基于时序特征的草图识别方法

摘要/Abstract

摘要： 草图识别是一项很具有挑战性的工作。目前,大部分草图识别的工作都将草图当作普通的纹理图像,忽视了草图的时序性。因此,文中通过挖掘草图的时序性,将草图笔画按照时间分组。为进一步利用时序特征在草图识别过程中的作用,使用了循环神经网络将笔画分组按照时间序列作为输入,最后使用联合贝叶斯将各个时序下获得的草图特征进行整合,完成草图的识别工作。在公开标准数据集上对所提算法进行了测试,实验结果显示该算法的识别准确率明显高于其他算法。

关键词: 草图识别, 联合贝叶斯, 门控制单元, 时序性, 循环神经网络

Abstract: Recognizing freehand sketches is a greatly challenging work.Most existing methods treat sketches as traditional texture images with fixed structural ordering and ignore the temporality of sketch.In this paper,a novel sketch recognition method was proposed based on the sequence of sketch.Strokes are divided into groups and their features are fed into recurrent neural network to make use of the temporality.The features from each temporality are combined to produce the final classification results.The proposed algorithm was tested on a benchmark,and the recognition rate is far above other methods.

Key words: Gate recurrent units(GRU), Joint bayes, Recurrent neural network, Sketch recognition, Temporality

中图分类号:

TP391

于美玉, 吴昊, 郭晓燕, 贾棋, 郭禾. 基于时序特征的草图识别方法[J]. 计算机科学, 2018, 45(11A): 198-202. https://doi.org/

YU Mei-yu, WU Hao, GUO Xiao-yan, JIA Qi GUO He. Sequential Feature Based Sketch Recognition[J]. Computer Science, 2018, 45(11A): 198-202. https://doi.org/

参考文献

[1]EITZ M,HAYS J,ALEXA M.How do humans sketch object?[J].ACM Transactions on Graphics,2012,31(4):1-10.
[2]SCHNEIDER R G,TUYTELAARS T.Sketch classification and classification-driven analysis using fisher vectors[J].ACM Transactions on Graphics,2014,33(6):174.
[3]EITZ M,HILDEBRAND K,BOUBEKEUR T,et al.Sketch-based image retrieval:Benchmark and bag-of-featuresdescriptors[J].IEEE Transactions on Visualization and Computer Grap-hics,2011,17(11):1624-1636.
[4]HU R,COLLOMOSSE J.A performance evaluation of gradient field hog descriptor for sketch based image retrieval[J].Computer Vision and Image Understanding,2013,117(7):790-806.
[5]WANG F,KANG L,LI Y.Sketch-based 3d shape retrieval using convolutional neural network[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE Press,2015:1875-1883.
[6]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,CA,USA:IEEE Press,2005,1:886-893.
[7]LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[8]YU Q,YANG Y,SONG Y Z,et al.Sketch-a-net that beats humans[C]∥British Machine Vision Conference,BMVC 2015.Swansea,UK:BMVA Press,2015:1-12.
[9]LI Y,HOSPEDALES T M,SONG Y Z,et al.Free-hand sketch recognition by multi-kernel feature learning[J].Computer Vision and Image Understanding,2015,137:1-11.
[10]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Image net classification with deep convolutional neural networks[C]∥Advances in Neural Information Processing Systems.Lake Tahoe,Nevada,USA:IEEE Press,2012:1097-1105.
[11]王卫,尹建峰,孙正兴.一种手绘草图的快速参数化方法[J].计算机科学,2006,33(1):264-268.
[12]袁贞明,金贵朝,张佳.基于贝叶斯网络的在线草图识别算法[J].计算机工程,2010,36(5):32-34.
[13]尹建锋,孙正兴.基于时序的多笔划草图识别[J/OL].中国科技论文在线,http://www.paper.edu.cn/search/simple?searchType=&searchContent=%25E5%259F%25BA%25E4%25BA%258E%25E6%2597%25B6%25E5%25BA%258F%25E7%259A%2584%25E5%25A4%259A%25E7%25AC%2594%25
E5%2588%2592%25E8%258D%2589%25E5%259B%25BE%25E8%25AF%2586%25E5%2588%25AB&searchDate=2003-2018&searchPage=1&searchSub-ject=%25E5%2585%25A8%25E9%2583%25A8&searchSort=relevant.
[14]SIMONYAN K,ZISSERMAN A.Very deep convolutional net works for large-scale image recognition[J].arXivpreprint arXiv:1409.1556,2014.
[15]LECUN Y,BOSER B E,DENKER J S,et al.Handwritten digit recognition with a back-propagation network[C]∥Advances in Neural Information Processing Systems.Denver,Colorado,USA:Morgan Kaufmann,1990:396-404.
[16]WANG F,KANG L,LI Y.Sketch-based 3d shape retrieval using convolutional neural networks[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Boston,MA,USA:IEEE Computer Society,2015:1875-1883.
[17]VINYALS O,RAVURI S V,POVEY D.Revisiting recurrent neural networks for robust ASR[C]∥2012 IEEE International Conference on Acoustics,Speech and Signal Processing.Kyoto,Japan:IEEE Press,2012:4085-4088.
[18]SUTSKEVER I,MARTENS J,HINTON G E.Generating text with recurrent neural networks[C]∥Proceedings of the 28th International Conference on Machine Learning.Bellevue,Wa-shington,USA:MLR.org,2011:1017-1024.
[19]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[20]CHO K,VAN MERRIËNBOER B,GULCEHRE C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]∥Proceedings of the 2014 Conference on Empirical Methods in Natural Language Proces-sing,EMNLP 2014.Doha,Qatar:Association for Computational Linguistics,2014:1724-1734.
[21]CHUNG J,GULCEHRE C,CHO K,et al.Gated feedback recurrent neural networks[C]∥International Conference on Machine Learning.Lille,France:MLR.org,2015:2067-2075.
[22]CHEN D,CAO X,WANG L,et al.Bayesian face revisited:A joint formulation[C]∥12^th European Conference on Computer Vision.Florence,Italy:Springer,2012:566-579.
[23]COLLOBERT R,BENGIO S,MARIÉTHOZ J.Torch:a modular machine learning software library[R].Idiap Research Report,2002.
[24]LI Y,SONG Y Z,GONG S.Sketch Recognition by Ensemble Matching of Structured Features[C]∥British Machine Vision Conference,BMVC 2013.Bristol,UK:BMVA Press,2013:2.
[25]YU Q,YANG Y,LIU F,et al.Sketch-a-net:A deep neural network that beats humans[J].International Journal of Computer Vision,2017,122(3):411-425.

