吉林大学学报(工学版) ›› 2020, Vol. 50 ›› Issue (1): 289-296.doi: 10.13229/j.cnki.jdxbgxb20180902

• 计算机科学与技术 • 上一篇    

基于本体的唐卡图像标注方法

王铁君1,2(),王维兰1,2()   

  1. 1. 西北民族大学 中国民族语言文字信息技术教育部重点实验室,兰州 730030
    2. 西北民族大学 数学与计算机科学学院,兰州730030
  • 收稿日期:2018-09-03 出版日期:2020-01-01 发布日期:2020-02-06
  • 通讯作者: 王维兰 E-mail:wtj@mail.lzjtu.cn;wangweilan@xbmu.edu.cn
  • 作者简介:王铁君(1981-),女,副教授,博士. 研究方向:模式识别,图像处理,信息检索. E-mail:wtj@mail.lzjtu.cn
  • 基金资助:
    国家自然科学基金项目(60875006);中央高校基本科研业务费专项项目(31920170146)

Thangka image annotation based on ontology

Tie-jun WANG1,2(),Wei-lan WANG1,2()   

  1. 1. Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou 730030, China
    2. School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou 730030, China
  • Received:2018-09-03 Online:2020-01-01 Published:2020-02-06
  • Contact: Wei-lan WANG E-mail:wtj@mail.lzjtu.cn;wangweilan@xbmu.edu.cn

摘要:

针对现有的图像自动标注算法对唐卡图像的自动标注和语义描述能力有限的缺点,提出了一种基于领域知识本体的唐卡图像语义标注方法。首先,构建了唐卡图像标注框架体系,然后,在前期唐卡图像中目标对象识别和分类的基础上,结合唐卡领域知识本体,对圣像类唐卡图像进行了两个层面的标注,即局部区域自动标注和基于本体的全局标注。实验结果表明,该标注方法对唐卡图像十分有效。

关键词: 计算机应用, 唐卡图像, 图像标注, 领域本体

Abstract:

The existing image automatic annotation algorithm has very limited ability of automatic annotation and semantic description of Thangka image. This paper proposes a semantic annotation method of Thangka image based on domain knowledge ontology. First, the system of Thangka image annotation framework was constructed. Then in the early study of the Thangka image target recognition and classification, on the basis of combining Thangka domain knowledge ontology, two levels of Thangka image annotation were realized, which were local region automatic annotation and ontology?based global annotation. Experimental results prove that the proposed method is effective for Thangka image semantic annotation.

Key words: computer application, Thangka image, image annotation, domain ontology

中图分类号: 

  • TP391

图1

基于本体的唐卡图像语义标注框架"

图2

头饰分类识别方法"

图3

头饰提取后的图像及其灰度图像"

图4

基本全局门限算法分割后的二值图像"

表1

头饰识别结果"

识别算法头冠发髻僧帽总分类正确率
文献[20]方法96.694.176.589.1
基于频率谱参数和颜色特征参数的DDkNN方法88848084.0
基于频率谱参数+颜色特征参数+形状参数+纹理参数的DDkNN方法96929293.33

图5

常见的6种手势识别"

图6

唐卡领域本体模型"

表2

通用推理规则列表"

关 系推理规则举例
常见人物关系(父子、母子、父女、母女、夫妻、兄弟、叔侄、爷孙、师徒、同门)

IF(A 有父亲 B) AND (B有父亲C) THEN (A 有孙子C)

IF(A 有儿子B) AND (B有母亲C) THEN (A 有妻子C)

IF(A 有兄弟B) AND (B有儿子C) THEN (A 有侄子C)

圣像特有关系(别名、原名、藏文名、梵文名、汉译名、意译名、音译名、化身、法身、报身)

IF(A 有别名B) AND (B有原名C) THEN (A 有原名C)

IF(A 有法身B) AND (B有别名C) THEN (A 有法身C)

IF(A 有报身B) AND (B有法身C) THEN (A 有法身C)

IF(A 有化身B) AND (B有报身C) THEN (A 有报身C)

表3

组合特征辨识主尊举例"

主 尊组合特征
不动明王忿怒相+一面二臂+三目+右手举般若剑+左手结期克印+半跪姿
大梵天坐骑天鹅+四面+左手持宝瓶+右手持轮
大黑天左手捧嘎巴拉碗+右手持金刚钺刀
喜金刚十六只手都持嘎巴拉碗
虚空藏菩萨寂静相+一面二臂+宝剑+蓝色身体
金刚亥母舞姿+猪首
狮面佛母狮头+蓝色人身+左手托嘎巴拉碗+右手结期克印+金刚钺刀+天杖

图7

基于本体的唐卡图像标注过程"

图8

唐卡图像标注系统"

