Center for Post-Doctoral Studies of Computer Science and Technology, Harbin University of Science and Technology , Harbin , Heilongjiang , China.
College of Computer and Information Engineering, Harbin University of Commerce , Harbin , Heilongjiang , China.
Comput Assist Surg (Abingdon). 2019 Oct;24(sup1):72-80. doi: 10.1080/24699322.2018.1560087. Epub 2019 Jan 28.
Color, texture, and shape are the common features used for the retrieval systems. However, many medical images have a spot of color information. Therefore, the discriminative texture and shape features should be extracted to obtain a satisfied retrieval result. In order to increase the credibility of the retrieval process, many features can be combined to be used for medical image retrieval. Meanwhile, more features require more processing time, which will decrease the retrieval speed. In this paper, wavelet decomposition is adopted to generate different resolution images. Bag-of-feature, texture, and LBP feature are extracted from three different-level wavelet images. Finally, the similarity measure function is obtained by fusing these three types of features. Experimental results show that the proposed multi-feature fusion method can achieve a higher retrieval accuracy with an acceptable retrieval time.
颜色、纹理和形状是检索系统中常用的特征。然而，许多医学图像的颜色信息是斑点状的。因此，应该提取有区别的纹理和形状特征，以获得满意的检索结果。为了提高检索过程的可信度，可以结合使用许多特征进行医学图像检索。同时，更多的特征需要更多的处理时间，这将降低检索速度。在本文中，采用小波分解生成不同分辨率的图像。从三个不同层次的小波图像中提取特征，包括特征袋、纹理和 LBP 特征。最后，通过融合这三种类型的特征来获得相似性度量函数。实验结果表明，所提出的多特征融合方法可以在可接受的检索时间内获得更高的检索精度。
