[1]宋涛,刘刚..一种基于内容的文档图像检索方法[J].郑州大学学报(工学版),2010,31(01):124.
SONG Tao,LIU Gang.A Content——Based Algorithm for Document Image Retrieval[J].Journal of Zhengzhou University (Engineering Science),2010,31(01):124.
点击复制
一种基于内容的文档图像检索方法(
)
《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]
- 卷:
-
31卷
- 期数:
-
2010年01期
- 页码:
-
124
- 栏目:
-
- 出版日期:
-
2010-01-30
文章信息/Info
- Title:
-
A Content——Based Algorithm for Document Image Retrieval
- 作者:
-
宋涛; 刘刚.
-
河南大学计算机与信息工程学院,河南,开封,475001
- Author(s):
-
SONG Tao; LIU Gang
-
1．Institute of Computer and Information Engineering，Henan University，Kaifeng 475001，China；2．Higer Education AdmissionOffice of Henan。Zhengzhou 45002．China
-
- Keywords:
-
CBIR; layout analysis; document image; mathematical morphology; image segmentation; image feature
- 文献标志码:
-
A
- 摘要:
-
使用一个图像作为查询检索输入,根据该图像的版面分析特征、统计特征、纹理特征与数据库中图像的相似程度检索图像.该检索方法首先利用数学形态学对文档图像进行段落分割和行分割,作为文档图像的版面结构特征;然后根据图像的统计特征包括字符数、统计数特征、纹理特征给出文档图像抽取算法;最后给出检索算法模型.实验结果表明,本算法具有较好的查准率和查全率,在基于内容的文档图像检索中具有应用价值.
- Abstract:
-
This paper studies the content—based image retrieval for document image．Given aquery image，the system returns overall similar images by layout analysis and statistic feature in image database．First，seg·ment an image into paragraphs and lines based on mathematical morphology，return the image layout analysisresults；and then compute the image statistic feature include characters，statistic count feature and texture togive distil arithmetic of the document image．In the end，we describe the matching model．This algorithm istested through trials and errors．The experiment results indicate this algorithm is good at precision and recall．This algorithm is highly valuable in document image retrieval．
更新日期/Last Update:
1900-01-01