基于灰度直方图与改进Hu不变矩的维吾尔文关键词图像二次检索

宋志平; 朱亚俐; 徐学斌; 吾尔尼沙·买买提; 库尔班·吾布力

doi:10.13568/j.cnki.651094.651316.2021.04.10.0003

您当前的位置：

首页 >

文章列表页 >

基于灰度直方图与改进Hu不变矩的维吾尔文关键词图像二次检索

更新时间：2026-01-21

- 基于灰度直方图与改进Hu不变矩的维吾尔文关键词图像二次检索
- Journal of Xinjiang University (Natural Science Edition in Chinese and English) Vol. 39, Issue 3, Pages: 323-330(2022)
- 作者机构：
  
  1. 新疆大学信息科学与工程学院
  2. 新疆多语种信息技术重点实验室
- 作者简介：
- 基金信息：
- DOI：10.13568/j.cnki.651094.651316.2021.04.10.0003
  CLC： H215;TP391.41
- Published：2022
- 稿件说明：
移动端阅览
[1]宋志平,朱亚俐,徐学斌,等.基于灰度直方图与改进Hu不变矩的维吾尔文关键词图像二次检索[J].新疆大学学报(自然科学版)(中英文),2022,39(03):323-330.
[1]宋志平,朱亚俐,徐学斌,等.基于灰度直方图与改进Hu不变矩的维吾尔文关键词图像二次检索[J].新疆大学学报(自然科学版)(中英文),2022,39(03):323-330. DOI： 10.13568/j.cnki.651094.651316.2021.04.10.0003.

DOI：10.13568/j.cnki.651094.651316.2021.04.10.0003.

摘要

维吾尔文文字具有粘连性大、结构不封闭等特点，这给维吾尔文关键词图像检索造成了极大的困难．为提高维吾尔文文档图像检索效率，提出一种基于灰度直方图与改进Hu不变矩的关键词图像二次检索算法，该算法对单词图像进行两次检索：粗略检索和二次检索．在粗略检索阶段，对切分后的单词图像提取灰度直方图特征并对单词数据库进行粗略匹配，在保证召回率的情况下，过滤掉部分无关单词图像形成候选单词库．在粗略匹配的基础上进行精确匹配，使用改进的Hu不变矩对关键词图像的轮廓特征进行描述，该方法在Hu不变矩中将离心率、区域矩和结构矩统一，可以有效地描述图像的轮廓信息．在包含115张纯文本维吾尔文文档图像数据库上进行实验，其检索准确率平均值为78.36%，召回率平均值为81.68%.

Abstract

Uygur characters have the characteristics of large adhesion and non-closed structure

which makes it very difficult for Uygur keyword image retrieval. In order to improve the efficiency of Uygur document image retrieval

a keyword image secondary retrieval algorithm based on gray histogram and improved Hu invariant moment is proposed. The algorithm retrieves word images twice: rough retrieval and secondary retrieval. In the rough retrieval stage

the gray histogram feature is extracted from the segmented word image and the word database is roughly matched

under the condition of ensuring the recall rate some irrelevant word images are filtered out to form a candidate word library. Accurate matching is carried out on the basis of rough matching and the improved Hu invariant moment is used to describe the contour features of keyword images

this method unifies the eccentricity regional moment and structural moment in Hu invariant moment

which can effectively describe the boundary information of the image. The experiment is carried out on the image database containing 115 plain text Uygur documents. The average retrieval accuracy is 78.36% and the average recall is 81.68%.

关键词

Keywords

references

LEE Y K,SONG J,WON Y.Improving personal information detection using OCR feature recognition rate[J].The Journal of Super Computing,2019,75(4):1941-1952.

MANMATHA R,HAN C,RISEMAN E M.Word spotting:a new approach to indexing handwriting[C].Amherst:Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition,IEEE,1996:631-637.

MANMATHA R,HAN C,RISEMAN E M,et al.Indexing handwriting using word matching[C].Bethesda:Proceedings of the First ACM International Conference on Digital Libraries,ACM International Conference on Digital Libraries,1996:151-159.

ROTHFEDER J L,FENG S,RATH T M.Using corner feature correspondences to rank word images by similarity[C].Madison:2003 Conference on Computer Vision and Pattern Recognition Workshop,IEEE,2003,3:30.

VADIVUKARASSI M,PUVIARASAN N,ARUNA P.A frame-work of keyword based image retrieval using proposed Hog Sift feature extraction method from Twitter dataset[J].Procedia Computer Science,2018,13(4):1422-1431.

NIAZ H A,AKRAM U,AKBAR U.Word spotting using clustering on extracted DCT and DWT features[C].Lahore:2018International Conference on Engineering and Emerging Technologies(ICEET),IEEE,2018:1-4.

黄祥琳,高芸,杨丽芳,等.一种基于关键词的中文文档图像检索方法[J].中文信息学报,2017,4(5):61-64.

魏宏喜.蒙古文古籍图像检索技术研究[D].呼和浩特:内蒙古大学,2012.

GUO G L,WEI H X,SU X.A case study of BOVW for keyword spotting on historical Mongolian document images[C].Datong:2016 9th International Congress on Image and Signal Processing,Bio Medical Engineering and Informatics(CISP-BMEI),IEEE,2016:374-378.

周文杰.基于关键词的维吾尔文文档图像检索技术研究[D].乌鲁木齐:新疆大学,2019.

李静静,木特力甫·马木提,吾尔尼沙·买买提,等.基于层级匹配的维吾尔文关键词文档图像检索[J].计算机工程与设计,2020,41(4):1062-1069.

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.

周文杰,木特力铺·马木提,吾尔尼沙·买买提,等.基于形态学梯度算法的维吾尔文文档图像单词切分[J].计算机工程与设计,2019,40(9):2552-2557.

欧阳彝华,黄芳,周敏.基于灰度直方图的心脏图像检索[J].计算机技术与发展,2009,19(9):125-127+203.

李顺山,庄天戈,陈辉.基于灰度直方图和互相关方法的医学图像检索[J].上海交通大学学报,2001,35(5):694-698.

HU M K.Visual pattern recognition by moment invariants[J].IRE Transactions on Information Theory,1962,8(2):179-187.

Views

217

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

⁰