浏览全部资源
扫码关注微信
收稿：2018-08-22，
修回：2018-10-14，
纸质出版：2019-04-16
移动端阅览
目的
2
少数民族服装色彩及样式种类繁多等因素导致少数民族服装图像识别率较低。以云南少数民族服装为例，提出一种结合人体检测和多任务学习的少数民族服装识别方法。
方法
2
首先通过
$$k$$
-poselets对输入的待识别图像和少数民族服装图像集中的训练图像进行人体整体和局部检测以及关键点的预测；其次，根据检测结果，从待识别图像和训练图像中分别提取颜色直方图、HOG（histogram of oriented gradient）、LBP（local binary pattern）、SIFT（scale invariant feature transform）以及边缘算子5种底层特征；然后，将自定义的少数民族服装语义属性与提取的底层特征进行匹配，采用多任务学习训练分类器模型，以学习少数民族服装的不同风格；最后实现少数民族服装图像的识别并输出识别结果。另外，由于目前缺少大型的少数民族服装数据集，本文构建了一个云南少数民族服装图像集。
结果
2
在构建的云南少数民族服装图像集上验证了本文方法，识别精度达到82.5%~88.4%，并与单任务学习方法进行比较，本文方法识别率更高。
结论
2
针对现有的少数民族服装识别率较低的问题，提出一种结合人体检测和多任务学习的少数民族服装识别方法，提高了少数民族服装图像识别的准确率和效率，同时能较好地满足实际应用需求。
Objective
2
In view of the increasing number and diversity of minority clothing in the domains of multimedia
digital clothing
graphics
and images
understanding and recognizing minority clothing images automatically is essential. However
most previous works have used low-level features directly for classification and recognition
there by lacking local feature analysis and semantic annotation of clothing. The diversity of clothing colors and styles results in low recognition accuracy of minority clothing. Therefore
a minority clothing recognition method based on human detection and multitask learning was proposed for Yunnan minority clothing.
Method
2
The main idea of this work is to propose the
$$k$$
-poselets detection method to detect minority clothing image and define the semantic attributes of the low-level features of minority clothing matching. Moreover
the multi-task learning method is also applied to improve the accuracy of recognition of minority clothing images. First
the
$$k$$
-poselets approach was used to perform global and local human detection and key point predictions using a minority clothing dataset. Second
five types of low-level feature
including color histogram
HOG (histogram of oriented gradient)
LBP(local binary pattern)
SIFT(scale invariant feature transform)
and edge
of the identifying and training image were extracted. Then
semantic attributes were defined to match the five low-level features
and a multitask learning classifier model was trained to obtain different styles of minority clothing. Finally
the recognition results of minority clothing were realized and outputted. Given the lack of minority clothing dataset
we also constructed a minority clothing dataset of Yunnan
including 25 minority clothing
which were collected mainly from online stores including Taobao
Tmall
Jingdong
and other platforms. Each ethnic group had 1 000 maps with a total of 25 000 images. The size of each image was set to 500×500 pixels
and different ethnic groups were classified and numbered. The background of the image was appropriately processed using.jpg format.
Result
2
The proposed method is validated on the dataset of Yunnan minority clothing. Results show that the human detection method not only achieves greater precise recall rate but also remarkably outperforms the DPM and the traditional poselet detection in the task of human prediction. At the same time
in comparison with the current detection method that uses the features extracted by the convolutional neural network
the experimental results are acceptable and demonstrate the effectiveness of the proposed approach. Moreover
the recognition accuracy of minority clothing images can reach 82.5%~88.4%. The proposed method has higher recognition rate than the single-task learning method.
Conclusion
2
Faced with a wide variety of colors and styles of minority clothing
the recognition rate of minority clothing is low. Thus
a minority clothing identification method based on human detection and multitask learning is proposed to improve the accuracy and efficiency of minority clothing image recognition for excellent practical applications. The research results can be used for the digital analysis
understanding
and identification of Chinese minority clothing
as well as provide an effective digital tool for recording
inheriting
and protecting the national culture and promote the development of tourism
economy
and culture in ethnic areas. Although the method has certain limitations
it can provide a clear direction for future research. We only consider major attributes and limited set of training images for detection
feature extraction
and classification. The diversity of human posture and occlusion issue can affect the recognition accuracy of minority clothing images. Furthermore
our current work focuses on the dataset with 25 minorities of Yunnan. In future works
we aim to extend our method to more applications and address the limitations in the current method. Further investigations and analysis are required for extreme situations
such as clothing accessories for minorities.