相关文章 15

[1]	彭双, 伍江江, 陈浩, 杜春, 李军. 基于注意力神经网络的对地观测卫星星上自主任务规划方法 Satellite Onboard Observation Task Planning Based on Attention Neural Network 计算机科学, 2022, 49(7): 242-247. https://doi.org/10.11896/jsjkx.210500093
[2]	喻昕, 林植良. 解决一类非光滑伪凸优化问题的新型神经网络 Novel Neural Network for Dealing with a Kind of Non-smooth Pseudoconvex Optimization Problems 计算机科学, 2022, 49(5): 227-234. https://doi.org/10.11896/jsjkx.210400179
[3]	安鑫, 代子彪, 李阳, 孙晓, 任福继. 基于BERT的端到端语音合成方法 End-to-End Speech Synthesis Based on BERT 计算机科学, 2022, 49(4): 221-226. https://doi.org/10.11896/jsjkx.210300071
[4]	时雨涛, 孙晓. 一种会话理解模型的问题生成方法 Conversational Comprehension Model for Question Generation 计算机科学, 2022, 49(3): 232-238. https://doi.org/10.11896/jsjkx.210200153
[5]	李昊, 曹书瑜, 陈亚青, 张敏. 基于注意力机制的用户轨迹识别模型 User Trajectory Identification Model via Attention Mechanism 计算机科学, 2022, 49(3): 308-312. https://doi.org/10.11896/jsjkx.210300231
[6]	肖丁, 张玙璠, 纪厚业. 基于多头注意力机制的用户窃电行为检测 Electricity Theft Detection Based on Multi-head Attention Mechanism 计算机科学, 2022, 49(1): 140-145. https://doi.org/10.11896/jsjkx.210100177
[7]	曾友渝, 谢强. 基于改进RNN和VAR的船舶设备故障预测方法 Fault Prediction Method Based on Improved RNN and VAR for Ship Equipment 计算机科学, 2021, 48(6): 184-189. https://doi.org/10.11896/jsjkx.200700117
[8]	尹久, 池凯凯, 宦若虹. 基于ATT-DGRU的文本方面级别情感分析 Aspect-level Sentiment Analysis of Text Based on ATT-DGRU 计算机科学, 2021, 48(5): 217-224. https://doi.org/10.11896/jsjkx.200500076
[9]	王习, 张凯, 李军辉, 孔芳, 张熠天. 联合自注意力和循环网络的图像标题生成 Generation of Image Caption of Joint Self-attention and Recurrent Neural Network 计算机科学, 2021, 48(4): 157-163. https://doi.org/10.11896/jsjkx.200300146
[10]	陈千, 车苗苗, 郭鑫, 王素格. 一种循环卷积注意力模型的文本情感分类方法 Recurrent Convolution Attention Model for Sentiment Classification 计算机科学, 2021, 48(2): 245-249. https://doi.org/10.11896/jsjkx.200100078
[11]	吕明琪, 洪照雄, 陈铁明. 一种融合时空关联与社会事件的交通流预测方法 Traffic Flow Forecasting Method Combining Spatio-Temporal Correlations and Social Events 计算机科学, 2021, 48(2): 264-270. https://doi.org/10.11896/jsjkx.200300098
[12]	李亚男, 胡宇佳, 甘伟, 朱敏. 基于深度学习的miRNA靶位点预测研究综述 Survey on Target Site Prediction of Human miRNA Based on Deep Learning 计算机科学, 2021, 48(1): 209-216. https://doi.org/10.11896/jsjkx.191200111
[13]	庄世杰, 於志勇, 郭文忠, 黄昉菀. 基于Zoneout的跨尺度循环神经网络及其在短期电力负荷预测中的应用 Short Term Load Forecasting via Zoneout-based Multi-time Scale Recurrent Neural Network 计算机科学, 2020, 47(9): 105-109. https://doi.org/10.11896/jsjkx.190800030
[14]	游兰, 韩雪薇, 何正伟, 肖丝雨, 何渡, 潘筱萌. 基于改进Seq2Seq的短时AIS轨迹序列预测模型 Improved Sequence-to-Sequence Model for Short-term Vessel Trajectory Prediction Using AIS Data Streams 计算机科学, 2020, 47(9): 169-174. https://doi.org/10.11896/jsjkx.190800060
[15]	赫磊, 邵展鹏, 张剑华, 周小龙. 基于深度学习的行为识别算法综述 Review of Deep Learning-based Action Recognition Algorithms 计算机科学, 2020, 47(6A): 139-147. https://doi.org/10.11896/JsJkx.190900176

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed