IJE TRANSACTIONS B: Applications Vol. 32, No. 2 (February 2019) 249-255    Article in Press

PDF URL: http://www.ije.ir/Vol32/No2/B/10-3009.pdf  
downloaded Downloaded: 45   viewed Viewed: 368

F. Azari Nasrabad, H. Hassanpour and S. Asadi Amiri
( Received: October 27, 2018 – Accepted in Revised Form: January 03, 2019 )

Abstract    The dark channel prior (DCP) technique is an effective method to enhance hazy images. Dark channel is an image with the same size as the hazy image which represents the haze severity in different places of the image. The DCP method suffers from two problems: it is incapable for removing haze from smooth regions, causing blocking effects on these areas; it cannot properly reduce a haze with a non-monotonic behavior. In this paper, an adaptive image dehazing method is proposed based on the DCP method to solve the problem of this method. In this method, to overcome the dark channel deficiency of the blocking effects, the dark channel is initially extracted. The hazy image is subsequently segmented into smooth and non-smooth regions. Regarding the smooth regions, the pixel values in the dark channel are reduced by dividing them with a rather great number. To solve the second problem, depending upon the haze severity, the haze removing technique is applied repeatedly until all the regions of the image are enhanced. Finally, the Gamma correction approach is used for contrast enhancement of the smooth regions. The performed subjective and objective comparison attest the superiority of the proposed method to the DCP one in removing the haze.


Keywords    Dehazing, Image enhancement, Dark channel prior, Segmentation.



روش کانال تاریک یک روش موثر برای بالا بردن کیفیت تصاویر دارای مه است. کانال تاریک، تصویری هم اندازه با تصویر مه آلود است که میزان مه را در قسمت‌‌¬های مختلف تصویر نشان می¬دهد. روش کانال تاریک دارای دو مشکل است: قادر به حذف مه از نواحی هموار نیست و موجب ایجاد اثر بلوکی در این نواحی می¬¬شود. همچنین این روش برای تصاویر دارای مه ناهمگن مناسب نیست. در این مقاله یک روش حذف مه بر اساس روش کانال تاریک پیشنهاد شده است. در این روش برای غلبه بر مشکل اثر بلوکی در نواحی هموار، ابتدا تصویر کانال تاریک استخراج می¬شود. سپس این تصویر به قسمت¬های هموار و غیر هموار تقسیم می-شود. با توجه به نواحی هموار، مقادیر پیکسل¬های متناظر در کانال تاریک با تقسیم بر یک عدد بزرگ کاهش می¬یابد. برای حل مشکل دوم با توجه به میزان مه، ممکن است این روش بارها تکرار شود تا کل تصویر بهبود یابد. در نهایت اصلاح گاما برای بالا بردن کیفیت نواحی هموار به کار می¬رود. مقایسه کمی و کیفی، برتری روش پیشنهادی بر روش کانال تاریک را نشان می¬دهد.


1. Gao, Y., Hu, HM., Wang, S. and Li, B., “A fast image dehazing algorithm based on negative correction”, Elsevier Signal Processing, Vol. 2, (2014), 380-398. 

2. Schechner, Y. Y., Narasimhan, S. G. and Nayar, S. K., “Instant dehazing of images using polarization”, IEEE Computer Vision and Pattern Recognition, Vol. 1, (2001), 325-332.

3. Shwartz, S., Namer, E. and Schechner, Y. Y., “Blind haze separation”, IEEE Computer Vision and Pattern Recognition, Vol. 2, (2006), 1984-1991. 

4. Narasimhan, S. G. and Nayar, S. K., “Chromatic framework for vision in bad weather”, IEEE Computer Vision and Pattern Recognition, Vol. 1, (2000), 598-605. 

5. Nayar, S.K. and Narasimhan, S.G., “vision in bad weather”, IEEE Computer Vision, Vol. 2, (1999), 820-827.

6. Narasimhan, S. G. and Nayar, S. K., “Contrast Restoration of Weather Degraded Images”, IEEE Pattern Analysis and Machine Intelligence, Vol. 25, (2003), 713-724.