Hu J Y, Kita Y. Classification of the category of clothing item after bringing it into limited shapes[C]//Proceedings of the 15th International Conference on Humanoid Robots. Seoul, South Korea: IEEE, 2015: 588-594.[ DOI:10.1109/HUMANOIDS.2015.7363422 http://dx.doi.org/10.1109/HUMANOIDS.2015.7363422 ]
Yu Y T, Zhu Q. The method of multi-step dimensionality reduction and parallel feature fusion in clothing recognition[C]//Proceedings of International Conference on Artificial Intelligence and Robotics and the International Conference on Automation, Control and Robotics Engineering. Kitakyushu, Japan: ACM, 2016: #13.[ DOI:10.1145/2952744.2952747 http://dx.doi.org/10.1145/2952744.2952747 ]
Yamaguchi K, Okatani T, Sudo K, et al. Mix and match: joint model for clothing and attribute recognition[C]//Proceedings of British Machine Vision Conference. Swansea, Wales: BMVA Press, 2015: 51.1-51.12.[ DOI:10.5244/C.29.51 http://dx.doi.org/10.5244/C.29.51 ]
Wang F, Zhao Q Y, Liu Q J, et al. Attribute basedapproach for clothing recognition[C]//Proceedings of the 7th Chinese Conference on Pattern Recognition. Chengdu, China: Springer, 2016: 364-378.[ DOI:10.1007/978-981-10-3005-5_30 http://dx.doi.org/10.1007/978-981-10-3005-5_30 ]
Chen L, Zhang Q, Li B X. Predicting multiple attributes via relative multi-task learning[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE Computer Society, 2014: 1027-1034.[ DOI:10.1109/CVPR.2014.135 http://dx.doi.org/10.1109/CVPR.2014.135 ]
Bourdev L, Maji S, Malik J. Describing people: a poselet-based approach to attribute classification[C]//Proceedings of 2011 IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE Computer Society, 2011: 1543-1550.[ DOI:10.1109/ICCV.2011.6126413 http://dx.doi.org/10.1109/ICCV.2011.6126413 ]
Song Z, Wang M, Hua X S, et al. Predicting occupation via human clothing and contexts[C]//Proceedings of 2011 IEEE International Conference on Computer Vision. Barcelona, Spain: IEEE, 2011: 1084-1091.[ DOI:10.1109/ICCV.2011.6126355 http://dx.doi.org/10.1109/ICCV.2011.6126355 ]
Felzenszwalb P, McAllester D, Ramanan D. A discriminatively trained, multiscale, deformable part model[C]//Proceedings of 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK, USA: IEEE, 2008, 8: 1-8.[ DOI:10.1109/CVPR.2008.4587597 http://dx.doi.org/10.1109/CVPR.2008.4587597 ]
Bourdev L, Maji S, Brox T, et al. Detecting people using mutually consistent poselet activations[C]//Proceedings of the 11th European Conference on Computer Vision. Heraklion, Crete, Greece: Springer Science + Business Media, 2010: 168-181.[ DOI:10.1007/978-3-642-15567-3_13 http://dx.doi.org/10.1007/978-3-642-15567-3_13 ]
Divvala S, Efros A, Hebert M, et al. Object instance sharing by enhanced bounding box correspondence[C]//Proceedings of British Machine Vision Conference. Surrey: British Machine Vision Association, 2012: 60.1-60.11.[ DOI:10.5244/C.26.60 http://dx.doi.org/10.5244/C.26.60 ]
Divvala S K, Efros A A, Hebert M. How important are "Deformable parts" in the deformable parts model?[C]//Proceedings of the 12th International Conference on Computer Vision. Florence, Italy: Springer, 2012: 31-40.[ DOI:10.1007/978-3-642-33885-4_4 http://dx.doi.org/10.1007/978-3-642-33885-4_4 ]
Parikh D, Zitnick C L. Finding the weakest link in person detectors[C]//Proceedings of 2011 IEEE Conference on Computer Vision and Pattern Recognition. Providence, RI, USA: IEEE Computer Society, 2011: 1425-1432.[ DOI:10.1109/CVPR.2011.5995450 http://dx.doi.org/10.1109/CVPR.2011.5995450 ]
Bourdev L, Maji S, Malik J. Poselets:a distributed representation for visual recognition[J]. Journal of Vision, 2011, 11:#891.[DOI:10.1167/11.11.891]
Yang M, Yu K. Real-time clothing recognition in surveillance videos[C]//Proceedings of the 18th IEEE International Conference on Image Processing. Brussels, Belgium: IEEE, 2011: 2937-2940.[ DOI:10.1109/ICIP.2011.6116276 http://dx.doi.org/10.1109/ICIP.2011.6116276 ]
Anandh A, Mala K, Suganya S. Content based image retrieval system based on semantic information using color, texture and shape features[C]//Proceedings of 2016 International Conference on Computing Technologies and Intelligent Data Engineering. Kovilpatti, India: IEEE, 2016: 1-8.[ DOI:10.1109/ICCTIDE.2016.7725364 http://dx.doi.org/10.1109/ICCTIDE.2016.7725364 ]
Li Z M, Li Y T, Liu Y J, et al. Clothing retrieval combining hierarchical over-segmentation and cross-domain dictionary learning[J]. Journal of Image and Graphics, 2017, 22(3):358-365.
