Abstract

Zayıf aydınlatmalı ortamlarda, kamera tarafından yakalanan görüntü düşük karşıtlığa ve düşük görünürlüğe sahiptir ve bu insanın görsel algısını aşırı derecede etkiler. Buradan hareketle, düşük aydınlıklı görüntülerde sıklıkla karşılaşılan yetersiz aydınlatma ve düşük karşıtlık gibi sorunları gidermek amacıyla, belirginlik-odaklı sanal pozlamaya dayalı bir yöntem önerilmiştir. Önerilen yöntem, düşük aydınlıklı giriş görüntüsünden sanal pozlama fonksiyonuyla çoklu pozlamalı görüntüler üretir. Daha sonra, çoklu pozlamalı görüntüler RGB renk uzayından HSV renk uzayına dönüştürülür. V bileşenine ait belirginlik ve karşıtlık bilgileri temel alınarak oluşturulan ağırlık haritası yardımıyla füzyon işlemi gerçekleştirilir. Füzyon işlemi RGB uzayındaki görüntü için her renk kanalına ayrı ayrı uygulanarak iyileştirilmiş görüntü elde edilir. Yöntemin etkinliğini göstermek amacıyla, Part2 Subset veri seti üzerinde literatürde sıkça kullanılan altı yöntemle kapsamlı bir karşılaştırma yapılmıştır. Nicel sonuçlar, önerilen yöntemin PSNR bakımından en iyi sonucu verdiğini, SSIM bakımından ise rekabetçi düzeyde sonuçlar elde edildiğini ortaya koymaktadır. Görsel sonuçlar, önerilen yöntemin aydınlatma iyileştirmesi, karşıtlık iyileştirmesi ve detay koruma açısından etkin ve dengeli sonuçlar ürettiğini göstermektedir.

References

[1] Shakibania H, Raoufi S, Khotanlou H. CDAN: convolutional dense attention-guided network for low-light image enhancement. Digit Signal Processing 2025;156:104802.

[2] Wang H, Chen Y, Cai Y, Chen L, Li Y, Sotelo MA, et al. SFNet-N: an improved SFNet algorithm for semantic segmentation of low-light autonomous driving road scenes. Transactions on Intelligent Transportation Systems 2022;23(11):21405–17.

[3] Hashmi KA, Kallempudi G, Stricker D, Afzal MZ. FeatEnhancer: enhancing hierarchical features for object detection and beyond under low-light vision. In Proceedings of the IEEE/CVF International Conference on Computer Vision 2023;6725–35.

[4] Fan Y, Wang Y, Liang D, Chen Y, Xie H, Wang FL, et al. Low-FaceNet: face recognition- driven low-light image enhancement IEEE Transactions on Instrumentation and Measurement. 2024.

[5] Kim W. Low-light image enhancement: a comparative review and prospects. IEEE Access 2022;10:84535–57.

[6] Li M, Liu J, Yang W, Sun X, Guo Z. Structure-revealing low-light image enhancement via robust Retinex model. IEEE Transaction on Image Processing 2018;27(6):2828–41.

[7] Ren X, Yang W, Cheng WH, Liu J. LR3M: robust low-light enhancement via low-rank regularized Retinex model. IEEE Transaction on Image Processing 2020;29:5862–76.

[8] Hines G, Rahman ZU, Jobson D, Woodell G. Single-scale Retinex using digital signal processors. . In Global Signal Processing Conference 2005;Paper 1324.

[9] Rahman ZU, Jobson DJ, Woodell GA. Multi-scaleı Retinex for color image enhancement. In Proceedings of 3rd IEEE İnternational Conference on mage Processing 1996;3:1003–6.

[10] Fu X, Zeng D, Huang Y, Zhang XP, Ding X. A weighted variational model for simultaneous reflectance and illumination estimation. . In Proceedings of The IEEE Conference on Computer Vision And Pattern Recognition 2016;2782–90.

[11] Guo X, Li Y, Ling H. LIME: low-light image enhancement via illumination map estimation. IEEE Transaction on Image Processing 2016;26(2):982–93.

[12] Ren X, Li M, Cheng WH, Liu J. Joint enhancement and denoising method via sequential decomposition. . In 2018 IEEE International Symposium on Circuits and Systems (ISCAS) 2018;1–5.

[13] Jobson DJ, Rahman ZU, Woodell GA. Properties and performance of a center/surround Retinex. IEEE Transaction on Image Processing 1997;6(3):451–62.

[14] Wang S, Zheng J, Hu HM, Li B. Naturalness preserved enhancement algorithm for non- uniform illumination images. . IEEE Transaction on Image Processing 2013;22(9):3538–48.

[15] Tao L, Zhu C, Xiang G, Li Y, Jia H, Xie X. LLCNN: a convolutional neural network for low- light image enhancement. Proc IEEE Visual Communication and Image Processing (VCIP) 2017:1–4.

[16] Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, et al. EnlightenGAN: deep light enhancement without paired supervision. IEEE Transaction on Image Processing 2021;30:2340–9.

[17] Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R. Zero-reference deep curve estimation for low-light image enhancement. . In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2020;1780–9.

[18] Cai Y, Bian H, Lin J, Wang H, Timofte R, Zhang Y. Retinexformer: one-stage Retinex-based transformer for low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2023;12504–13.

[19] Guo J, Ma J, García-Fernández ÁF, Zhang Y, Liang H. A survey on image enhancement for low-light images. Heliyon 2023;9(4):e14558.

[20] KS GR, Biswas A, Patel MS, Prasad BP. Deep multi-stage learning for HDR with large object motions. In 2019 IEEE International Conference on Image Processing (ICIP) 2019;4714–8.

[21] Fu X, Zeng D, Huang Y, Liao Y, Ding X, Paisley J. A fusion-based enhancing method for weakly illuminated images. Signal Processing 2016;129:82–96.

[22] Ancuti C, Ancuti CO, Haber T, Bekaert P. Enhancing underwater images and videos by fusion. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2012;81–8.

[23] Wang W, Yan D, Wu X, He W, Chen Z, Yuan X, Li L. Low-light image enhancement based on virtual exposure. Signal Processing: Image Communication 2023;118:117016.

[24] He K, Sun J, Tang X. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence 2012;35(6):1397–409.

[25] Cai J, Gu S, Zhang L. Learning a deep single image contrast enhancer from multi-exposure images. IEEE Transaction on Image Processing 2018;27(4):2049–62.

[26] Wang Z, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE Transaction on Image Processing 2004;13(4):600–12.

[27] Fu X, Zeng D, Huang Y, Zhang XP, Ding X. A weighted variational model for simultaneous reflectance and illumination estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2016;2782–90.

[28] Guo X, Li Y, Ling H. LIME: low-light image enhancement via illumination map estimation. IEEE Transaction on Image Processing 2016;26(2):982–93.

[29] Li M, Liu J, Yang W, Sun X, Guo Z. Structure-revealing low-light image enhancement via robust Retinex model. IEEE Transaction on Image Processing 2018;27(6):2828–41.

[30] Wang R, Zhang Q, Fu CW, Shen X, Zheng WS, Jia J. Underexposed photo enhancement using deep illumination estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2019;6849–57.

[31] Ma L, Ma T, Liu R, Fan X, Luo Z. Toward fast, flexible, and robust low-light image enhancement. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022;5637–46.

[32] Jeon JJ, Park JY, Eom IK. Low-light image enhancement using gamma correction prior in mixed color spaces. Pattern Recognition 2024;146:110001.