization with Minimum Information Loss
| dc.contributor.author | Tajrin, Tamanna | |
| dc.date.accessioned | 2026-07-28T10:21:59Z | |
| dc.date.issued | 2025-10-25 | |
| dc.description | Supervised by Dr. Md. HasanulKabir, Professor, Department of Computer Science and Engineering (CSE) Islamic University of Technology (IUT) Board Bazar, Gazipur, Bangladesh This thesis is submitted in partial fulfillment of the requirement for the degree of Master of Science in Computer Science and Engineering, 2025 | |
| dc.description.abstract | Underwater imaging suffers from severe visual degradation as a result of wavelength dependent light absorption and scattering, resulting in low contrast, color shifts, and loss of finedetails. Toovercomethesechallenges, thisstudypresentsamulti-modular underwater image enhancement framework. The first module, adaptive color cor rection, addresses color shift by compensating the RGB channels and adjusting each channel using condition-checked compensation values, effectively removing bluish, greenish, or yellowish casts. The second module, contrast optimization, enhances visibility by employing dark channel prior-based estimation along with a cost func tion that maximizes contrast while minimizing information loss. The third module focuses on fusion and visual improvement, where gamma correction adjusts lumi nance levels, unsharpmaskingimprovesedgesharpness, imagefusionandhistogram stretching redistributes pixel intensities across the full range to improve tonal balance andtexture clarity. The system was evaluated on multiple underwater image datasets —OccanDark, UIEB, UIEDP, and EUVP—covering diverse degradation conditions. Performance was measured using both subjective visual assessment and objective metrics, including PCQI, UCIQE, IE, and UIQM. Results confirm that the proposed framework comparatively outperforms existing techniques in color fidelity, contrast enhancement, and detail preservation. By addressing color casts, low contrast, and poor brightness with detail representation, the framework delivers high-quality un derwater images with minimal information loss, making it suitable for marine engi neering, underwater exploration, and scientific research | |
| dc.identifier.citation | [1] ShunminAn,LihongXu,Zhichao Deng, et al. “HFM: A hybrid fusion method for underwater image enhancement”. In: Engineering Applications of Artificial Intelligence 127 (Jan. 2024), p. 107219. issn: 0952-1976. doi: 10 . 1016 / j . engappai.2023.107219. url: http://dx.doi.org/10.1016/j.engappai. 2023.107219. [2] CodrutaO.Ancuti,CosminAncuti,Christophe DeVleeschouwer, et al. “Color Balance and Fusion for Underwater Image Enhancement”. In: IEEE Transac tions on Image Processing 27.1 (Jan. 2018), pp. 379–393. issn: 1941-0042. doi: 10.1109/tip.2017.2759252. url: http://dx.doi.org/10.1109/TIP. 2017.2759252. [3] M.Sudhakara, M. Janaki Meena, et al. “Multi-scale fusion for underwater im ageenhancementusingmulti-layerperceptron”.In:IAESInternationalJournal of Artificial Intelligence (IJ-AI) 10.2 (June 2021), p. 389. issn: 2089-4872. doi: 10.11591/ijai.v10.i2.pp389-397. url: http://dx.doi.org/10.11591/ ijai.v10.i2.pp389-397. [4] KaiboLiao,XiPeng,etal. In: PLOSONE 19.2(Feb.2024).Ed.byXueboZhang, e0299110.issn:1932-6203.doi:10.1371/journal.pone.0299110.url:http: //dx.doi.org/10.1371/journal.pone.0299110. [5] ShijieLin, ZheLi,FuhaiZheng,etal.“UnderwaterImageEnhancementBased on Adaptive Color Correction and Improved Retinex Algorithm”. In: IEEE Ac cess 11 (2023), pp. 27620–27630. issn: 2169-3536. doi: 10.1109/access.2023. 