Su Altı Görüntülerinin CVC Yöntemi Kullanılarak İyileştirilmesi

Year 2023, Volume: 28 Issue: 3, 962 - 972, 29.12.2023

Arda Üstübioğlu Beste Üstübioğlu

https://doi.org/10.53433/yyufbed.1249102

Abstract

Su altı görüntülerinin, sudan geçen ışığın dalga boyuna bağlı olarak seçici zayıflama sonucunda kontrastı ve görünürlüğü oldukça düşük olmaktadır. Bu sebeple ilgili çalışmada sualtı görüntülerinde görüntü kontrastlarını iyileştirmek amacıyla literatürde ilk kez görüntünün parlaklık özelliklerini RGB uzayında değerlendiren Bağlamsal ve Değişken Kontrast (CVC) tabanlı bir yöntem önerilmiştir. Önerilen yöntem kontrastı iyileştirirken aynı zamanda sualtı görüntüsü üzerinde yerel renk düzeltmesi de yapmaktadır. Literatürde bu alandaki yöntemler kanalların global histogramı üzerinde çeşitli yaklaşımlar uygularken, önerilen yöntem HSV uzayında S ve V kanalındaki görüntüleri örtüşmeyen alt bloklara bölerek histogram eşitleme uygulamaktadır. Nitel analiz sonuçlarına bakıldığında, önerilen yöntemin diğer iyileştirme yöntemlerine kıyasla kontrast, renk ve ayrıntı bakımından çok iyi görüntüler ürettiği görülmektedir. Önerilen yöntem ayrıca çıktı görüntülerindeki mavi-yeşil efektini de azaltmaktadır. Nicel analiz olarak ise önerilen yöntem 200 sualtı görüntüsü için diğer çalışmalar arasında en yüksek ortalama entropi (7.86), EME (40.90), EMEE (32.13) ve Sobel (90982) değerini üretmektedir.

Keywords

Bağlamsal ve değişken kontrast, Entropi, Kontrast sınırlı uyarlanabilir histogram eşitleme

Underwater Image Enhancement using CVC Method

Abstract

Contrast and visibility of underwater images become very low as a result of selective attenuation depending on the wavelength of light passing through the water. For this reason, a CVC-based method, which evaluates the brightness properties of the image in RGB space, is proposed for the first time in the literature to improve image contrasts in underwater images. While the proposed method improves the contrast, it also performs local color correction on the underwater image. While the methods in this field in the literature apply various approaches on the global histogram of the channels, the proposed method divides the images in the S and V channels into non-overlapping sub-blocks in the HSV space and applies histogram equalization to them. The qualitative analysis results show that the proposed method produces very good images in terms of contrast, color and detail compared to other enhancement methods. The proposed method also reduces the blue-green effect in the output image. As for quantitative analysis, the proposed method produces the highest mean entropy (7.86), EME (40.90), EMEE (32.13) and Sobel (90982) values among other studies for 200 underwater images.

