Abstract
The paper proposes an efficient method of removing haze from outdoor images using dark channel prior (DCP) method. The DCP represents the statistics of outdoor images. In dark channel images, minimum of one-color channel of haze-free images from outdoor locations has pixels having very low intensity. Therefore, using imaging model of dark channel prior (DCP), we can identify the quantity of haze in an image. Moreover, the transmission map estimation and refinement using guided filter are done after the application of DCP which improves the transmission map of the image. The comparative values of PSNR and RMSE are identified for images of the transmission map obtained from DCP image and are found to have minimum value for the guided filter. The results based on the proposed method are demonstrated for generating DCP, transmission map estimation, refinement, and recovery of radiance of images. It is imperative to say that this method succeeded in its aim to transform haze images into haze-free images with high-intensity pixel values.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
He, K., et al.: Single image haze removal using dark channel prior. IEEE Tran. Patt. Ana. Mach. Intell. 33(12), 2341–2353 (2011)
Kim, J.Y., et al.: An advanced contrast enhancement using partially overlapped sub-block histogram equalization. IEEE Tran. Cir. Sys. Vid. Tech. 11(4), 475–484 (2001)
Tan, R.T.: Visibility in bad weather from a single image. In: Proc. IEEE Conf. Comp. Vis. Patt. Recog.(CVPR), pp. 1–8 (2008)
Fattal, R.: Single image dehazing. ACM Trans. G. (TOG) 27(3), art. 72 (2008)
Wang,Y., et al.: Improved single image dehazing using dark channel prior. In: IEEE Intl. Conf. Intell. Comp. Intell. Sys. (ICIS), vol. 2, pp. 789–792 (2010)
Chen, B.H., et al.: An advanced visibility restoration algorithm for single hazy image. ACM Trans. Mult. Comp., Comm., Appll. 11(4), art.53.(2015). https://doi.org/10.1145/2726947
Azari, F., et al.: Adaptive image dehazing via improving dark channel prior. Intl. J. Eng. 32(22), 49–55 (2019)
Hassanpour, H., et al.: Improving dark channel prior for single image Dehazing. Intl. J. of Eng., Trans. C: Aspect. 28(6), 880–887 (2015)
Huang, D.A., et al.: Self-learning based image decomposition with applications to single image de-noising. IEEE Trans. Mult. 16(1), 83–93 (2014)
Qin, B., et al.: Fast single image dehazing with domain transformation-based edge-preserving filter weighted quad tree subdivision. In: IEEE Intl. Conf. Image Process, pp. 4233–4237 (2015)
Tarel, J.P., et al.: Fast visibility restoration from a single color or gray level image. In: IEEE 12th Intl. Conf. on Comp. Vision, pp. 2201–2208 (2009)
Lee, S., et al.: A review on dark channel prior based image dehazing algorithms. EURASIP J. Image Video Proc. Art. 4 (2016)
He, K., et al.: Guided image filtering. Comp. Vision–ECCV 2010. Springe,r Berlin Heidelberg, pp. 1–14 (2010)
Pizer, S.M., et al.: Adaptive histogram equalization and its variations. Comp. Vision, Graph. Image Proc. 39(3), 355–368 (1987)
Stark, J.A.: Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Trans. Image Proc. 9(5), 889–896 (2000)
Shan, Z, Q., et al.: Fast image/video up-sampling. ACM Trans. on Graph. 27(5), art. 153. (2008)
Wu, X., et al.: Low bit-rate image compression via adaptive down-sampling and constrained least squares up-conversion. IEEE Trans. Image Proc. 18(3), 552–561 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Singh, R., Dubey, A.K., Kapoor, R. (2021). Improved Transmission Map for Dehazing of Natural Images. In: Hassanien, A.E., Bhattacharyya, S., Chakrabati, S., Bhattacharya, A., Dutta, S. (eds) Emerging Technologies in Data Mining and Information Security. Advances in Intelligent Systems and Computing, vol 1286. Springer, Singapore. https://doi.org/10.1007/978-981-15-9927-9_34
Download citation
DOI: https://doi.org/10.1007/978-981-15-9927-9_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9926-2
Online ISBN: 978-981-15-9927-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)