SkelGAN: A Font Image Skeletonization Method
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this research, we study the problem of font image skeletonization using an end-to-end deep adversarialnetwork, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies havebeen concerned with skeletonization, but a few have utilized deep learning. Further, no study has consideredgenerative models based on deep neural networks for font character skeletonization, which are more delicatethan natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of fontcharacters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization,in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generatoris proved superior to all well-known mathematical skeletonization methods in terms of character structure,including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominanceof our method against the state-of-the-art supervised image-to-image translation method in font characterskeletonization task.
Abstract
In this research, we study the problem of font image skeletonization using an end-to-end deep adversarialnetwork, in contrast with the state-of-the-art methods that use mathematical algorithms. Several studies havebeen concerned with skeletonization, but a few have utilized deep learning. Further, no study has consideredgenerative models based on deep neural networks for font character skeletonization, which are more delicatethan natural objects. In this work, we take a step closer to producing realistic synthesized skeletons of fontcharacters. We consider using an end-to-end deep adversarial network, SkelGAN, for font-image skeletonization,in contrast with the state-of-the-art methods that use mathematical algorithms. The proposed skeleton generatoris proved superior to all well-known mathematical skeletonization methods in terms of character structure,including delicate strokes, serifs, and even special styles. Experimental results also demonstrate the dominanceof our method against the state-of-the-art supervised image-to-image translation method in font characterskeletonization task.
참고문헌 (31)
- F. Zhao, "Preprocessing and postprocessing for skeleton-based fingerprint minutiae extraction", Pattern Recognition, 40(4), pp.1270~1281 (2007)
- M. P. Sampat, "Detection of spiculated lesions in mammograms", Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No. 03CH37439), pp.810~813 (2003)
- W. Shen, "Skeletonization: Theory, Methods and Applications", pp.259~285 (2017), Academic Press
- N. Li, "An implementation of OCR system based on skeleton matching", Computing Laboratory, University of Kent, ~ (1993)
- X. Bai, "Skeleton filter : A self-symmetric filter for skeletonization in noisy text images", IEEE Transactions on Image Processing, 29, pp.1815~1826 (2019)
- R. Vemulapalli, "Human action recognition by representing 3D skeletons as points in a lie group", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.588~595 (2014)
- C. Shu, "Morphological thinning based on image's edges", Proceedings of the International Conference on Communication Technology (IEEE Cat. No. 98EX243) (1998)
- J. W. Brandt, "Continuous skeleton computation by Voronoi diagram", CVGIP : Image Understanding, 55(3), pp.329~338 (1992)
- G. Borgefors, "Distance transformations in digital images", Computer Vision, Graphics, and Image Processing, 34(3), pp.344~371 (1986)
- P. K. Saha, "A survey on skeletonization algorithms and their applications", Pattern Recognition Letters, 76, pp.3~12 (2016)
- T. Y. Zhang, "A fast parallel algorithm for thinning digital patterns", Communications of the ACM, 27(3), pp.236~239 (1984)
- Z. Guo, "Parallel thinning with two-subiteration algorithms", Communications of the ACM, 32(3), pp.359~373 (1989)
- T. C. Lee, "Building skeleton models via 3-D medial surface axis thinning algorithms", CVGIP : Graphical Models and Image Processing, 56(6), pp.462~478 (1994)
- S. Wei, "Skeleton pruning as trade-off between skeleton simplicity and reconstruction error", Science China Information Sciences, 53, pp.1~14 (2013)
- P. Vincent, "Extracting and composing robust features with denoising autoencoders", Proceedings of the 25th International Conference on Machine Learning, pp.1096~1103 (2008)
- "Auto-encoding variational Bayes" (2014)[URL]
- I. J. Goodfellow, "Generative adversarial networks", Advances in Neural Information Processing System, 27, pp.2672~2680 (2014)
- P. Isola, "Image-to-image translation with conditional adversarial networks", Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.5967~5976 (2017)
- W. P. Choi, "Extraction of the Euclidean skeleton based on a connectivity criterion", Pattern Recognition, 36(3), pp.721~729 (2003)
- W. Shen, "Skeleton growing and pruning with bending potential ratio", Pattern Recognition, 44(2), pp.196~209 (2011)
- Z. Yu, "A segmentation-free approach for skeletonization of gray-scale images via anisotropic vector diffusion", Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.415~420 (2004)
- Q. Zhang, "Accurate centerline detection and line width estimation of thick lines using the radon transform", IEEE Transactions on Image Processing, 16(2), pp.310~316 (2007)
- T. Lindeberg, "Edge detection and ridge detection with automatic scale selection", International Journal of Computer Vision, 30(2), pp.117~156 (1998)
- S. Xie, "Holistically-nested edge detection", Proceedings of the IEEE International Conference on Computer Vision, pp.1395~1403 (2015)
- S. Chen, "DeepSkeleton: learning multi-task scale-associated deep side outputs for object skeleton extraction in natural images", IEEE Transactions on Image Processing, 26(11), pp.5298~5311 (2017)
- J. Long, "Fully convolutional networks for semantic segmentation", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.3431~3440 (2015)
- O. Panichev, "U-Net based convolutional neural network for skeleton extraction", Proceedings of the IEEE, 2019, 1186~1189
- S. Nathan, "Skeletonnet : shape pixel to skeleton pixel", Proceedings of the IEEE, 2019, 1181~1185
- R. Atienza, "Pyramid U-network for skeleton extraction from shape points", Proceedings of the IEEE, 2019, 1177~1180
- W. Tang, "Neural Information Processing", pp.461~472 (2018), Springer
- "The GAN landscape: losses, architectures, regularization, and normalization" (2018)[URL]