Skip to content
BY 4.0 license Open Access Published by De Gruyter Open Access September 11, 2020

Image Restoration by Learning Morphological Opening-Closing Network

  • Ranjan Mondal EMAIL logo , Moni Shankar Dey and Bhabatosh Chanda

Abstract

Mathematical morphology is a powerful tool for image processing tasks. The main difficulty in designing mathematical morphological algorithm is deciding the order of operators/filters and the corresponding structuring elements (SEs). In this work, we develop morphological network composed of alternate sequences of dilation and erosion layers, which depending on learned SEs, may form opening or closing layers. These layers in the right order along with linear combination (of their outputs) are useful in extracting image features and processing them. Structuring elements in the network are learned by back-propagation method guided by minimization of the loss function. Efficacy of the proposed network is established by applying it to two interesting image restoration problems, namely de-raining and de-hazing. Results are comparable to that of many state-of-the-art algorithms for most of the images. It is also worth mentioning that the number of network parameters to handle is much less than that of popular convolutional neural network for similar tasks. The source code can be found here https://github.com/ranjanZ/Mophological-Opening-Closing-Net

MSC 2010: 68T07; 68T45; 68U10

References

[1] Codruta O Ancuti, Cosmin Ancuti, Radu Timofte, and Christophe De Vleeschouwer. O-haze: a dehazing benchmark with real hazy and haze-free outdoor images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 754–762, 2018.10.1109/CVPRW.2018.00119Search in Google Scholar

[2] Cosmin Ancuti, Codruta O Ancuti, and Christophe De Vleeschouwer. D-hazy: A dataset to evaluate quantitatively dehazing algorithms. In 2016 IEEE International Conference on Image Processing (ICIP), pages 2226–2230. IEEE, 2016.10.1109/ICIP.2016.7532754Search in Google Scholar

[3] Cosmin Ancuti, Codruta O Ancuti, Radu Timofte, Luc Van Gool, Lei Zhang, Ming-Hsuan Yang, Vishal M Patel, He Zhang, Vishwanath A Sindagi, Ruhao Zhao, et al. Ntire 2018 challenge on image dehazing: Methods and results. In CVPR Workshops, volume 1, 2018.10.1109/CVPRW.2018.00134Search in Google Scholar

[4] Jesus Angulo. A mathematical morphology approach to cell shape analysis. In Progress in Industrial Mathematics at ECMI 2006, pages 543–547. Springer, 2008.10.1007/978-3-540-71992-2_87Search in Google Scholar

[5] Amy Bearman, Olga Russakovsky, Vittorio Ferrari, and Li Fei-Fei. What’s the point: Semantic segmentation with point supervision. In European conference on computer vision, pages 549–565. Springer, 2016.10.1007/978-3-319-46478-7_34Search in Google Scholar

[6] D. Berman, T. Treibitz, and S. Avidan. Non-local Image Dehazing. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1674–1682, June 2016. 10.1109/CVPR.2016.185.10.1109/CVPR.2016.185Search in Google Scholar

[7] Alan C Bovik. Handbook of image and video processing. 2005.10.1201/9781420027822.ch14Search in Google Scholar

[8] Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, and Dacheng Tao. Dehazenet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 25(11):5187–5198, 2016.Search in Google Scholar

[9] Nick Efford. Digital image processing: a practical introduction using java (with CD-ROM). Addison-Wesley Longman Publishing Co., Inc., 2000.Search in Google Scholar

[10] Raanan Fattal. Dehazing using color-lines. ACM transactions on graphics (TOG), 34(1):13, 2014.10.1145/2651362Search in Google Scholar

[11] Raanan Fattal. Dehazing Using Color-Lines. ACM Trans. Graph., 34(1):13:1–13:14, December 2014. ISSN 0730-0301. 10.1145/2651362. URL http://doi.acm.org/10.1145/2651362.10.1145/2651362Search in Google Scholar

[12] Richard J Feehs and Gonzalo R Arce. Multidimensional morphological edge detection. In Visual Communications and Image Processing II, volume 845, pages 285–292. International Society for Optics and Photonics, 1987.10.1117/12.976517Search in Google Scholar

[13] Gianni Franchi, Amin Fehri, and Angela Yao. Deep morphological networks. Pattern Recognition, page 107246, 2020.10.1016/j.patcog.2020.107246Search in Google Scholar

