发明名称 PROBABILISTIC INTENSITY SIMILARITY MEASURE BASED ON NOISE DISTRIBUTIONS
摘要 Technologies for comparing observed intensities using a probabilistic similarity measure. In the probabilistic similarity measure example, there is no attempt to estimate a true intensity. Rather, the similarity of two observed intensities is defined as the likelihood that they each resulted from the same but unknown true identity while taking into account the noise characteristics of the camera observing the intensities. Since the true intensity is unknown, all possible true intensities are taken into account, rather than using a specific true intensity estimate. The probabilistic similarity measure indicates the degree to which two intensities correspond to the same intensity without estimating a true scene intensity value.
申请公布号 US2009268938(A1) 申请公布日期 2009.10.29
申请号 US20080110362 申请日期 2008.04.28
申请人 MICROSOFT CORPORATION 发明人 MATSUSHITA YASUYUKI;LIN STEPHEN SSU-TE
分类号 G06K9/00 主分类号 G06K9/00
代理机构 代理人
主权项
地址