1 钱建军. 基于语义的唐卡图像标注与检索研究[D].兰州:西北民族大学中国民族信息技术研究院,2010.
Qian Jian-jun. A study on semantic-based thangka image annotation and retrieval[D]. Lanzhou:National Information Technology Research Institute,Northwest Minzu University,2010.
2 毕学慧, 刘华明, 王维兰. 基于头饰特征的唐卡标注和检索[J]. 计算机科学, 2014, 41(2): 312-316.
Bi Xue-hui, Liu Hua-ming, Wang Wei-lan. Thangka annotation and retrieval based on headdress features[J]. Computer Science, 2014, 41(2): 312-316.
3 鲍泓, 徐光美, 冯松鹤, 等. 自动图像标注技术研究进展[J]. 计算机科学, 2011, 38(7): 35-40.
Bao Hong, Xu Guang-mei, Feng Song-he. Advances in automatic image annotation[J]. Computer Science, 2011, 38(7): 35-40.
4 Zhang D, Islam M M, Lu G. A review on automatic image annotation techniques[J]. Pattern Recognition, 2012, 45(1): 346-362.
5 李志欣, 施智平, 张灿龙, 等. 混合生成式和判别式模型的图像自动标注[J]. 中国图象图形学报, 2015, 20(5): 687-699.
Li Zhi-xin, Shi Zhi-ping, Zhang Can-long, et al. Hybrid generative/discriminative model for automatic image annotation[J]. Journal of Image and Graphics, 2015, 20(5): 687-699.
6 Ding X, Li B, Xiong W, et al. Multi-Instance multi-label learning combining hierarchical context and its application to image annotation[J]. IEEE Transactions on Multimedia, 2016, 18(8): 1-12.
7 Zhou Z H, Zhang M L. Multi-label learning[M]∥ Sammut Claude, Webbv Geoffrey I. Encyclopedia of Machine Learning and Data Mining, Berlin: Springer, 2016:352-366.
8 Zhao M, Chow T W S, Zhang Z, et al. Automatic image annotation via compact graph based semi-supervised learning[J]. Knowledge-Based Systems, 2015, 76: 148-165.
9 史彩娟, 阮秋琦. 基于增强稀疏性特征选择的网络图像标注[J]. 软件学报, 2015, 26(7): 1800-1811.
Shi Cai-juan, Ruan Qiu-qi. Feature selection with enhanced sparsity for web image annotation[J]. Journal of Software, 2015, 26(7): 1800-1811.
10 Wang H, Liu S, Chia L T. Does ontology help in image retrieval? a comparison between keyword, text ontology and multi-modality ontology approaches[C]∥ACM International Conference on Multimedia, Santa Barbara, USA, 2006: 109-112.
11 Srikanth M, Varner J, Bowden M, et al. Exploiting ontologies for automatic image annotation[C]∥Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, Salvador, Brazil, 2005: 552-558.
12 Smailis C V, Iakovidis D K. Ontology-based automatic image annotation exploiting generalized qualitative spatial semantics[C]∥The 7th Hellenic Conference on Artificial Intelligence, Lamia, Greece, 2012: 299-306.
13 Singh P, Goudar R H, Rathore R, et al. Domain ontology based efficient image retrieval[C]∥The 7th International Conference on Intelligent Systems and Control, Coimbatore, Tamilnadu, India, 2013: 445-452.
14 王琦, 鲁东明. 基于构图分析的古代壁画相关度评价方法[J]. 浙江大学学报:工学版, 2012, 46(3): 21-30.
Wang Qi, Lu Dong-Ming. Composition analysis-based relevance ranking for ancient mural[J]. Journal of Zhejiang University(Engineering Science), 2012, 46(3): 21-30.
15 Wei Z, Luo X, Zhou F. Ontology based automatic image annotation using multi-class SVM[C]∥The 7th International Conference on Image and Graphics, Qingdao, China, 2013: 434-438.
16 Ismat A R, Md Z U, Masaki A. Ontology based supervised learning for image annotation[J]. IEICE Technical Report Image Engineering[J]. 2014, 114: 41-46.
17 Ferdinand D, Paul M, Stéphanie F, et al. Developing a knowledge base to support the annotation of ultrasound images of ectopic pregnancy[J]. Journal of Biomedical Semantics, 2017, 8(1): 4-17.
18 Hyun-Deok No, Kwang-won Seo, Dong-Hyuk Im. Semantic image annotation and retrieval in mobile environments[J]. Journal of Korea Multimedia Society, 2016, 19(8): 1498-1504.
