×

zbMATH — the first resource for mathematics

Morphological networks for image de-raining. (English) Zbl 07118262
Couprie, Michel (ed.) et al., Discrete geometry for computer imagery. 21st IAPR international conference, DGCI 2019, Marne-la-Vallée, France, March 26–28, 2019, Proceedings. Cham: Springer (ISBN 978-3-030-14084-7/pbk; 978-3-030-14085-4/ebook). Lecture Notes in Computer Science 11414, 262-275 (2019).
Summary: Mathematical morphological methods have successfully been applied to filter out (emphasize or remove) different structures of an image. However, it is argued that these methods could be suitable for the task only if the type and order of the filter(s) as well as the shape and size of operator kernel are designed properly. Thus the existing filtering operators are problem (instance) specific and are designed by the domain experts. In this work we propose a morphological network that emulates classical morphological filtering consisting of a series of erosion and dilation operators with trainable structuring elements. We evaluate the proposed network for image de-raining task where the SSIM and mean absolute error (MAE) loss corresponding to predicted and ground-truth clean image is back-propagated through the network to train the structuring elements. We observe that a single morphological network can de-rain an image with any arbitrary shaped rain-droplets and achieves similar performance with the contemporary CNNs for this task with a fraction of trainable parameters (network size). The proposed morphological network (MorphoN) is not designed specifically for de-raining and can readily be applied to similar filtering/noise cleaning tasks. The source code can be found here https://github.com/ranjanZ/2D-Morphological-Network.
For the entire collection see [Zbl 1420.68008].
MSC:
68U05 Computer graphics; computational geometry (digital and algorithmic aspects)
Software:
DeepLab; GitHub; MorphoN
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] de A. Araujo, R.: A morphological perceptron with gradient-based learning for Brazilian stock market forecasting. Neural Netw. 28, 61-81 (2012)
[2] Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE TPAMI 40(4), 834-848 (2018)
[3] Davidson, J.L., Hummer, F.: Morphology neural networks: An introduction with applications. Circ. Syst. Sig. Process. 12(2), 177-210 (1993) · Zbl 0783.68136
[4] Fu, X., Huang, J., Ding, X., Liao, Y., Paisley, J.: Clearing the skies: a deep network architecture for single-image rain removal. IEEE TIP 26(6), 2944-2956 (2017) · Zbl 1409.94161
[5] Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning, vol. 1. MIT press, Cambridge (2016) · Zbl 1373.68009
[6] Mondal, R., Santra, S., Chanda, B.: Image dehazing by joint estimation of transmittance and airlight using bi-directional consistency loss minimized FCN. In: CVPR Workshops, pp. 920-928 (2018)
[7] Mondal, R., Santra, S., Chanda, B.: Dense morphological network: an universal function approximator. arxiv e-prints arXiv:1901.00109, January 2019
[8] Perret, B., Cousty, J., Ura, J.C.R., Guimarães, S.J.F.: Evaluation of morphological hierarchies for supervised segmentation. In: Benediktsson, J.A., Chanussot, J., Najman, L., Talbot, H. (eds.) ISMM 2015. LNCS, vol. 9082, pp. 39-50. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18720-4_4 · Zbl 1445.68311
[9] Pessoa, L.F.C., Maragos, P.: Neural networks with hybrid morphological/rank/linear nodes: a unifying framework with applications to handwritten character recognition. Pattern Recogn. 33, 945-960 (2000)
[10] Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91-99 (2015)
[11] Ritter, G.X., Sussner, P.: An introduction to morphological neural networks. In: ICPR, vol. 4, pp. 709-717, August 1996
[12] Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234-241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
[13] Sussner, P.: Morphological perceptron learning. In: ICRA, pp. 477-482 September 1998
[14] Vincent, L.: Morphological grayscale reconstruction in image analysis: applications and efficient algorithms. IEEE TIP 2(2), 176-201 (1993)
[15] Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE TIP 13(4), 600-612 (2004)
[16] Wdowiak, M., Markiewicz, T., Osowski, S., Swiderska, Z., Patera, J., Kozlowski, W.: Hourglass shapes in rank grey-level hit-or-miss transform for membrane segmentation in HER2/neu images. In: Benediktsson, J.A., Chanussot, J., Najman, L., Talbot, H. (eds.) ISMM 2015. LNCS, vol. 9082, pp. 3-14. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18720-4_1 · Zbl 06483282
[17] Zamora, E., Sossa, H.: Dendrite morphological neurons trained by stochastic gradient descent. Neurocomputing 260, 420-431 (2017)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.