[14] Xueyang Fu, Jiabin Huang, Xinghao Ding, Yinghao Liao, and John Paisley. Clearing the skies: A deep network architecture for single-image rain removal. IEEE TIP, 26(6):2944–2956, 2017.Search in Google Scholar

[15] Xueyang Fu, Jiabin Huang, Delu Zeng, Yue Huang, Xinghao Ding, and John Paisley. Removing rain from single images via a deep detail network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3855–3863, 2017.Search in Google Scholar

[16] Ross Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448, 2015.10.1109/ICCV.2015.169Search in Google Scholar

[17] Xavier Glorot and Yoshua Bengio. Understanding the diflculty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics, pages 249–256, 2010.Search in Google Scholar

[18] Kaiming He, Jian Sun, and Xiaoou Tang. Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence, 33(12):2341–2353, 2010.10.1109/TPAMI.2010.168Search in Google Scholar PubMed

[19] Kaiming He, Jian Sun, and Xiaoou Tang. Single Image Haze Removal Using Dark Channel Prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2341–2353, December 2011. ISSN 0162-8828. 10.1109/TPAMI.2010.168.10.1109/TPAMI.2010.168Search in Google Scholar

[20] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.Search in Google Scholar

[21] HJAM Heijmans, Michael Buckley, and Hugues Talbot. Path-based morphological openings. In 2004 International Conference on Image Processing, 2004. ICIP’04., volume 5, pages 3085–3088. IEEE, 2004.Search in Google Scholar

[22] Harald Koschmieder. Theorie der horizontalen sichtweite. Beitrage zur Physik der freien Atmosphare, pages 33–53, 1924.Search in Google Scholar

[23] Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, and Dan Feng. Aod-net: All-in-one dehazing network. In Proceedings of the IEEE International Conference on Computer Vision, pages 4770–4778, 2017.Search in Google Scholar

[24] Boyi Li, Xiulian Peng, Zhangyang Wang, Jizheng Xu, and Dan Feng. AOD-Net: All-In-One Dehazing Network. In Proceedings of the IEEE International Conference on Computer Vision, pages 4770–4778, 2017.Search in Google Scholar

[25] Yu Li, Robby T Tan, Xiaojie Guo, Jiangbo Lu, and Michael S Brown. Rain streak removal using layer priors. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2736–2744, 2016.10.1109/CVPR.2016.299Search in Google Scholar

[26] Yu Luo, Yong Xu, and Hui Ji. Removing rain from a single image via discriminative sparse coding. In Proceedings of the IEEE International Conference on Computer Vision, pages 3397–3405, 2015.10.1109/ICCV.2015.388Search in Google Scholar

[27] Gili Mendel. Optical character recognition using morphological attributes. 1993.Search in Google Scholar

[28] Gaofeng Meng, Ying Wang, Jiangyong Duan, Shiming Xiang, and Chunhong Pan. Eflcient image dehazing with boundary constraint and contextual regularization. In Proceedings of the IEEE international conference on computer vision, pages 617–624, 2013.10.1109/ICCV.2013.82Search in Google Scholar

[29] Ranjan Mondal, Sanchayan Santra, and Bhabatosh Chanda. Image dehazing by joint estimation of transmittance and airlight using bi-directional consistency loss minimized fcn. In CVPR Workshops, pages 920–928, 2018.10.1109/CVPRW.2018.00137Search in Google Scholar

[30] Ranjan Mondal, Deepayan Chakraborty, and Bhabatosh Chanda. Learning 2d morphological network for old document image binarization. In 2019 International Conference on Document Analysis and Recognition (ICDAR), pages 65–70. IEEE, 2019.10.1109/ICDAR.2019.00020Search in Google Scholar

[31] Ranjan Mondal, Pulak Purkait, Sanchayan Santra, and Bhabatosh Chanda. Morphological networks for image de-raining. In International Conference on Discrete Geometry for Computer Imagery, pages 262–275. Springer, 2019.10.1007/978-3-030-14085-4_21Search in Google Scholar

[32] Ranjan Mondal, Sanchayan Santra, and Bhabatosh Chanda. Dense Morphological Network: An Universal Function Approximator. arXiv e-prints, art. arXiv:1901.00109, January 2019.Search in Google Scholar

[33] Susanta Mukhopadhyay and Bhabatosh Chanda. A multiscale morphological approach to local contrast enhancement. Signal Processing, 80(4):685–696, 2000.10.1016/S0165-1684(99)00161-9Search in Google Scholar

[34] Hyeonwoo Noh, Seunghoon Hong, and Bohyung Han. Learning deconvolution network for semantic segmentation. In Proceedings of the IEEE international conference on computer vision, pages 1520–1528, 2015.Search in Google Scholar

[35] Bryan A Plummer, Liwei Wang, Chris M Cervantes, Juan C Caicedo, Julia Hockenmaier, and Svetlana Lazebnik. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In Proceedings of the IEEE international conference on computer vision, pages 2641–2649, 2015.10.1109/ICCV.2015.303Search in Google Scholar

[36] Kendall Preston Jr and Michael JB Duff. Modern cellular automata: theory and applications. Springer Science & Business Media, 2013.Search in Google Scholar

[37] Joseph Redmon and Ali Farhadi. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.Search in Google Scholar

[38] Wenqi Ren, Si Liu, Hua Zhang, Jinshan Pan, Xiaochun Cao, and Ming-Hsuan Yang. Single image dehazing via multi-scale convolutional neural networks. In European conference on computer vision, pages 154–169. Springer, 2016.10.1007/978-3-319-46475-6_10Search in Google Scholar

[39] Wenqi Ren, Si Liu, Hua Zhang, Jinshan Pan, Xiaochun Cao, and Ming-Hsuan Yang. Single Image Dehazing via Multi-scale Convolutional Neural Networks. In Computer Vision - ECCV 2016, Lecture Notes in Computer Science, pages 154–169. Springer, Cham, October 2016. 10.1007/978-3-319-46475-6_10.10.1007/978-3-319-46475-6_10Search in Google Scholar

[40] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015.10.1007/978-3-319-24574-4_28Search in Google Scholar

[41] A Rosenfeld. Ac kak digital picture processing vol. 2, 1982.Search in Google Scholar

[42] Dan Schonfeld and John Goutsias. Optimal morphological pattern restoration from noisy binary images. IEEE Transactions on Pattern Analysis & Machine Intelligence, (1):14–29, 1991.10.1109/34.67627Search in Google Scholar

[43] Stanley R Sternberg. Grayscale morphology. Computer vision, graphics, and image processing, 35(3):333–355, 1986.10.1016/0734-189X(86)90004-6Search in Google Scholar

[44] Ketan Tang, Jianchao Yang, and Jue Wang. Investigating haze-relevant features in a learning framework for image dehazing. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2995–3000, 2014.10.1109/CVPR.2014.383Search in Google Scholar

[45] Luc Vincent. Morphological area openings and closings for grey-scale images. In Shape in Picture, pages 197–208. Springer, 1994.10.1007/978-3-662-03039-4_13Search in Google Scholar

[46] Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE TIP, 13(4):600–612, 2004.Search in Google Scholar

[47] He Zhang and Vishal M Patel. Densely connected pyramid dehazing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3194–3203, 2018.10.1109/CVPR.2018.00337Search in Google Scholar

[48] He Zhang, Vishwanath Sindagi, and Vishal M Patel. Multi-scale single image dehazing using perceptual pyramid deep network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pages 902–911, 2018.10.1109/CVPRW.2018.00135Search in Google Scholar

[49] Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, and Lei Zhang. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing, 26(7):3142–3155, 2017.Search in Google Scholar

[50] Kai Zhang, Wangmeng Zuo, and Lei Zhang. Ffdnet: Toward a fast and flexible solution for cnn-based image denoising. IEEE Transactions on Image Processing, 27(9):4608–4622, 2018.Search in Google Scholar

[51] Qingsong Zhu, Jiaming Mai, and Ling Shao. A fast single image haze removal algorithm using color attenuation prior. IEEE transactions on image processing, 24(11):3522–3533, 2015.10.1109/TIP.2015.2446191Search in Google Scholar PubMed

Received: 2019-09-12
Accepted: 2020-08-06
Published Online: 2020-09-11

© 2020 Ranjan Mondal et al., published by De Gruyter

This work is licensed under the Creative Commons Attribution 4.0 International License.

Downloaded on 27.9.2023 from https://www.degruyter.com/document/doi/10.1515/mathm-2020-0103/html
Scroll to top button