Abstract
Recently, researches on clothing segmentation and style recognition in still images have made a big breakthrough. Clothing parsing, as the basis of the above researches, has also made great progress. Unfortunately, it still tends to over-segmentation and poor accuracy when parsing the clothing with complex texture. To address this issue, we consider improving both graph-based image segmentation method and pixel labeling method. For image segmentation, we attempt to reduce the over-segmentation by taking image cells instead of pixels as vertices of the graph, and expanding the range for finding out adjacent vertices. Furthermore, we calculate the weight of edges using different features such as color and texture. For pixel labeling, we train a pairwise CRF model based on multi-level features of the pixel and the region, rather than relying on the human pose. We demonstrate the effectiveness of our approach on Fashionista dataset, which greatly reduce the over-segmentation and scattered pixel labeling of the clothing with complex texture.
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
Sun, G.L., Wu, X., Chen, H.H., et al.: Clothing style recognition using fashion attribute detection. In: International Conference on Mobile Multimedia Communications. ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering), pp. 145–148 (2015)
Surakarin, W., Chongstitvatana, P.: Classification of clothing with weighted SURF and local binary patterns. In: Computer Science and Engineering Conference, pp. 1–4. IEEE (2015)
Bourdev, L., Maji, S., Malik, J.: Describing people: a poselet-based approach to attribute classification. In: IEEE International Conference on Computer Vision, ICCV 2011, Barcelona, Spain, November, pp. 1543–1550. DBLP (2011)
Guan, P., Freifeld, O., Black, M.J.: A 2D human body model dressed in Eigen clothing. In: Proceedings of the European Conference on Computer Vision, ECCV 2010, Heraklion, Crete, Greece, 5–11 September 2010, pp. 285–298. DBLP (2010)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Yamaguchi, K., Kiapour, M.H., Ortiz, L.E., et al.: Parsing clothing in fashion photographs. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3570–3577. IEEE (2012)
Yamaguchi, K., Kiapour, M.H., Berg, T.L.: Paper Doll Parsing: retrieving similar styles to parse clothing items. In: IEEE International Conference on Computer Vision, pp. 3519–3526. IEEE Computer Society (2013)
Simo-Serra, E., Fidler, S., Moreno-Noguer, F., Urtasun, R.: A high performance CRF model for clothes parsing. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9005, pp. 64–81. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16811-1_5
Borràs, A., Tous, F., Lladós, J., et al.: High-level clothes description based on colour-texture and structural features. In: Proceedings of the First Iberian Conference on Pattern Recognition and Image Analysis, IbPRIA 2003, Puerto de Andratx, Mallorca, Spain, 4–6 June 2003, pp. 108–116. DBLP (2003)
Zhang, M., Alhajj, R.: Improving the graph-based image segmentation method. In: IEEE International Conference on TOOLS with Artificial Intelligence, pp. 617–624. IEEE (2006)
Liu, Z., Hu, D.W., Shen, H., et al.: Graph-based image segmentation using directional nearest neighbor graph. Sci. China Inf. Sci. 56(11), 1–10 (2013)
He, X., Zemel, R.S.: Multiscale conditional random fields for image labeling. In: Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004, vol. 2, pp. II-695–II-702. IEEE (2004)
Gould, S., Rodgers, J., Cohen, D., et al.: Multi-class segmentation with relative location prior. Int. J. Comput. Vis. 80(3), 300–316 (2008)
Kohli, P., Ladický, L., Torr, P.H.S.: Robust higher order potentials for enforcing label consistency. Int. J. Comput. Vis. 82(3), 302–324 (2009)
Delong, A., Osokin, A., Isack, H.N., et al.: Fast approximate energy minimization with label costs. Comput. Vis. Patt. Recogn. 96, 2173–2180 (2012). IEEE
Wang, X., Zhang, L., Lin, L., et al.: Deep joint task learning for generic object extraction. Comput. Sci., 523–531 (2015)
Acknowledgement
This work was supported in part by the National Natural Science Foundation of China under Grant Nos. 61672273.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Ji, J., Yang, R. (2018). An Improved Clothing Parsing Method Emphasizing the Clothing with Complex Texture. In: Zeng, B., Huang, Q., El Saddik, A., Li, H., Jiang, S., Fan, X. (eds) Advances in Multimedia Information Processing – PCM 2017. PCM 2017. Lecture Notes in Computer Science(), vol 10735. Springer, Cham. https://doi.org/10.1007/978-3-319-77380-3_46
Download citation
DOI: https://doi.org/10.1007/978-3-319-77380-3_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77379-7
Online ISBN: 978-3-319-77380-3
eBook Packages: Computer ScienceComputer Science (R0)