7. Kopf, J., Neubert, B., Chen, B. Cohen, M., Cohen, D., Deussen, O., Uyttendaele, M. and Lischinski, D., “Deep photo: model-based photograph enhancement and viewing”, Association for Computing Machinery, Vol.27, (2008), 116. 

8. Narasimhan, S. G. and Nayar, S. K. “Interactive deweathering of an image using physical models”, IEEE Workshop Color and Photometric Methods in Computer Vision, Vol.6, (2003), 1. 

9. Tan, R., “Visibility in bad weather from a single image”, IEEE Computer Vision and Pattern Recognition, Vol. 25, (2008), 1-8.

10. Fattal, R., “Single image dehazing”, Analysis and Machine Intelligence, Vol.27, (2008), 72. 

11. Fan, X. and Luo, z., “Haze editing with natural transmission”, The Visual Computer, Vol. 32, (2016), 137-147.

12. Galdran, A. “Image dehazing by artificial multiple-exposure image fusion”, Signal Processing, Vol. 149, (2018), 135-147.

13. He, K., Sun, J. and Tang, X., “Single image haze removal using dark channel prior”, IEEE Computer Vision and Pattern Recognition, Vol. 33, (2011), 2341-2353.

14. He, K., Sun, J. and Tang, X., “Guided Image Filtering”, Pattern Analysis, Vol.35, (2013), 1397–1409.

15. Li, Z. and Zheng, J., “Single image de-hazing using globally guided image filtering”, IEEE Transactions on Image Processing, Vol. 27, (2018), 442-450.

16. Tarel, J. and Hautiere, N., “Fast visibility restoration from a single color or gray level image”, Computer Vision, Vol.16, (2009), 2201-2208.

17. Hassanpour, H., Azari, F. and Asadi, S., “Improving Dark Channel Prior for Single Image Dehazing”, International Journal of Engineering, Transactions C: Aspects, Vol. 28, No. 6, (2015), 880-887.

18. Bai, L. and Wu, Y., “Real time image haze removal on multi-core DSP”, Procedia Engineering, Vol. 99, (2015), 244-252.

19. Ranota, H. and Kaur, P., “A new single image dehazing approach using modified dark channel prior”, Advances in Intelligent Informatics, Vol. 98, (2015), 77-85.

20. Zeng, Y. and Liu, X., “A multi-scale fusion-based dark channel prior dehazing algorithm”, International Conference on Graphic and Image Processing, Vol. 6, (2014), 94-98.

21. Hung, C., Lin, Y. and Wang, H., “Image haze removal of optimized contrast enhancement based on GPU”, Springer Singapore, Vol. 3, (2016), 53-63.

22. Asadi, S. and Hassanpour, H., “A preprocessing approach for image analysis using gamma correction”, International Journal of Computer Applications, Vol. 38, (2012), 38-46. 

23. Hassanpour, H., Yousefian, H. and Zehtabian, A., “Pixon-based image segmentation in Image Segmentation”, Intech pen Access Publisher, Vol. 2, (2011), 495-515. 

24. Fattal, R., and Raanan, A., “Dehazing using Color-Lines”, http://www.cs.huji.ac.il/~raananf/¬projects/dehaze_cl/results. Accessed  12 August 2016.

25. Carvalho, F., “Fuzzy c-means clustering methods for symbolic interval data”, Pattern Recognition Letters, Vol. 28, (2007), 423-437. 

26. Ma, K., Duanmu, Z., Wu, Q., Wang, Z., Yong, H., Li, H. and Zhang, L., “Waterloo exploration database: New challenges for image quality assessment models”, IEEE Transactions on Image Processing, Vol. 26, (2017), 1004-1016.

27. Hassanpour, H. and Asadi, S., “Image quality enhancement using pixel wise gamma correction”, International Journal of Engineering, Transactions B: Applications, Vol. 24, No. 4, (2011), 301-311. 

Download PDF 

International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir