低级特征和语义特征相结合的医学图像检索方法

邵虹; 崔文成; 张继武; 赵宏

doi:10.11834/jig.20040239

学术论文与技术报告 | 浏览量 : 0 下载量: 295 CSCD: 0

PDF
导出
分享
收藏
专辑

低级特征和语义特征相结合的医学图像检索方法
Medical Image Retrieval Based on Low Level Featuresand Semantic Features
2004年9卷第2期页码：220
纸质出版：2004
DOI： 10.11834/jig.20040239
稿件说明：

移动端阅览

邵虹, 崔文成, 张继武, 赵宏. 低级特征和语义特征相结合的医学图像检索方法[J]. 中国图象图形学报, 2004,9(2):220. DOI： 10.11834/jig.20040239.

Medical Image Retrieval Based on Low Level Featuresand Semantic Features[J]. Journal of Image and Graphics, 2004, 9(2): 220. DOI： 10.11834/jig.20040239.

摘要

提出了一种将图像本身的低级特征和语义特征描述相结合的医学图像检索方法。首先提取图像的灰度特征、矩特征和纹理特征，进一步采用遗传算法进行最优特征的选择，由于这些低层特征对图像的描述与人类对图像的描述存在较大差异，直接利用这些特征作为检索依据常得不到满意的结果，因此需要进一步提取语义特征，将影像报告中医生给出的关于图像的描述作为语义内容进行相似性检索。实验结果表明，综合低级特征和语义特征的检索比仅利用低级特征的检索更接近于人的视觉理解。

Abstract

In this paper

a new medical image retrieval approach based on low level features and semantic features is proposed. The low level features include gray

moment and texture features

which are selected by genetic algorithm. These features can't express the human's understanding of the images. Directly using these features can't get satisfying results

so the semantic features are needed. The image describing in the image report by doctors are chosen for semantic content. Experiment results show that the retrieval result by low features and semantic features are better than only by low features.