Abstract
The skeleton is an important topological description of the object’s geometric form. As an advanced feature, the object skeleton information constitutes an abstract representation of the original shape. Skeleton detection helps further understanding of the object detection and recognition tasks. When processing natural images with complex backgrounds, which often blurred skeleton pixel scale or inaccurate classification. In this paper, we propose a Fusing Multi-scale Residual Network (FMRN) to improve the accuracy of skeleton detection, driven by pre-training the backbone network and adding multi-scale side output in its different stages, we also add the residual module to solve the computational redundancy problem. The atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales and ensure good resolution in feature maps. The experiments were conducted on five open datasets, where the datasets SK-LARGE, SK-SMALL (SK506), and WH-SYMMAX are commonly used for the skeleton detection task. The F-measure score obtained for these three datasets are 0.789, 0.751, and 0.865, respectively. The effectiveness of the method in this paper can be verified by ablation study, and the evaluation protocol are represented by F-measure and P-R curve. The test results showed that our approach has positive extraction accuracy and generalization ability.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Blum, H.: A transformation for extracting new descriptors of shape. Models for the Preception of Speech & Visual Form 19, 362–380 (1967)
Saha, P.K., et al.: A survey on skeletonization algorithms and their applications. Pattern Recognit. Lett. 76, 3–12 (2016)
Zhu, S.C., Yuille, A.L.: FORMS: a flexible object recognition and modelling system. Int. J. Comp. Visi. 20, 187–212 (1995)
Felzenszwalb, P.F., Huttenlocher, D.P.: Pictorial structures for object recognition. Int. J. Comput. Vision 61(1), 55–79 (2005)
Shotton, J., et al.: Real-time human pose recognition in parts from single depth images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1297–1304 (2011)
Zhang, Z., Shen, W., Yao, C., Bai, X.: Symmetry-based text line detection in natural scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2558–2567 (2015)
Widynski, N., et al.: Local symmetry detection in natural images using a particle filtering approach. IEEE Transactions on Image Processing 23, 5309–5322 (2014)
Girshick, R.B., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 580–587 (2014)
Redmon, J., et al.: You Only Look Once: Unified, Real-Time Object Detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2015)
Liu, W., et al.: SSD: Single Shot MultiBox Detector. In: European Conference on Computer Vision (2015)
Shen, W., et al.: Object skeleton detection in natural images by fusing scale-associated deep side outputs. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 222–230 (2016)
Zhao, K., et al.: Hi-Fi: hierarchical feature integration for skeleton detection. In: International Joint Conference on Artificial Intelligence (2018)
Lindeberg, T.: Edge detection and ridge detection with automatic scale selection. Int. J. Comp. Visi. 30, 117–156 (1996)
Liu, T.-L., et al.: Segmenting by seeking the symmetry axis. Proceedings. In: International Conference on Pattern Recognition, vol.2, p. 2, 994–998 (1998)
Jang, J.H., Ki, S.H.: A pseudo-distance map for the segmentation-free skeletonization of gray-scale images. In: IEEE International Conference on Computer Vision, pp. 18–23 (2001)
Postolski, M., et al.: Scale filtered euclidean medial axis and its hierarchy. Comp. Visi. Ima. Underst. 129, 89–102 (2014)
Bai, X., et al.: Skeleton filter: a self-symmetric filter for skeletonization in noisy text images. IEEE Transactions on Image Processing 29, 1815–1826 (2020)
Bai, X., et al.: ProMask: Probability Mask for Skeleton Detection. Neural Networks 162, (2022)
Xie, S., Tu, Z.: Holistically-nested edge detection. Int. J. Comp. Visi. 125, 3–18 (2015)
Liu, Y., et al.: Richer convolutional features for edge detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5872–5881 (2016)
Liu, C., et al.: Adaptive linear span network for object skeleton detection. IEEE Transactions on Image Processing 30, 5096–5108 (2021)
Ke, W., et al.: SRN: side-output residual network for object symmetry detection in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 302–310 (2017)
Liu, C., et al.: RSRN: rich side-output residual network for medial axis detection. In: IEEE International Conference on Computer Vision Workshops, pp. 1739–1743 (2017)
Xu, W., et al.: Geometry-aware end-to-end skeleton detection. British Machine Vision Conference (2019)
Szegedy, C., et al.: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. ArXiv abs/1602.07261 (2016)
Chen, L.,-C., et al.: DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Trans. Pattern Anal. Machi. Intelli. 40, 834–848 (2016)
He, K., et al.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2015)
Wang, Y., et al.: DeepFlux for skeletons in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5282–5291 (2018)
Tsogkas, S., Kokkinos, I.: Learning-based symmetry detection in natural images. In: European Conference on Computer Vision (2012)
Acknowledgement
This work is supported by the National Natural Science Foundation of China (NSFC) under Grant 61962007 and in part by the HET of Guangxi Province of China under Grant 2020JGB238.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Fan, Q., Li, Z., Wang, Z. (2023). Fusing Multi-scale Residual Network for Skeleton Detection. In: Lu, H., et al. Image and Graphics . ICIG 2023. Lecture Notes in Computer Science, vol 14358. Springer, Cham. https://doi.org/10.1007/978-3-031-46314-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-46314-3_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-46313-6
Online ISBN: 978-3-031-46314-3
eBook Packages: Computer ScienceComputer Science (R0)