3258698. url: http://dx.doi.org/10.1109/ACCESS.2023.3258698. [6] Peixian Zhuang, Chongyi Li, et al. “Bayesian Retinex Underwater Image En hancement”.In:EngineeringApplicationsofArtificialIntelligence101(May2021), p. 104171. issn: 0952-1976. doi: 10.1016/j.engappai.2021.104171. url: http://dx.doi.org/10.1016/j.engappai.2021.104171. [7] Peixian Zhuang, Ming Li, Rui Chen, et al. “Retinex Underwater Image En hancementWithMultiorderGradientPriors”.In:2021IEEEInternationalCon ference on Image Processing (ICIP). IEEE, Sept. 2021, pp. 1709–1713. doi: 10. 48 1109/icip42928.2021.9506104. url: http://dx.doi.org/10.1109/ ICIP42928.2021.9506104. [8] JingchunZhou,JianYao,WeishiZhang,etal. “Multi-scale retinex-based adap tive gray-scale transformation method for underwater image enhancement”. In: Multimedia Tools and Applications 81.2 (Oct. 2021), pp. 1811–1831. issn: 1573-7721. doi: 10.1007/s11042-021-11327-8. url: http://dx.doi.org/ 10.1007/s11042-021-11327-8. [9] LinZhang, Tong Peng, Wei Liu, et al. “Underwater image enhancement based on improved adaptive MSRCR and Gamma function”. In: 2023 2nd Interna tional Conference on Cloud Computing, Big Data Application and Software En gineering (CBASE). IEEE, Nov. 2023, pp. 246–252. doi: 10.1109/cbase60015. 2023.10439083. url: http://dx.doi.org/10.1109/CBASE60015.2023. 10439083. [10] Peixian Zhuang, Xinghao Ding, et al. “Underwater image enhancement using an edge-preserving filtering Retinex algorithm”. In: Multimedia Tools and Ap plications 79.25–26 (Jan. 2020), pp. 17257–17277. issn: 1573-7721. doi: 10. 1007/s11042-019-08404-4. url: http://dx.doi.org/10.1007/s11042 019-08404-4. [11] Weilin Luo, Shunqiang Duan, et al. “Underwater Image Restoration and En hancement Based on a Fusion Algorithm With Color Balance, Contrast Op timization, and Histogram Stretching”. In: IEEE Access 9 (2021), pp. 31792 31804. issn: 2169-3536. doi: 10.1109/access.2021.3060947. url: http: //dx.doi.org/10.1109/ACCESS.2021.3060947. [12] Weidong Zhang, Songlin Jin, Peixian Zhuang, et al. “Underwater Image En hancement via Piecewise Color Correction and Dual Prior Optimized Contrast Enhancement”. In: IEEESignal Processing Letters 30 (2023), pp. 229–233. issn: 1558-2361. doi: 10.1109/lsp.2023.3255005. url: http://dx.doi.org/10. 1109/LSP.2023.3255005. [13] Dan Xiang, Huihua Wang, Dengyu He, et al. “Research on Histogram Equal ization Algorithm Based on Optimized Adaptive Quadruple Segmentation and CroppingofUnderwaterImage(AQSCHE)”.In:IEEEAccess11(2023),pp.69356 69365. issn: 2169-3536. doi: 10.1109/access.2023.3290201. url: http: //dx.doi.org/10.1109/ACCESS.2023.3290201. [14] Dabing Yu et al. “Underwater Image Restoration Based on Red Channel and Haze-Lines Prior”. In: Intelligent Robotics and Applications. Springer Interna tional Publishing, 2019, pp.148–158.isbn:9783030275327.doi:10.1007/978 3-030-27532-7_13. url: http://dx.doi.org/10.1007/978-3-030-27532 7_13. 49 [15] ManviJha,AshishKumarBhandari,RajeshSingh,etal.“CBLA:Color-Balanced Locally Adjustable Underwater Image Enhancement”. In: IEEE Transactions onInstrumentationandMeasurement 73(2024),pp.1–11.issn:1557-9662.doi: 10.1109/tim.2024.3396850. url: http://dx.doi.org/10.1109/TIM. 2024.3396850. [16] Siyi Ren, Xianqiang Bao, Tianjiang Wang, et al. “UIEVUS: An underwater im age enhancement method for various underwater scenes”. In: Signal Process ing: Image Communication 135 (July 2025), p. 117264. issn: 0923-5965. doi: 10.1016/j.image.2025.117264. url: http://dx.doi.org/10.1016/j. image.2025.117264. [17] Lei Pang, Jingchun Zhou, Weishi Zhang, et al. “Underwater image enhance ment via variable contrast and saturation enhancement model”. In: Multime dia Tools and Applications 82.30(May2023),pp.47495–47516.issn:1573-7721. doi: 10.1007/s11042-023-15419-5. url: http://dx.doi.org/10.1007/ s11042-023-15419-5. [18] FarongGao,KaiWang,ZhangyiYang,etal.