基于知识图谱的图像语义分析技术及应用研究
The Research of Image Semantic Analysis Technology and Application Based on Knowledge Graph
DOI: 10.12677/CSA.2018.89148, PDF,  被引量   
作者: 邓莉琼*, 张贵新, 郝向宁：空军通信士官学校指挥信息系统与网络系，辽宁 大连
关键词: 知识图谱；深度学习；图像；语义分析；语义检索；Knowledge Graph； Deep Learning； Image； Semantic Analysis； Semantic Retrieval
摘要: 图像的语义分析技术一直是图像领域的研究难点之一，知识图谱作为一种智能的知识组织方式，可以帮助用户迅速、准确地查询到所需要的信息。本文首先提出了一种基于知识图谱的图像语义分析流程，然后采用了深度表达模型对图像的机构化语义信息进行描述和抽取，在此基础上研究了基于知识图谱的图像语义知识融合和加工技术，构建后的多层次图像语义模型具备管理实体关系三元组的能力、支持图谱的自动构建与多模式查询。最后基于该思路分析了图像语义分析技术在语义检索、关联分析及可视化方面等的应用，对媒体语义中的信息组织和知识管理有一定的指导意义。
Abstract: The semantic analysis technology of image has always been a difficult point in image field. As an intelligent and efficient way of organizing, knowledge graph can help users accurately query the information. This paper firstly puts forward an image semantic analysis process based on knowledge graph, then adopts deep learning model to describe image’s features. Image semantic knowledge fusion and processing is studied on this basis; a multilevel image semantic model constructed has ability to manage entity triples and support automatic construction. Finally, applications in semantic retrieval, association and visualization are analyzed, which has some guiding significance for in-formation organization and knowledge management of media semantic.
文章引用：邓莉琼, 张贵新, 郝向宁. 基于知识图谱的图像语义分析技术及应用研究[J]. 计算机科学与应用, 2018, 8(9): 1364-1371. https://doi.org/10.12677/CSA.2018.89148

参考文献

[1] Zhou, H., Yuan, Y. and Shi, C. (2009) Object Tracking Using SIFT Features and Mean Shift. Computer Vision and Image Under-standing, 113, 345-352. [Google Scholar] [CrossRef] 
[2] Krahenbühl, P. and Koltun, V. (2011) Efficient Inference in Fully Connected Crfs with Gaussian Edge Potentials. Advances in Neural Information Processing Systems. MIT Press, Massachu-setts, 109-117.
[3] 曹倩, 赵一鸣. 知识图谱的技术实现流程及相关应用[J]. 情报理论与实践, 2015, 38(12): 13-18.
[4] Zhang, X.L., Du, C.L., Li, P.S., et al. (2011) Knowledge Graph Completion via Local Semantic Contexts. Database Systems for Advanced Applications, 9642, 432-446. [Google Scholar] [CrossRef] 
[5] Shotton, J., Winn, J. and Rother, C. (2009) Texton Boost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context. International Journal of Computer Vision, 81, 2-3. [Google Scholar] [CrossRef] 
[6] He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. IEEE Proceedings of the Conference on Computer Vision and Pattern Recognition, Piscataway, 770-778.
[7] Lin, G., Shen, C., van den Hengel, A., et al. (2016) Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation. IEEE Proceedings of the Conference on Computer Vision and Pattern Recognition, Piscataway, 3194-3203.
[8] 张瑞茂, 彭杰锋, 吴恙, 林倞. 融合语义知识的深度表达学习及在视觉理解中的应用[J]. 计算机研究与发展, 2017, 54(6): 1251-1266.
[9] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolutional Networks for Semantic Segmentation. Proceeding of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, 3431-3440. [Google Scholar] [CrossRef] 
[10] Sharma, A., Tuzel, O. and Jacobs, D.W. (2015) Deep Hierarchical Parsing for Semantic Segmentation. Proceeding of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Piscataway, 3128-3137. [Google Scholar] [CrossRef] 
[11] 庄严, 李国良, 冯建华. 知识库实体对齐技术综述[J]. 计算机研究与发展, 2016, 53(1): 165-192.
[12] 孙霞, 董乐红. 基于监督学习的同义关系自动抽取方法[J]. 西北大学学报, 2008, 38(1): 35-39.
[13] 李跃鹏, 金翠, 及俊川. 基于Word2vec的关键词提取算法[J]. 科研信息化技术与应用, 2015(4): 54-59.
[14] 杨思洛, 韩瑞珍. 知识图谱研究现状及趋势的可视化分析[J]. 情报资料工作, 2012, 33(4): 22-28.