|本期目录/Table of Contents|

[1]张 聪,李岳阳,罗海驰,等.基于交互式分割的蕾丝花型检索算法[J].丝绸,2018,55(4):041107.[doi:10.3969/j.issn.1001-7003.2018.04.007]
 ZHANG Conga,LI Yueyanga,LUO Haichib,et al.Lace retrieval algorithm based on interactive segmentation[J].Journal of Silk,2018,55(4):041107.[doi:10.3969/j.issn.1001-7003.2018.04.007]
点击复制

基于交互式分割的蕾丝花型检索算法(PDF)
分享到:

《丝绸》[ISSN:1001-7003/CN:33-1122/TS]

卷:
55
期数:
2018年4期
页码:
041107
栏目:
研究与技术
出版日期:
2018-04-20

文章信息/Info

Title:
Lace retrieval algorithm based on interactive segmentation
文章编号:
1001-7003(2018)04-0038-06
作者:
张 聪 李岳阳 罗海驰 蒋高明 丛洪莲
江南大学 a.教育部针织技术工程研究中心;b.轻工过程先进控制教育部重点实验室
Author(s):
ZHANG Conga LI Yueyanga LUO Haichib JIANG Gaominga CONG Hongliana
a. Engineering Research Center for Knitting Technology, Ministry of Education; b. Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education; c. Key Laboratory of Eco-Textiles, Ministry of Education, Jiangnan University, Wuxi 214122, China
关键词:
蕾丝花型Live Wire 分割算法傅立叶描述子几何特征纹理特征层次匹配
Keywords:
lace pattern Live Wire segmentation algorithms Fourier descriptor geometric feature texture feature hierarchical matching
分类号:
TS186.4
doi:
10.3969/j.issn.1001-7003.2018.04.007
文献标志码:
A
摘要:
由于蕾丝花边工艺复杂,花型图案种类繁多,且传统的基于文本的图像检索方法采用人工标注,工作量大、主观性强,不能满足蕾丝花型的检索需求,因此文章采用基于Live Wire交互式图像分割和层次匹配的方法对蕾丝花型进行检索。首先利用Live Wire算法提取蕾丝花边中一个或多个花型轮廓;然后分别提取傅立叶描述子、几何特征、灰度共生矩阵作为其特征向量;最后将每个测试花型的特征向量与1327个样本花型的特征向量进行匹配并按相似度大小排序。实验结果表明,相比于单一的特征识别,该方法具有更高的识别率,能够满足蕾丝花型的检索需求。
Abstract:
The lace process is complex , and pattern types are numerous. Besides, traditional text-based image retrieval is manually annotated, which has the advantages of heavy workload and strong subjectivity. So, it cannot meet the retrieval demand of lace. Therefore, a novel method of retrieving lace patterns based on Live Wire interactive image segmentation and hierarchical matching is proposed in this paper. One or more pattern contours were extracted by using Live Wire algorithms firstly . Then, Fourier descriptors, geometric features and gray level co-occurrence matrix were extracted respectively as feature vectors. Lastly, feature vectors of each testing pattern were matched with those of 1327 sample patterns according to similarity degree. The results show that the method proposed here presents much higher recognition rate compared with single characteristic recognition, which could meet higher standards of lace pattern retrieval.

参考文献/References:

[1]何甜, 吴志明. 多梳拉舍尔定位蕾丝面料的边部设计[J]. 纺织学报, 2016, 37( 3): 55-59.
HE Tian, WU Zhiming. Edge design multi-bar Radchel positio ning lace fabric [J]. Journal of Textile Research, 2016, 37(3): 55-59.
[2]沈雷, 吴小艺, 陈赟银. 蕾丝的角色转变:从辅料到面料[J]. 丝绸, 2012, 49(11): 51-56.
SHEN Lei, WU Xiaoyi, CHEN Yunyin. Role transition o f lace fabric: from aaccessories to outerwear’s fabrics [J]. Journal of Silk, 2012, 49(11): 51-56.
[3]ZHANG L J, L IU X L , LU Z H , et al . Lace fabric image retrieval based on multi-scale and rotation invariant LBP [C]//International Conference on Internet Multimedia Computing and Service, ACM. 2015: 1-5.
[4]曹霞, 李岳阳, 罗海驰, 等. 蕾丝花边的改进型纹理特征检索方法[J]. 纺织学报, 2016, 37( 6): 142-147, 154.
CAO Xia, LI Yueyang, LUO Haichi, et al. Lace retrieval method based on improved texture feature [J]. Journal of Textile Research, 2016, 37( 6): 142-147, 154.
[5]BARRETT W A, MORTENSEN E N. Fast, accurate, and reproducible live-wire boundary extraction [J]. Proceedings of Visualization in Biomedical Computing, 1996(1): 183-192.
[6]王阳萍, 党建武, 李强, 等. 基于改进搜索策略的Live-Wire医学图像分割算法[J]. 计算机工程与应用, 2007 ,43(29): 24-26.
WANG Yangping, DANG Jianwu, LI Qiang, et al. Live-Wire algorithm for medical image segmentation based on improved search strategy [J]. Computer Engineering and Applications, 2007, 43(29): 24- 26.
[7]ZAHN C T,ROSKIES R Z . Fourier descriptors for plane closed curves [J] . IEEE Trans on Computers, 1972, 21: 269-28.
[8]JANE Y, KONG W, ZHANG D, et al. On hierarchical palmprint coding with multiple features for personal identification in large databases [J]. IEEE Transactions on Circuits and Systems For Video Technology, 2004, 14(2): 234-243.
[9]姚伟克, 庄哲民, 杨金耀, 等. 基于改进Live-Wire算法的超声图像弱边缘分割算法[J]. 测试技术学报, 2015,29(5): 397-403.
YAO Weike, ZHUANG Zhemin, YANG Jinyao, et al. Segmentation of ultrasound images with weak edge base on improved Live-Wire algorithm [J]. Journal of Te st and Measurement Technology, 2015,29(5): 397-403.
[10]刘建立, 左保齐. 基于小波变换和阈值分割的织物疵点边缘检测[J]. 丝绸, 2006( 8): 42-44, 50.
LIU Jianli, ZUO Baoqi. Edge detection of fabric defects based on wavelet transform and threshold segmentation algorithm [J]. Journal of Silk, 2006( 8): 42-44, 50.
[11]葛元, 郭兴伟, 王林泉. 傅立叶描述子在手势识别中的应用[J]. 计算机应用与软件, 2005 ,22(6): 12-13, 92.
GE Yuan, GUO Xingwei, WANG Linquan. The application of fourier descriptors to the recognition of alphabet gesture [J] . Computer Applications and Software, 2005,22(6):12-13, 92.
[12]高士忠. 基于灰度共生矩阵的织物纹理分析[J]. 计算机工程与设计, 2008 ,29(16): 4385-4388.

备注/Memo

备注/Memo:
基金项目:江苏高校优势学科建设工程资助项目(苏政办发〔2014〕37号);江苏省产学研联合创新资金-前瞻性联合研究项目(BY2015019-20、BY2016022-35);国家工信部智能制造综合标准化与新模式应用项目子课题(1064130201160660)
收稿日期:2017-05-20
修回日期:2018-00-00
作者简介:张聪(1991—),女,硕士研究生,研究方向为图像处理在针织上的应用
通信作者:李岳阳,副教授,lyueyang@jiangnan.edu.cn
更新日期/Last Update: 2018-03-22