纺织学报 ›› 2020, Vol. 41 ›› Issue (08): 95-100.doi: 10. 13475/ j.fzxb.20191003306

• 服装工程 • 上一篇    下一篇

服装设计知识图谱中的服装装饰工艺分类模型

杨 娟1,2, 张远鹏3,4   

  1. 1. 苏州大学纺织与服装工程学院, 江苏苏州 215123;  2. 南通大学纺织服装学院, 江苏南通 226001; 3. 南通大学智能信息技术研究中心, 江苏南通 226001;  4. 香港理工大学电子计算学系, 香港 999077
  • 收稿日期:2019-10-16 修回日期:2020-05-15 出版日期:2020-08-15 发布日期:2020-08-21

Garment ornamenting craft classification model for knowledge graph on clothing design

YANG Juan1,2, ZHANG Yuanpeng3,4   

  1. 1. College of Textile and Clothing Engineering, Soochow University, Suzhou, Jiangsu 215123, China;  2. School of Textile and Clothing, Nantong University, Nantong, Jiangsu 226001, China;  3. Research Institute of Smart Information Technology, Nantong University, Nantong, Jiangsu 226001, China;  4. Departing of Computing, The Hong Kong Polytechnic University, Hong Kong 999077, China
  • Received:2019-10-16 Revised:2020-05-15 Online:2020-08-15 Published:2020-08-21

摘要:

为解决服装装饰工艺类别判定中噪声视角或弱相关视角带来的负影响问题,采用具备视角约减功能的多视角分类模型对噪声视角或弱相关视角进行动态过滤。首先基于1-阶TSK 模糊系统,在其目标优化函数中引入视角间分类误差一致性约束,实现多视角协同学习;然后通过变体信息熵学习各视角的权重,并在权重学习过程中制定视角约减规则,自动剔除噪声视角或弱相关视角;最后通过服装装饰工艺类别分类实验对所构建模型的分类精度进行验证。结果表明:相比视角约减之前,所提出的多视角分类模型的测试精度提高了2. 68%,可有效地过滤噪声视角或弱相关视角,降低其对分类精度的影响。

关键词: 服装装饰工艺, 模糊系统, 多视角数据, 视角约减, 协同学习, 服装设计资源, 知识图谱

Abstract:

In order to eliminate the negative influences caused by noisy views or weakly relevant views in the garment ornamenting craft classification tasks, an automatic view-reduction multi-view classification model was used to filter noisy views or weakly relevant views in this research. Based on the 1-order TSK fuzzy system, an error constraint item was introduced to be the objective function for collaborative learning. Then, a variant entropy item was designed to learn the weight of each view, and a reduction principle was designed to filter noisy views or weakly relevant views during collaborative learning. The proposed model was tested as the final step on the clothing ornamenting craft classification tasks. Experimental results demonstrate that the proposed classification model can reduce noisy views or weakly relevant views effectively such that the negative influences generated by them can be avoided. Compared with the model without view-reduction, the proposed classification model achieves a 2. 68% improvement in terms of data accuracy.

Key words: garment ornamenting craft, fuzzy system, multi-view data, view-reduction, collaborative, learning, clothing design resource, knowledge graph

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 胡凤霞;张健;盛家镛. 新型蚕丝材料的纤维取向结构[J]. 纺织学报, 2005, 26(1): 33 -35 .
[2] 程国模. 全国色织产品设计、工艺与仿毛效果学术讨论会[J]. 纺织学报, 1984, 5(08): 15 .
[3] 董秀洁;周光辉;张景昌. PVC基纳米SiO2复合材料电改性研究[J]. 纺织学报, 2004, 25(04): 16 -17 .
[4] 翁晓明. 胶辊改革过程中几个注意问题[J]. 纺织学报, 1987, 8(01): 9 .
[5] 张聿. 基于弱混沌理论的纹织设计方法研究[J]. 纺织学报, 2004, 25(04): 22 -23 .
[6] 崔运花. 超声波技术在苎麻纤维预处理中的应用[J]. 纺织学报, 1998, 19(06): 43 -44 .
[7] 马晓宇;冯毅力. 三维服装模拟技术的研究进展[J]. 纺织学报, 2004, 25(04): 122 -124 .
[8] 严灏景;李再清. 各种混和比混纺纱的强力[J]. 纺织学报, 1981, 2(03): 31 -34 .
[9] 王文炆;张森林. 基于三维小波变换的图像融合[J]. 纺织学报, 2004, 25(05): 81 -83 .
[10] 李惠杰. 服装企业销售物流信息化管理体系的构建[J]. 纺织学报, 2004, 25(05): 84 -86 .