人像抠图无监督语义精修算法
Unsupervised Semantic Human Matting Refinement
DOI: 10.12677/CSA.2021.111015, PDF,   
作者: 曾广荣, 程良伦, 卢 增：广东工业大学，广东 广州
关键词: 人像抠图；深度学习；语义精修；Human Matting； Deep Learning； Semantic Refinement
摘要: 针对当前不使用三分图作为先验知识的人像抠图算法在远景人像抠图任务中存在多余的干扰信息、人像边缘轮廓粗糙、人体携带物品易与背景混淆等问题，提出了人像抠图无监督语义精修算法。该算法由人像边框感知模块与无监督语义精修模块组成。人像边框感知模块首先使用了行人检测模型识别出所有人像，并结合边框感知算法来去除多余的干扰信息。无监督语义精修模块利用了无监督语义分割模型提取特征，然后使用语义精修算法进行人像轮廓的修复。实验表明，在自制的远景人像数据集中，使用主流的人像抠图算法作为基线，并加入人像抠图无监督语义精修算法后，效果得到了明显的提高，人体携带物品也能精准识别，人像轮廓也更加清晰。同时在半身人像数据集中，效果也有一定的提升，表明了该算法也具有泛用性。
Abstract: Aiming at the problems of human matting algorithm, which does not use trimap as a prior knowledge, such as redundant interference information, rough portrait edge contour, and easy confusion between objects carried by human body and the background, an unsupervised semantic matting algorithm for human matting is proposed. The algorithm is composed of human border sensing module and unsupervised semantic refinement module. The portraits border sensing module firstly uses the pedestrian detection model to identify all the portraits, and combines the border sensing algorithm to remove the redundant interference information. Unsupervised semantic refinement module uses unsupervised semantic segmentation model to extract features, and then uses semantic refinement algorithm to repair the portrait contour. Experiments show that in the self-made longterm portrait data set, the mainstream portrait matting algorithm is used as the baseline, and the unsupervised semantic refinement algorithm for portrait matting is added. The effect is significantly improved, and the objects carried by the human body can also be accurately identified. The outline is also clearer. At the same time, in the portrait data set, the effect is also improved to some extent, indicating that the algorithm is also generalized.
文章引用：曾广荣, 程良伦, 卢增. 人像抠图无监督语义精修算法[J]. 计算机科学与应用, 2021, 11(1): 133-142. https://doi.org/10.12677/CSA.2021.111015

参考文献

[1] Wu, X., Fang, X.N., Chen, T., et al. (2020) JMNet: A Joint Matting Network for Automatic Human Matting. Computa-tion Visual Media, 6, 215-224. [Google Scholar] [CrossRef] 
[2] Badrinarayanan, V., Kendall, A. and Cipolla, R. (2019) SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 2481-2495. [Google Scholar] [CrossRef] 
[3] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolu-tional Networks for Semantic Segmentation. Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, 7-12 June 2015, 3431-3440. [Google Scholar] [CrossRef] 
[4] Aksoy, Y., Aydın, T.O. and Pollefeys, M. (2017) Designing Effective Inter-Pixel Information Flow for Natural Image Matting. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 29-37. [Google Scholar] [CrossRef] 
[5] Chen, Q.F., et al. (2013) KNN Matting. IEEE Transactions on Pattern Analysis & Machine Intelligence, 35, 2175-2188. [Google Scholar] [CrossRef] 
[6] Cai, S., Zhang, X., Fan, H., et al. (2019) Disentangled Image Matting. The IEEE International Conference on Computer Vision, Seoul, 27-28 October 2019, 8818-8827. [Google Scholar] [CrossRef] 
[7] Shen, X., Tao, X., Gao, H., et al. (2016) Deep Automatic Portrait Matting. European Conference on Computer Vision, Amsterdam, 8-16 October 2016, 92-107. [Google Scholar] [CrossRef] 
[8] Cho, D., Tai, Y.W. and Kweon, I. (2016) Natural Im-age Matting Using Deep Convolutional Neural Networks. The European Conference on Computer Vision, Amsterdam, 8-16 October 2016, 626-643. [Google Scholar] [CrossRef] 
[9] Levin, A. (2006) A Closed Form Solution to Natural Image Matting. Proceedings of 2006 IEEE Conference on Computer Vision and Pattern Recognition, New York, 17-22 June 2006, 228-242. [Google Scholar] [CrossRef] 
[10] Ning, X., Price, B., Cohen, S. and Huang, T. (2017) Deep Image Matting. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 2970-2979.
[11] Lutz, S., Amplianitis, K. and Smolic, A. (2018) AlphaGAN: Generative Adversarial Networks for Natural Image Matting. British Machine Vision Conference, Newcastle, 3-6 September 2018, 259.
[12] Chen, Q., Ge, T., Xu, Y., et al. (2018) Semantic Human Matting. 2018 ACM Multimedia Conference, Seoul, 22-26 October 2018, 618-626. [Google Scholar] [CrossRef] 
[13] Liu, J., Yao, Y., Hou, W., et al. (2020) Boosting Semantic Human Matting with Coarse Annotations. Proceedings of 2020 IEEE Conference on Computer Vision and Pattern Recognition, Seattle, 14-19 June 2020, 8560-8569. [Google Scholar] [CrossRef] 
[14] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incre-mental Improvement.
[15] Kanezaki, A. (2018) Unsupervised Image Segmentation by Backpropagation. IEEE Interna-tional Conference on Acoustics, Calgary, 15-20 April 2018, 1543-1547. [Google Scholar] [CrossRef] 
[16] Kingma, D.P. and Jimmy, B. (2014) Adam: A Method for Stochastic Optimization.
[17] Felzenszwalb, P.F. and Huttenlocher, D.P. (2004) Efficient Graph-Based Image Segmen-tation. International Journal of Computer Vision, 59, 167-181. [Google Scholar] [CrossRef] 
[18] Achanta, R., Shaji, A., Smith, K., et al. (2012) SLIC Superpixels Compared to State-of-the-Art Superpixel Methods. IEEE Transactions on Pattern Analysis & Machine Intel-ligence, 34, 2274-2282. [Google Scholar] [CrossRef]