Abstract




 
   

IJE TRANSACTIONS C: Aspects Vol. 28, No. 6 (June 2015) 880-887    Article in Press

downloaded Downloaded: 211   viewed Viewed: 2365

  IMPROVING DARK CHANNEL PRIOR FOR SINGLE IMAGE DEHAZING
 
H. Hassanpour, F. Azari and S. Asadi
 
( Received: April 09, 2015 – Accepted: June 11, 2015 )
 
 

Abstract    This paper proposes an improved dark channel prior for removing haze from images. Dark channel prior is an effective method for removing haze. Dark channel is an image in the same size as the hazy image which is obtained by dividing the RGB images into windows and for each window, the minimum of each R, G and B channels are calculated. Then again the minimum of these three values is calculated and is replaced on all pixels in that window. For removing haze from images by dark channel prior, it is necessary to find transmission coefficient of haze and for this, airlight must be estimated. By having these factors, haze-free images can be restored. The dark channel prior method does not yield favorable results for some images, especially for those containing smooth regions. To overcome on this deficiency of the dark channel prior approach, the hazy image is initially segmented into smooth and non-smooth regions in this paper. Then for removing haze from smooth regions, the Gamma correction approach is used for contrast enhancement. Finally, for non-smooth regions, depending to the severity of haze, dark channel prior might be applied several times. The subjective and objective image quality assessments attest superiority of the proposed method compared to dark channel prior in haze removing.

 

Keywords    Dehazing, Image enhancement, Dark channel prior, Segmentation

 

چکیده    در این مقاله یک الگوریتم بهسازی برای رفع مه از تصاویر با استفاده از کانال تاریک پیشنهاد شده است. کانال تاریک یکی از روش­های موثر برای رفع مه از تصویر است. کانال تاریک، تصویری هم­اندازه­ی تصویر دارای مه است که برای به دست آوردن آن، تصاویر رنگی RGBرا به قسمت­هایی تقسیم کرده و در هر قسمت مینیمم هر سه کانال R، G و B به صورت جداگانه محاسبه و دوباره از این سه مقدار مینیمم گرفته می­شود و این مقدار جایگزین کل آن قسمت می­شود. برای رفع مه از تصاویر با استفاده از کانال تاریک، یافتن تابع انتقال مه ضروری است و برای این تابع، نور محیط باید تخمین زده شود. با داشتن این دو عامل، می­توان تصاویر بدون مه را بازیابی کرد. روش­های مبتنی بر کانال تاریک در مورد تمامی تصاویر به خصوص برای نواحی هموار نتایج مطلوبی ندارند. در این مقاله با تقسیم بندی تصویر، نواحی هموار و غیر هموار از هم جدا می­شوند، برای رفع مه از نواحی هموار از روش اصلاح گاما استفاده می­شود تا وضوح این نواحی بالا رود. در نهایت برای نواحی غیر هموار با توجه به میزان مه آنها، از روش کانال تاریک استفاده می­شود. از معیارهای کمی و کیفی برای نشان دادن برتری روش پیشنهادی نسبت به کانال تاریک استفاده شده است.

References   

 

1.     Gao, Y., Hu, H.-M., Wang, S. and Li, B., "A fast image dehazing algorithm based on negative correction", Signal Processing,  Vol. 103, (2014), 380-398.

2.     Schechner, Y.Y., Narasimhan, S.G. and Nayar, S.K., "Instant dehazing of images using polarization", in Computer Vision and Pattern Recognition,. CVPR. Proceedings of the 2001 IEEE Computer Society Conference on, IEEE. Vol. 1, (2001), I-325-I-332.

3.     Shwartz, S., Namer, E. and Schechner, Y.Y., "Blind haze separation", in Computer Vision and Pattern Recognition, IEEE Computer Society Conference on, IEEE. Vol. 2, (2006), 1984-1991.

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

5.     Nayar, S.K. and Narasimhan, S.G., "Vision in bad weather", in Computer Vision,. The Proceedings of the Seventh IEEE International Conference on, IEEE. Vol. 2, (1999), 820-827.

6.     Narasimhan, S.G. and Nayar, S.K., "Contrast restoration of weather degraded images", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 25, No. 6, (2003), 713-724.

7.     Kopf, J., Neubert, B., Chen, B., Cohen, M., Cohen-Or, D., Deussen, O., Uyttendaele, M. and Lischinski, D., "Deep photo: Model-based photograph enhancement and viewing", in ACM Transactions on Graphics (TOG), ACM. Vol. 27, (2008), 116-124.

 8.     Narasimhan, S.G. and Nayar, S.K., "Interactive (DE) weathering of an image using physical models", in IEEE Workshop on Color and Photometric Methods in Computer Vision, France. Vol. 6, (2003), 1.

9.     Tan, R.T., "Visibility in bad weather from a single image", in Computer Vision and Pattern Recognition. CVPR. IEEE Conference on, IEEE. (2008), 1-8.

10.   Fattal, R., "Single image dehazing", in ACM Transactions on Graphics (TOG), ACM. Vol. 27, (2008), 72-82

11.   He, K., Sun, J. and Tang, X., "Single image haze removal using dark channel prior", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 33, No. 12, (2011), 2341-2353.

12.   Levin, A., Lischinski, D. and Weiss, Y., "A closed-form solution to natural image matting", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 30, No. 2, (2008), 228-242.

13.   Hassanpour, H., Zehtabian, A. and Yousefian, H., "Pixon-based image segmentation, INTECH Open Access Publisher,  (2011).

14.   de Carvalho, F.d.A., "Fuzzy c-means clustering methods for symbolic interval data", Pattern Recognition Letters,  Vol. 28, No. 4, (2007), 423-437.

15.   Qi, H., Zheng, D. and Zhao, J., "Human visual system based adaptive digital image watermarking", Signal Processing,  Vol. 88, No. 1, (2008), 174-188.

16.   Hassanpour, H. and Ghadi, A.R., "Image enhancement via reducing impairment effects on image components", International Journal of Engineering-Transactions B: Applications,  Vol. 26, No. 11, (2013), 1267-1274.

17.   Gonzalez, R.C., "Digital image processing, Pearson Education India,  (2009).

18.   Amiri, S.A. and Hassanpour, H., "A preprocessing approach for image analysis using gamma correction", International Journal of Computer Applications,  Vol. 38, No. 12, (2012), 45-56.

19.   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.





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