“UnderwaterImageEnhancement Based on Local Contrast Correction and Multi-Scale Fusion”. In: Journal of Marine Science and Engineering 9.2 (Feb. 2021), p. 225. issn: 2077-1312. doi: 10.3390/jmse9020225. url: http://dx.doi.org/10.3390/jmse9020225. [19] Kai-Fu Yang, Hui Li, Hulin Kuang, et al. “An Adaptive Method for Image Dy namic Range Adjustment”. In: IEEE Transactions on Circuits and Systems for VideoTechnology29.3(Mar.2019),pp.640–652.issn:1558-2205.doi:10.1109/ tcsvt.2018.2810212. url: http://dx.doi.org/10.1109/TCSVT.2018. 2810212. [20] WeidongZhang,YudongWang,ChongyiLi,etal.“UnderwaterImageEnhance ment by Attenuated Color Channel Correction and Detail Preserved Contrast Enhancement”.In:IEEEJournalofOceanicEngineering47.3(July2022),pp.718 735. issn: 2373-7786. doi: 10.1109/joe.2022.3140563. url: http://dx. doi.org/10.1109/JOE.2022.3140563. [21] ZhengLiang,WeidongZhang,RuiRuan,etal.“UnderwaterImageQualityIm provement via Color, Detail, and Contrast Restoration”. In: IEEE Transactions on Circuits and Systems for Video Technology 34.3 (Mar. 2024), pp. 1726–1742. issn: 1558-2205. doi: 10.1109/tcsvt.2023.3297524. url: http://dx.doi. org/10.1109/TCSVT.2023.3297524. [22] JunAo,ChunboMa,etal.“AdaptiveStretchingMethodforUnderwaterImage Color Correction”. In: International Journal of Pattern Recognition and Artifi cial Intelligence 32.02 (Nov. 2017), p. 1854001. issn: 1793-6381. doi: 10.1142/ s0218001418540010.url:http://dx.doi.org/10.1142/S0218001418540010. 50 [23] Tunai Porto Marques, Alexandra Branzan Albu, et al. “L2UWE: A Framework for the Efficient Enhancement of Low-Light Underwater Images Using Local Contrast and Multi-Scale Fusion”. In: (June 2020). [24] ZhisenWang,ZhuoyiLi,XuanxuanTeng,etal.“LPMsDE:Multi-ScaleDenois ing and Enhancement Method Based on Laplacian Pyramid Framework for Forward-Looking Sonar Image”. In: IEEEAccess 11 (2023), pp. 132942–132954. issn: 2169-3536. doi: 10.1109/access.2023.3335372. url: http://dx.doi. org/10.1109/ACCESS.2023.3335372. [25] Guojia Hou, Nan Li, Peixian Zhuang, et al. “Non-Uniform Illumination Un derwater ImageRestoration via Illumination Channel Sparsity Prior”. In: IEEE TransactionsonCircuitsandSystemsforVideoTechnology34.2(Feb.2024),pp.799 814. issn: 1558-2205. doi: 10.1109/tcsvt.2023.3290363. url: http://dx. doi.org/10.1109/TCSVT.2023.3290363. [26] Ashraf Saleem, Sidike Paheding, Nathir Rawashdeh, et al. “A Non-Reference Evaluation of Underwater Image Enhancement Methods Using a New Under water Image Dataset”. In: IEEE Access 11 (2023), pp. 10412–10428. issn: 2169 3536. doi: 10.1109/access.2023.3240648. url: http://dx.doi.org/10. 1109/ACCESS.2023.3240648. [27] Chongyi Li, Chunle Guo, Wenqi Ren, et al. “An Underwater Image Enhance ment Benchmark Dataset and Beyond”. In: IEEE Transactions on Image Pro cessing 29 (2020), pp. 4376–4389. issn: 1941-0042. doi: 10.1109/tip.2019. 2955241. url: http://dx.doi.org/10.1109/TIP.2019.2955241. [28] ShiqiWang,KedeMa,HojatollahYeganeh,et al. “A Patch-Structure Represen tation Method for Quality Assessment of Contrast Changed Images”. In: IEEE SignalProcessingLetters 22.12(Dec.2015),pp.2387–2390.issn:1558-2361.doi: 10.1109/lsp.2015.2487369. url: http://dx.doi.org/10.1109/LSP. 2015.2487369. [29] Miao Yang, Arcot Sowmya, Jian Li, et al. “An Underwater Color Image Qual ity Evaluation Metric”. In: IEEE Transactions on Image Processing 24.12 (Dec. 2015),pp.6062–6071.issn:1941-0042.doi:10.1109/tip.2015.2491020.url: http://dx.doi.org/10.1109/TIP.2015.2491020. [30] Karen Panetta, Chen Gao, Sos Agaian, et al. “Human-Visual-System-Inspired Underwater Image Quality Measures”. In: IEEE Journal of Oceanic Engineer ing 41.3 (July 2016), pp. 541–551. issn: 2373-7786. doi: 10.1109/joe.2015. 