Abstract
The key challenge for edge detection is that salient edge is difficult to detect due to the complex background. To improve the resolution and accuracy of salient edge effectively, we propose a novel method of edge detection called MSDF (Multi Scale Decode and Fusion) based on deep structured multi-scale features in this paper. The decoding layer of MSDF can fuse the adjacent features of the DNN multi-scale and increase the correlation between the features. In the fusion of different scale’s information, the traditional method of up-sample based on deconvolution is not used and Subpixel [16] algorithm is adopted to improve the resolution of the convolution layer’s output image. We also build a new Conditional Random Fields (CRF) model with CRF-RNN layer to reduce the number of irrelevant features and eliminate the weak correlation information while retaining the important structural attributes. Extensive experiments on BSDS500 [1] dataset and the larger NYUD [17] dataset show that the effectiveness of the proposed model and of the overall hierarchical framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arbelaez, P., Maire, M., Fowlkes, C., Malik, J.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 898–916 (2011)
Dollár, P., Zitnick, C.L.: Fast edge detection using structured forests. IEEE Trans. Pattern Anal. Mach. Intell. 37(8), 1558–1570 (2015)
Hallman, S., Fowlkes, C.C.: Oriented edge forests for boundary detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1732–1740 (2015)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hou, Q., Liu, J., Cheng, M.M., Borji, A., Torr, P.H.: Three birds one stone: a unified framework for salient object segmentation, edge detection and skeleton extraction. arXiv preprint arXiv:1803.09860 (2018)
Kokkinos, I.: Pushing the boundaries of boundary detection using deep learning. arXiv preprint arXiv:1511.07386 (2015)
Lee, C.Y., Xie, S., Gallagher, P., Zhang, Z., Tu, Z.: Deeply-supervised nets. In: Artificial Intelligence and Statistics, pp. 562–570 (2015)
Liao, Y., Fu, S., Lu, X., Zhang, C., Tang, Z.: Deep-learning-based object-level contour detection with CCG and CRF optimization. In: 2017 IEEE International Conference on Multimedia and Expo (ICME), pp. 859–864. IEEE (2017)
Lim, J.J., Zitnick, C.L., Dollár, P.: Sketch tokens: a learned mid-level representation for contour and object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3158–3165 (2013)
Liu, Y., Cheng, M.M., Hu, X., Wang, K., Bai, X.: Richer convolutional features for edge detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5872–5881. IEEE (2017)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101 (2017)
Maninis, K.K., Pont-Tuset, J., Arbeláez, P., Van Gool, L.: Convolutional oriented boundaries: from image segmentation to high-level tasks. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 819–833 (2018)
Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891–898 (2014)
Shen, W., Wang, X., Wang, Y., Bai, X., Zhang, Z.: Deepcontour: a deep convolutional feature learned by positive-sharing loss for contour detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3982–3991 (2015)
Shi, W., et al.: Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1874–1883 (2016)
Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746–760. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33715-4_54
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Wang, Y., Zhao, X., Huang, K.: Deep crisp boundaries. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3892–3900 (2017)
Xie, S., Tu, Z.: Holistically-nested edge detection. Int. J. Comput. Vision 125(1–3), 3–18 (2017)
Xu, D., Ouyang, W., Alameda-Pineda, X., Ricci, E., Wang, X., Sebe, N.: Learning deep structured multi-scale features using attention-gated CRFs for contour prediction. In: Advances in Neural Information Processing Systems, pp. 3961–3970 (2017)
Yang, J., Price, B., Cohen, S., Lee, H., Yang, M.H.: Object contour detection with a fully convolutional encoder-decoder network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 193–202 (2016)
Zheng, S., et al.: Conditional random fields as recurrent neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1529–1537 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Dong, Z., Zhang, R., Shao, X., Li, H., Yang, Z. (2018). Multi-scale Feature Decode and Fuse Model with CRF Layer for Boundary Detection. In: Cheng, L., Leung, A., Ozawa, S. (eds) Neural Information Processing. ICONIP 2018. Lecture Notes in Computer Science(), vol 11302. Springer, Cham. https://doi.org/10.1007/978-3-030-04179-3_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-04179-3_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-04178-6
Online ISBN: 978-3-030-04179-3
eBook Packages: Computer ScienceComputer Science (R0)