19 Vinyals O, Toshev A, Bengio S, et al. Show and tell: a neural image caption generator[C]∥Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Boston, United States, 2015: 3156-3164.
20 Xu K, Ba J L, Kiros R, et al. Show, attend and tell: neural image caption generation with visual attention [C]∥The 32nd International Conference on Machine Learning, Lile, France, 2015: 2048-2057.
21 蒋树强, 闵巍庆, 王树徽. 面向智能交互的图像识别技术综述与展望[J]. 计算机研究与发展, 2016, 53(1): 113-122.
Jiang Shu-qiang, Min Wei-qing, Wang Shu-hui. Survey and prospect of intelligent interaction-oriented image recognition techniques[J]. Journal of Computer Research and Development, 2016, 53(1): 113-122.
22 Karpathy A, Li F F. Deep visual-semantic alignments for generating image descriptions[C]//IEEE Conference on Computer Vision and Pattern Recognition, Boston, United States, 2015: 3128-3137.
23 Fang H, Platt J C, Zitnick C L, et al. From captions to visual concepts and back[C]//IEEE Conference on Computer Vision and Pattern Recognition, Boston, United States, 2015: 1473-1482.
24 Borisyuk F, Gordo A, Sivakumar V. Rosetta: large scale system for text detection and recognition in images[C]//The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, United Kingdom, 2018: 71-79.
25 王铁君, 王维兰. 基于多特征融合的唐卡图像法器识别方法[J]. 计算机工程, 2016, 42(3): 198-203, 207.
Wang Tie-jun, Wang Wei-lan. Religious ritual implement recognition method in Thangka image based on multi-feature fusion[J]. Computer Engineering, 2016, 42(3): 198-203, 207.
26 吴禄慎,常参参,王晓辉,等. 基于局部调节卷积神经网络的图像识别方法[J]. 计算机工程, 2018, 44(12): 240-246.
Wu Lu-shen,Chang Can-can,Wang Xiaohui,et al. Image recognition method based on local adjustment convolutional neural network[J]. Computer Engineering, 2018, 44(12): 240-246.
27 王铁君, 王维兰. 基于Jena的唐卡领域本体推理[J]. 吉林大学学报:工学版, 2016, 46(6): 2059-2066.
Wang Tie-jun, Wang Wei-lan. Thangka domain ontology reasoning based on Jena[J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(6): 2059-2066.
28 王铁君, 王维兰. 唐卡领域本体研究与构建[J]. 吉林大学学报: 理学版, 2017, 55(2): 363-370.
Wang Tie-jun, Wang Wei-lan. Research and construction of Thangka domain ontology[J]. Journal of Jilin University (Science Edition), 2017, 55(2): 363-370.
[1] 张笑东,夏筱筠,吕海峰,公绪超,廉梦佳. 大数据网络并行计算环境中生理数据流动态负载均衡[J]. 吉林大学学报(工学版), 2020, 50(1): 247-254.
[2] 王晓辉,吴禄慎,陈华伟. 基于法向量距离分类的散乱点云数据去噪[J]. 吉林大学学报(工学版), 2020, 50(1): 278-288.
[3] 邓钧忆,刘衍珩,冯时,赵荣村,王健. 基于GSPN的Ad⁃hoc网络性能和安全平衡[J]. 吉林大学学报(工学版), 2020, 50(1): 255-261.
[4] 李雄飞,王婧,张小利,范铁虎. 基于SVM和窗口梯度的多焦距图像融合方法[J]. 吉林大学学报(工学版), 2020, 50(1): 227-236.
[5] 王洪雁,邱贺磊,郑佳,裴炳南. 光照变化下基于低秩稀疏表示的视觉跟踪方法[J]. 吉林大学学报(工学版), 2020, 50(1): 268-277.
[6] 车翔玖,刘华罗,邵庆彬. 基于Fast RCNN改进的布匹瑕疵识别算法[J]. 吉林大学学报(工学版), 2019, 49(6): 2038-2044.
[7] 周炳海,吴琼. 考虑工具和空间约束的机器人装配线平衡优化[J]. 吉林大学学报(工学版), 2019, 49(6): 2069-2075.
[8] 赵宏伟,王鹏,范丽丽,胡黄水,刘萍萍. 相似性保持实例检索方法[J]. 吉林大学学报(工学版), 2019, 49(6): 2045-2050.
[9] 沈军,周晓,吉祖勤. 服务动态扩展网络及其结点系统模型的实现[J]. 吉林大学学报(工学版), 2019, 49(6): 2058-2068.
[10] 周柚,杨森,李大琳,吴春国,王岩,王康平. 基于现场可编程门电路的人脸检测识别加速平台[J]. 吉林大学学报(工学版), 2019, 49(6): 2051-2057.
[11] 李宾,周旭,梅芳,潘帅宁. 基于K-means和矩阵分解的位置推荐算法[J]. 吉林大学学报(工学版), 2019, 49(5): 1653-1660.
[12] 李雄飞,宋璐,张小利. 基于协同经验小波变换的遥感图像融合[J]. 吉林大学学报(工学版), 2019, 49(4): 1307-1319.
[13] 刘元宁,刘帅,朱晓冬,霍光,丁通,张阔,姜雪,郭书君,张齐贤. 基于决策粒子群优化与稳定纹理的虹膜二次识别[J]. 吉林大学学报(工学版), 2019, 49(4): 1329-1338.
[14] 李宾,申国君,孙庚,郑婷婷. 改进的鸡群优化算法[J]. 吉林大学学报(工学版), 2019, 49(4): 1339-1344.
[15] 孙延君,申铉京,陈海鹏,赵永哲. 基于局部平面线性点的翻拍图像鉴别算法[J]. 吉林大学学报(工学版), 2019, 49(4): 1320-1328.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!