2469915. url: http://dx.doi.org/10.1109/JOE.2015.2469915. [31] OmarAlmutiry, Khalid Iqbal, Shariq Hussain, et al. “Underwater images con trast enhancement and its challenges: a survey”. In: Multimedia Tools and Ap plications 83.5 (Feb. 2021), pp. 15125–15150. issn: 1573-7721. doi: 10.1007/ 51 s11042-021-10626-4. url: http://dx.doi.org/10.1007/s11042-021 10626-4. [32] Smitha Raveendran, Mukesh D. Patil, Gajanan K. Birajdar, et al. “Underwater image enhancement: a comprehensive review, recent trends, challenges and applications”. In: Artificial Intelligence Review 54.7 (June 2021), pp. 5413–5467. issn: 1573-7462. doi: 10.1007/s10462-021-10025-z. url: http://dx.doi. org/10.1007/s10462-021-10025-z. [33] Kancharagunta Kishan Babu, Ashreen Tabassum, Bommakanti Navaneeth, et al. “Underwater image enhancement using generative adversarial networks: a survey”. In: International Journal of Computers and Applications 47.4 (Feb. 2025), pp. 356–372. issn: 1925-7074. doi: 10.1080/1206212x.2025.2466197. url: http://dx.doi.org/10.1080/1206212X.2025.2466197. [34] JianxiangLu,FeiYuan,WeidiYang,etal.“AnImagingInformationEstimation Network forUnderwaterImageColorRestoration”.In:IEEEJournalofOceanic Engineering 46.4 (Oct. 2021), pp. 1228–1239. issn: 2373-7786. doi: 10.1109/ joe.2021.3077692. url: http://dx.doi.org/10.1109/JOE.2021.3077692. [35] Dabing Yu et al. “Underwater Image Restoration Based on Red Channel and Haze-Lines Prior”. In: Intelligent Robotics and Applications. Springer Interna tional Publishing, 2019, pp.148–158.isbn:9783030275327.doi:10.1007/978 3-030-27532-7_13. url: http://dx.doi.org/10.1007/978-3-030-27532 7_13. [36] Derya Akkaynak, Tali Treibitz, et al. “Sea-Thru: A Method for Removing Wa ter From Underwater Images”. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). June 2019. [37] Shengcong Wu, Ting Luo, Gangyi Jiang, et al. “A Two-Stage Underwater En hancement Network Based on Structure Decomposition and Characteristics of UnderwaterImaging”.In:IEEEJournalofOceanicEngineering46.4(Oct.2021), pp.1213–1227.issn:2373-7786.doi:10.1109/joe.2021.3064093.url:http: //dx.doi.org/10.1109/JOE.2021.3064093. [38] N.Deluxni, Pradeep Sudhakaran, R. Narayanamoorthi, et al. “Underwater Im age Enhancement Using White Balancing with Color Correction Based on Re current Neural Network”. In: 2025 International Conference on Data Science andBusinessSystems(ICDSBS).IEEE,Apr.2025,pp.1–7.doi:10.1109/icdsbs63635. 2025.11032066. url: http://dx.doi.org/10.1109/ICDSBS63635.2025. 11032066. [39] PengLiu, GuoyuWang,HaoQi,et al. “Underwater Image Enhancement With a Deep Residual Framework”. In: IEEEAccess 7 (2019), pp. 94614–94629. issn: 52 2169-3536. doi: 10.1109/access.2019.2928976. url: http://dx.doi.org/ 10.1109/ACCESS.2019.2928976. [40] YudongWang,JichangGuo,HuanGao,etal.“UIEC2−𝑁𝑒𝑡 ∶ 𝐶𝑁𝑁−𝑏𝑎𝑠𝑒𝑑𝑢𝑛𝑑𝑒𝑟𝑤𝑎𝑡𝑒𝑟𝑖𝑚𝑎𝑔𝑒𝑒𝑛ℎ𝑎𝑛𝑐𝑒𝑚𝑒𝑛𝑡𝑢𝑠𝑖𝑛𝑔𝑡𝑤𝑜𝑐𝑜𝑙𝑜𝑟𝑠𝑝𝑎𝑐𝑒 In: Signal Processing: Image Communication 96 (Aug. 2021), p. 116250. issn: 0923-5965. doi: 10.1016/j.image.2021.116250. url: http://dx.doi.org/ 10.1016/j.image.2021.116250. [41] RunminCong,WenyuYang,WeiZhang,etal.