Lahmiri Salim, Boukadoum Mounir
Department of Computer Science, University of Québec at Montréal, C P 8888, SuccursaleC-V, Montréal, Québec H3C 3P8, Canada.
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:5104-7. doi: 10.1109/IEMBS.2011.6091264.
A new methodology to automatically extract features from mammograms and classify them is presented. It relies on a hybrid processing system that sequentially uses the discrete cosine transform (DCT) to obtain the high frequency component of the mammogram and then applies the Radon transform to the obtained DCT image in order to extract its directional features. The features are subsequently fed to a support vector machine for classification. The approach was tested on a database of one hundred images and shows improved classification accuracy in comparison to using the discrete cosine transform or the Radon transform alone, as done in others works.
提出了一种从乳房X光照片中自动提取特征并进行分类的新方法。它依赖于一个混合处理系统，该系统依次使用离散余弦变换（DCT）来获取乳房X光照片的高频分量，然后将Radon变换应用于所获得的DCT图像，以提取其方向特征。随后将这些特征输入到支持向量机进行分类。该方法在一个包含一百张图像的数据库上进行了测试，与其他研究中单独使用离散余弦变换或Radon变换相比，显示出更高的分类准确率。
