公开(公告)号：US07562057B2

公开(公告)日：2009-07-14

申请号：US11230848

申请日：2005-09-19

申请人： Mauro M. Maggioni ,  Ronald R. Coifman ,  Andreas C. Coppi ,  Gustave L. Davis ,  Richard A. Deverse ,  William G. Fateley ,  Frank Geshwind ,  Frederick J. Warner

发明人： Mauro M. Maggioni ,  Ronald R. Coifman ,  Andreas C. Coppi ,  Gustave L. Davis ,  Richard A. Deverse ,  William G. Fateley ,  Frank Geshwind ,  Frederick J. Warner

IPC分类号： G06N5/00

CPC分类号： G06K9/00127

摘要： An improved method and system for classifying tissue samples comprises determining a tissue type classification based on spectral data of training samples of known target classification. Denoised spectral data is generated from the spectral data based on the tissue type classification. A classifier is then trained using the denoised spectral data to classify the tissue samples.

摘要翻译： 用于分类组织样本的改进的方法和系统包括基于已知目标分类的训练样本的光谱数据确定组织类型分类。 基于组织类型分类从光谱数据生成去噪光谱数据。 然后使用去噪的光谱数据对分类器进行训练，以对组织样本进行分类。

公开(公告)号：US07219086B2

公开(公告)日：2007-05-15

申请号：US11075257

申请日：2005-03-07

申请人： Frank Geshwind ,  Ronald R. Coifman ,  Andreas Coppi ,  Gustave L. Davis ,  Richard A. Deverse ,  William G. Fateley ,  Frederick J. Warner

发明人： Frank Geshwind ,  Ronald R. Coifman ,  Andreas Coppi ,  Gustave L. Davis ,  Richard A. Deverse ,  William G. Fateley ,  Frederick J. Warner

IPC分类号： G06N5/00

CPC分类号： G06K9/4652 ,  G01J3/02 ,  G01J3/0208 ,  G01J3/021 ,  G01J3/0218 ,  G01J3/10 ,  G01J3/28 ,  G01J3/2823 ,  G01J3/36 ,  G06K9/0063

摘要： A hyper-spectral analysis method for characterizing or distinguishing diverse elements within hyper-spectral images. A plurality of patches of pixels from within the hyper-spectral images are extracted as being patches around pixels of the elements to be characterized or distinguished. The statistics of spectra for each patch of pixels are computed. A first classifier is computed from frequency-wise standard deviation of the spectra in each patch and a set of second classifiers are computed from principal components of the spectral in each patch. A combined classifier is computed based on the output of the first classifier and at least one of the second classifiers. The elements are characterized or distinguished based on the output of at least one of the classifiers, preferably the combined classifier.

摘要翻译： 用于表征或区分超光谱图像中不同元素的超光谱分析方法。 从超光谱图像内的多个像素块被提取为待表征或区分的元素的像素周围的斑块。 计算每个像素块的光谱统计。 第一分类器是从每个贴片中的频谱的逐频标准偏差计算的，并且一组第二分类器是根据每个贴片中的光谱的主分量计算的。 基于第一分类器的输出和至少一个第二分类器来计算组合分类器。 基于至少一个分类器的输出来表征或区分元素，优选地是组合分类器。