Keywords

CVC, CLAHE, Entropy

References

• Agaian, S. S., Panetta, K., & Grigoryan, A. M. (2000, January). A new measure of image enhancement. IASTED International Conference on Signal Processing & Communication, Rhodes, Greece.
• Celik, T., & Tjahjadi, T. (2011). Contextual and variational contrast enhancement. IEEE Transactions on Image Processing, 20(12), 3431-3441. doi:10.1109/TIP.2011.2157513
• Chiang, J. Y., & Chen, Y. C. (2011). Underwater image enhancement by wavelength compensation and dehazing. IEEE Transactions on Image Processing, 21(4), 1756-1769. doi:10.1109/TIP.2011.2179666
• Çelebi, A. T., & Ertürk, S. (2012). Visual enhancement of underwater images using empirical mode decomposition. Expert Systems with Applications, 39(1), 800-805.doi:10.1016/j.eswa.2011.07.077
• Eustice, R., Pizarro, O., Singh, H., & Howland, J. (2002, Nisan). UWIT: Underwater image toolbox for optical image processing and mosaicking in MATLAB. In Proceedings of the 2002 International Symposium on Underwater Technology (Cat. No. 02EX556), Tokyo, Japonya. doi:10.1109/UT.2002.1002415
• Garg, D., Garg, N. K., & Kumar, M. (2018). Underwater image enhancement using blending of CLAHE and percentile methodologies. Multimedia Tools and Applications, 77, 26545-26561. doi:10.1007/s11042-018-5878-8
• Ghani, A. S. A., & Isa, N. A. M. (2015a). Enhancement of low quality underwater image through integrated global and local contrast correction. Applied Soft Computing, 37, 332-344. doi:10.1016/j.asoc.2015.08.033
• Ghani, A. S. A., & Isa, N. A. M. (2015b). Underwater image quality enhancement through integrated color model with Rayleigh distribution. Applied Soft Computing, 27, 219-230. doi:10.1016/j.asoc.2014.11.020
• Ghani, A. S. A., & Isa, N. A. M. (2017). Automatic system for improving underwater image contrast and color through recursive adaptive histogram modification. Computers and Electronics in Agriculture, 141, 181-195. doi:10.1016/j.compag.2017.07.021
• Guo, Y., Li, H., & Zhuang, P. (2020). Underwater image enhancement using a multiscale dense generative adversarial network. IEEE Journal of Oceanic Engineering, 45, 862-870. doi:10.1109/JOE.2019.2911447
• Hitam, M. S., Awalludin, E. A., Yussof, W. N. J. H. W., & Bachok, Z. (2013, Ocak). Mixture contrast limited adaptive histogram equalization for underwater image enhancement. International Conference on Computer Applications Technology (ICCAT). Sousse, Tunus. doi:10.1109/ICCAT.2013.6522017
• Iqbal, K., Salam, R. A., Osman, A., & Talib, A. Z. (2007). Underwater image enhancement using an integrated colour model. IAENG International Journal of Computer Science, 34(2).
• Iqbal, K., Odetayo, M., James, A., Salam, R. A., & Talib, A. Z. H. (2010, Ekim). Enhancing the low quality images using unsupervised colour correction method. IEEE International Conference on Systems, Man and Cybernetics, İstanbul.
• Li, C., Guo, J., Guo, C., Cong, R., & Gong, J. (2017a). A hybrid method for underwater image correction. Pattern Recognition Letters, 94, 62-67. doi:10.1016/j.patrec.2017.05.023
• Li, J., Skinner, K., Eustice, R., & Johnson-Roberson, M. (2017b). WaterGAN: Unsupervised generative network to enable real-time color correction of monocular underwater ımages. IEEE Robotics and Automation Letters, 3, 387-394. doi:10.1109/LRA.2017.2730363
• Li, C., Anwar, S., & Porikli, F. (2020). Underwater scene prior inspired deep underwater image and video enhancement. Pattern Recognition, 98, 107038. doi:10.1016/j.patcog.2019.107038
• Ulutas, G., & Ustubioglu, B. (2021). Underwater image enhancement using contrast limited adaptive histogram equalization and layered difference representation. Multimedia Tools and Applications, 80, 15067-15091. doi:10.1007/s11042-020-10426-2
• Sun, B., Mei, Y., Yan, N., & Chen, Y. (2023). UMGAN: Underwater image enhancement network for unpaired image-to-image translation. Journal of Marine Science and Engineering, 11(2), 447. doi:10.3390/jmse11020447
• Wu, J., Huang, H., Qiu, Y., Wu, H., Tian, J., & Liu, J. (2005, July). Remote sensing image fusion based on average gradient of wavelet transform. IEEE International Conference Mechatronics and Automation, Niagara Falls, Kanada.
• Ye, Z. (2009). Objective assessment of nonlinear segmentation approaches to gray level underwater images. International Journal on Graphics, Vision, and Image Processing (GVIP), 9(2), 39-46.
• Zhang, Y., Chen, D., Zhang, Y., Shen, M., & Zhao, W. (2023). A two-stage network based on transformer and physical model for single underwater image enhancement. Journal of Marine Science and Engineering, 11(4), 787. doi:10.3390/jmse11040787