“PUGAN:PhysicalModel-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators”. In: IEEE Transactions on Image Processing 32 (2023), pp. 4472–4485. issn: 1941 0042. doi: 10.1109/tip.2023.3286263. url: http://dx.doi.org/10.1109/ TIP.2023.3286263. [42] Jie Han, Jian Zhou, Lin Wang, et al. “FE-GAN: Fast and Efficient Underwater Image Enhancement Model Based on Conditional GAN”. In: Electronics 12.5 (Mar. 2023), p. 1227. issn: 2079-9292. doi: 10.3390/electronics12051227. url: http://dx.doi.org/10.3390/electronics12051227. [43] Yang Guan, Xiaoyan Liu, Zhibin Yu, et al. “Fast underwater image enhance ment based on a generative adversarial framework”. In: Frontiers in Marine Science 9 (Feb. 2023). issn: 2296-7745. doi: 10.3389/fmars.2022.964600. url: http://dx.doi.org/10.3389/fmars.2022.964600. [44] Zhen Shen, Haiyong Xu, Ting Luo, et al. “UDAformer: Underwater image en hancement based on dual attention transformer”. In: Computers Graphics 111 (Apr. 2023), pp. 77–88. issn: 0097-8493. doi: 10.1016/j.cag.2023.01.009. url: http://dx.doi.org/10.1016/j.cag.2023.01.009. [45] Lintao Peng, Chunli Zhu, Liheng Bian, et al. “U-Shape Transformer for Un derwater Image Enhancement”. In: IEEE Transactions on Image Processing 32 (2023), pp. 3066–3079. issn: 1941-0042. doi: 10.1109/tip.2023.3276332. url: http://dx.doi.org/10.1109/TIP.2023.3276332. [46] MohamedBadran, Marwan Torki, et al. “DAUT: Underwater Image Enhance ment Using Depth Aware U-shape Transformer”. In: 2023 IEEE International Conference on Image Processing (ICIP). IEEE, Oct. 2023, pp. 1830–1834. doi: 10.1109/icip49359.2023.10222895. url: http://dx.doi.org/10.1109/ ICIP49359.2023.10222895. [47] Yi Liu, Qiuping Jiang, Xinyi Wang, et al. “Underwater Image Enhancement With Cascaded Contrastive Learning”. In: IEEE Transactions on Multimedia 27 (2025), pp. 1512–1525. issn: 1941-0077. doi: 10.1109/tmm.2024.3521739. url: http://dx.doi.org/10.1109/TMM.2024.3521739. 53 [48] Zhengyong Wang, Liquan Shen, Mai Xu, et al. “Domain Adaptation for Un derwater Image Enhancement”. In: IEEE Transactions on Image Processing 32 (2023), pp. 1442–1457. issn: 1941-0042. doi: 10.1109/tip.2023.3244647. url: http://dx.doi.org/10.1109/TIP.2023.3244647. [49] Wang Li, Xing Li, Ke Li, et al. “Underwater image restoration based on dual information modulation network”.In:ScientificReports 14 (2024), p. 5416. doi: 10.1038/s41598-024-55990-x. url: https://doi.org/10.1038/s41598 024-55990-x. [50] Ajay Kumar, Gagandeep Berar, Manmohan Sharma, et al. “Underwater image enhancement using hybrid transformers and evolutionary particle swarm op timization”. In: Scientific Reports 15 (2025), p. 29575. doi: 10.1038/s41598 025-14439-5. url: https://doi.org/10.1038/s41598-025-14439-5. [51] TongLiu,KaiyanZhu,XinyiWang,etal.“Lightweightunderwaterimageadap tive enhancement based on zero-reference parameter estimation network”. In: Frontiers in Marine Science 11 (2024), p. 1378817. doi: 10.3389/fmars.2024. 1378817. url: https://doi.org/10.3389/fmars.2024.1378817. [52] DazhaoDu,EnhanLi,LingyuSi,etal.UIEDP:UnderwaterImageEnhancement with Diffusion Prior. 2023. doi: 10.48550/ARXIV.2312.06240. url: https: //arxiv.org/abs/2312.06240. | |
| dc.identifier.uri | https://repository.iutoic-dhaka.edu/handle/123456789/2765 | |
| dc.language.iso | en | |
| dc.publisher | Department of Computer Science and Engineering (CSE), Islamic University of Technology (IUT), Board Bazar, Gazipur, Bangladesh. | |
| dc.title | Underwater Image Enhancement Based on Adaptive Color Balance and Contrast Optimization with Minimum Information Loss | |
| dc.type | Thesis |
Files
Original bundle
License bundle
1 - 1 of 1
Loading...
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: