权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Fast Retrieval of Massive linage Archives based on Similarity of I cleat Feature Descriptor

基于I cleat特征描述符相似度的海量谱系档案快速检索

基本信息

批准号：
18300061
负责人：
KAWASHIMA Toshio
金额：
$ 4.35万
依托单位：
Future University-Hakodate
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (B)
财政年份：
2006
资助国家：
日本
起止时间：
2006 至 2007
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-18300061/
关键词：
ARCHIVES IMAGE RETRIEVAL LOCAL DESCRIPTOR HASHING

项目摘要

In the research projects we developed fast retrieval method of historical document database using local feature of images. We also developed codes for local feature detection for MX-1 parallel processors, and LSH algorithm for fast character recognition. The followings are the outcomes of the project.1 Historical document retrieval based on PCAEigenspace method (PCA) applied to document image matching showed fast retrieval of document database. Image of character strings are sliced into slit-wise small images and reduced the dimension using eigenspace method. The performance of retrieval for was 73-93 percent.2 Retrieval using gradient histogramWe refined feature vector based on PCA vector to gradient histogram. The approach improved the performance of PCA to 95-98 percent.3 Application of local feature matchingWe developed a transcript mapping software for historical document based on the pattern of frequency of words in the document using method 1.4 Fast computation of local feature using parallel processorAlgorithms of SURF image feature are implemented on a MX-1 parallel processor. Computation of scale detection and gradient distribution calculation are accelerated using the processor.5 Locality sensitive hashing of local feature vectorWe discussed fast dictionary retrieval method for reproduction of historical document. We implemented Locality Sensitive Hashing algorithm for document image retrieval to search similar character image from dictionary of character image examples.

在研究项目中，我们开发了利用图像局部特征的历史文档数据库的快速检索方法。我们还开发了用于 MX-1 并行处理器的局部特征检测的代码，以及用于快速字符识别的 LSH 算法。该项目的成果如下：1基于PCAEigenspace方法（PCA）的历史文档检索应用于文档图像匹配，显示了文档数据库的快速检索。将字符串图像分割成狭缝小图像，并使用特征空间方法降低维度。检索性能为73-93%。 2 使用梯度直方图检索我们将基于PCA向量的特征向量细化为梯度直方图。该方法将PCA的性能提高到95-98％。3局部特征匹配的应用我们使用方法1.4基于文档中单词的频率模式开发了历史文档的转录映射软件使用并行处理器快速计算局部特征SURF图像特征算法在MX-1并行处理器上实现。使用处理器加速尺度检测和梯度分布计算的计算。5局部特征向量的局部敏感散列我们讨论了用于再现历史文档的快速字典检索方法。我们实现了用于文档图像检索的局部敏感哈希算法，以从字符图像示例字典中搜索相似的字符图像。