李宗民, 李妍特, 刘玉杰, 等.结合层次分割和跨域字典学习的服装检索[J].中国图象图形学报, 2017, 22(3):358-365. [DOI:10.11834/jig.20170310]
Hidayati S C, You C W, Cheng W H, et al. Learning and recognition of clothing genres from full-body images[J]. IEEE Transactions on Cybernetics, 2018, 48(5):1647-1659.[DOI:10.1109/TCYB.2017.2712634]
Shen J, Liu G C, Chen J, et al. Unified structured learning for simultaneous human pose estimation and garment attribute classification[J]. IEEE Transactions on Image Processing, 2014, 23(11):4786-4798.[DOI:10.1109/TIP.2014.2358082]
Bossard L, Dantone M, Leistner C, et al. Apparel classification with style[C]//Proceedings of the 11th Asian Conference on Computer Vision. Daejeon, Korea: Springer Berlin Heidelberg, 2012: 321-335.[ DOI:10.1007/978-3-642-37447-0_25 http://dx.doi.org/10.1007/978-3-642-37447-0_25 ]
Chen H Z, Gallagher A, Girod B. Describing clothing by semantic attributes[C]//Proceedings of the 12th European Conference on Computer Vision. Florence, Italy: Springer, 2012: 609-623.[ DOI:10.1007/978-3-642-33712-3_44 http://dx.doi.org/10.1007/978-3-642-33712-3_44 ]
Di W, Wah C, Bhardwaj A, et al. Style finder: fine-grained clothing style detection and retrieval[C]//Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Portland, OR, USA: IEEE, 2013: 8-13.[ DOI:10.1109/CVPRW.2013.6 http://dx.doi.org/10.1109/CVPRW.2013.6 ]
Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE Computer Society, 2005: 886-893.[ DOI:10.1109/CVPR.2005.177 http://dx.doi.org/10.1109/CVPR.2005.177 ]
Yang Y, Ramanan D. Articulated human detection with flexible mixtures of parts[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12):2878-2890.[DOI:10.1109/TPAMI.2012.261]
Wei L. National Minority Women's Wear Design[M]. Beijing:China Minzu University Press, 2014:3-28.
魏莉.少数民族女装结构设计[M].北京:中央民族大学出版社, 2014:3-28.
Chang L, Fang Y C, Jiang X D. Multi-task attribute joint feature learning[C]//Proceedings of the 10th Chinese Conference on Biometric Recognition. Tianjin, China: Springer, 2015: 193-200.[ DOI:10.1007/978-3-319-25417-3_24 http://dx.doi.org/10.1007/978-3-319-25417-3_24 ]
Zhang N, Donahue J, Girshick R, et al. Part-based R-CNNs for fine-grained category detection[M]//Fleet D, Pajdla T, Schiele B, et al. Computer Vision-ECCV 2014. Zurich, Switzerland: Springer International Publishing, 2014: 834-849.[ DOI:10.1007/978-3-319-10590-1_54 http://dx.doi.org/10.1007/978-3-319-10590-1_54 ]
Chang C C, Lin C J. LIBSVM:a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):#27.[DOI:10.1145/1961189.1961199]
相关作者
相关机构
京公网安备11010802024621
