[1]阿丽亚·巴吐尔,努尔毕亚·亚地卡尔,吾尔尼沙·买买提,等.改进SURF特征的维吾尔文复杂文档图像匹配检索[J].智能系统学报,2019,14(02):296-305.[doi:10.11992/tis.201709014]
 ALIYA Batur,NURBIYA Yadikar,HORNISA Mamat,et al.Complex Uyghur document image matching and retrieval based on modified SURF feature[J].CAAI Transactions on Intelligent Systems,2019,14(02):296-305.[doi:10.11992/tis.201709014]
点击复制

改进SURF特征的维吾尔文复杂文档图像匹配检索(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年02期
页码:
296-305
栏目:
出版日期:
2019-03-05

文章信息/Info

Title:
Complex Uyghur document image matching and retrieval based on modified SURF feature
作者:
阿丽亚·巴吐尔1 努尔毕亚·亚地卡尔1 吾尔尼沙·买买提1 阿力木江·艾沙2 库尔班·吾布力1
1. 新疆大学 信息科学与工程学院, 新疆 乌鲁木齐, 830046;
2. 新疆大学 网络与信息中心, 新疆 乌鲁木齐, 830046
Author(s):
ALIYA Batur1 NURBIYA Yadikar1 HORNISA Mamat1 ALIMJAN Aysa2 KURBAN Ubul1
1. School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China;
2. Network and information center, Xinjiang University, Xinjiang University, Urumqi 830046, China
关键词:
复杂文档维吾尔文档图像文档图像分割特征提取SURF特征FLANN双向匹配KD-Tree+BBF匹配图像检索
Keywords:
complex document imageUyghur document imagedocument image segmentationfeature extractionSURF featureFALNN bidirectional matchingKD-Tree+BBF matchingimage retrieval
分类号:
TP391.1
DOI:
10.11992/tis.201709014
摘要:
针对图像局部特征的词袋模型(Bag-of-Word,BOW)检索研究中聚类中心的不确定性和计算复杂性问题,提出一种由不同种类的距离进行相似程度测量的检索和由匹配点数来检索的方法。这种方法首先需要改进文档图像的SURF特征,有效降低特征提取复杂度;其次,对FAST+SURF特征实现FLANN双向匹配与KD-Tree+BBF匹配,在不同变换条件下验证特征鲁棒性;最后,基于这两种检索方法对已收集整理好的各类维吾尔文文档图像数据库进行检索。实验结果表明:基于距离的相似性度量复杂度次于基于匹配数目的检索,而且两种检索策略都能满足快速、精确查找需求。
Abstract:
This study is aimed at the uncertainty and computational complexity of the clustering center in local image features retrieval based on the bag-of-words (BOW) model. A method to retrieve the measure of similarity degree from different kinds of distance and another method that requires using the matching point number as the basis of retrieval are proposed in this paper. In this method, the SURF feature is first modified to effectively reduce feature extraction complexity, and then FLANN (fast library for approximate nearest neighbors) bidirectional matching and KD-Tree + BBF matching are implemented for FAST + SURF features. Feature robustness is verified under different transformation conditions. Finally, all kinds of Uyghur document images that have been classified and sorted based on these two retrieval methods are retrieved. The results of the retrieval experiments indicate that the similarity degree measure retrieval based on distance is inferior to the retrieval based on matching number, and both of these two retrieval strategies can meet the requirements of fast and accurate searching.

参考文献/References:

[1] 张敬丽, 张会清, 代汝勇. 基于MIC-SURF的快速图像匹配算法[J]. 计算机工程, 2016, 42(1):210-214 ZHANG Jingli, ZHANG Huiqing, DAI Ruyong. Fast image matching algorithm based on MIC-SURF[J]. Computer engineering, 2016, 42(1):210-214
[2] ALFANINDYA A, HASHIM N, ESWARAN C. Content based image retrieval and classification using speeded-up robust features (SURF) and grouped bag-of-visual-words (GBoVW)[C]//Proceedings of 2013 International Conference on Technology, Informatics, Management, Engineering, and Environment. Bandung, Indonesia, 2013:77-82.
[3] 王澍, 吕学强, 张凯, 等. 基于快速鲁棒特征集合统计特征的图像分类方法[J]. 计算机应用, 2015, 35(1):224-230 WANG Shu, LYU Xueqiang, ZHANG Kai, et al. Image classification approach based on statistical features of speed up robust feature set[J]. Journal of computer applications, 2015, 35(1):224-230
[4] 赵璐璐, 耿国华, 李康, 等. 基于SURF和快速近似最近邻搜索的图像匹配算法[J]. 计算机应用研究, 2013, 30(3):921-923 ZHAO Lulu, GENG Guohua, LI Kang, et al. Images matching algorithm based on SURF and fast approximate nearest neighbor search[J]. Application research of computers, 2013, 30(3):921-923
[5] CHEON S H, EOM I K, HA S W, et al. An enhanced SURF algorithm based on new interest point detection procedure and fast computation technique[J]. Journal of real-time image processing, 2016.
[6] 闫利, 陈林. 一种改进的SURF及其在遥感影像匹配中的应用[J]. 武汉大学学报(信息科学版), 2013, 38(7):770-773, 804 YAN Li, CHEN Lin. A modified SURF descriptor and its application in remote sensing images matching[J]. Geomatics and information science of Wuhan university, 2013, 38(7):770-773, 804
[7] 陈剑虹, 韩小珍. 结合FAST-SURF和改进k-d树最近邻查找的图像配准[J]. 西安理工大学学报, 2016, 32(2):213-217, 252 CHEN Jianhong, HAN Xiaozhen. Image matching algorithm combining FAST-SURF and improved k-d tree nearest neighbor search[J]. Journal of Xi’an university of technology, 2016, 32(2):213-217, 252
[8] 罗楠, 孙权森, 陈强, 等. 结合SURF特征点与DAISY描述符的图像匹配算法[J]. 计算机科学, 2014, 41(11):286-290, 300 LUO Nan, SUN Quansen, CHEN Qiang, et al. Image matching algorithm combining SURF feature point and DAISY descriptor[J]. Computer science, 2014, 41(11):286-290, 300
[9] 王亚文, 陈鸿昶, 李邵梅, 等. 基于关键点匹配的多策略尺度自适应跟踪算法[J]. 计算机工程与设计, 2016, 37(1):247-253 WANG Yawen, CHEN Hongchang, LI Shaomei, et al. Multi-strategy scale adaptive tracking algorithm via keypoint matching[J]. Computer engineering and design, 2016, 37(1):247-253
[10] 张凤晶, 王志强, 吴迪, 等. 基于SURF的图像配准改进算法[J]. 长春理工大学学报(自然科学版), 2016, 39(1):112-115 ZHANG Fengjing, WANG Zhiqiang, WU Di, et al. Improved algorithm of image regestration based on SURF[J]. Journal of Changchun university of science and technology (natural science edition), 2016, 39(1):112-115
[11] LIU Yanling, MA Sihang. Research on image based on improved SURF feature matching[C]//Proceedings of 7th International Symposium on Computational Intelligence and Design. Hangzhou, China, 2014:581-584.
[12] EL-GAYAR M M, SOLIMAN H, MEKY N. A comparative study of image low level feature extraction algorithms[J]. Egyptian informatics journal, 2013, 14(2):175-181.
[13] HUANG Liqin, CHEN Caigan, SHEN Henghua, et al. Adaptive registration algorithm of color images based on SURF[J]. Measurement, 2015, 66:118-124.
[14] 安维胜, 余让明, 伍玉铃. 基于FAST和SURF的图像配准算法[J]. 计算机工程, 2015, 41(10):232-235, 239 AN Weisheng, YU Rangming, WU Yuling. Image registration algorithm based on FAST and SURF[J]. Computer engineering, 2015, 41(10):232-235, 239
[15] HUI Dong, YUAN Handian. Research of image matching algorithm based on SURF features[C]//Proceedings of 2012 International Conference on Computer Science and Information Processing (CSIP). Xi’an, China, 2012:1140-1143.
[16] 阿丽亚·巴吐尔. 基于局部特征的维吾尔文印刷体复杂文档图像检索研究[D]. 乌鲁木齐:新疆大学, 2017. ALIYA Batur. Research on Uyghur printed complex document image retrieval based on local feature[D]. Urumchi:Xinjiang University, 2017.

备注/Memo

备注/Memo:
收稿日期:2017-09-17。
基金项目:国家自然科学基金项目(61563052,61163028,61363064);新疆大学博士科研启动基金项目(BS150262),新疆维吾尔自治区高校科研计划创新团队项目(XJEDU2017T002).
作者简介:阿丽亚·巴吐尔,女,1990年生,硕士研究生,主要研究方向为模式识别、图像检索。;努尔毕亚·亚地卡尔,女,1970年生,讲师,中国人工智能学会会员,主要研究方向为图像处理、计算机视觉。;吾尔尼沙·买买提,女,1976年生,讲师,中国人工智能学会会员,主要研究方向为信号与信息处理、模式识别。
通讯作者:库尔班·吾布力.E-mail:urbanu@xju.edu.cn
更新日期/Last Update: 2019-04-25