发明名称 IMAGE PROCESSING APPARATUS, METHOD OF PROCESSING IMAGE, AND PROGRAM
摘要 An image processing apparatus calculating to determine one category, to which an input image data belongs, among categories, which are provided to classify image data, includes a convolution processing unit which performs a convolution process using a first coefficient used for calculating to determine the one category and previously learnt; total combination processing units which are prepared for each category performs a total combination process for a processing result obtained by the convolution processing unit using a second coefficient used for calculating to determine the one category and previously learnt, and calculates to determine the one category; and a normalization unit which performs normalization of a processing result obtained by the total combination processing unit for each category, wherein the convolution processing unit performs learning of the first coefficient in common with the categories, and the total combination processing unit performs learning of the second coefficient for each category.
申请公布号 US2015332126(A1) 申请公布日期 2015.11.19
申请号 US201514710700 申请日期 2015.05.13
申请人 HIKIDA Satoshi 发明人 HIKIDA Satoshi
分类号 G06K9/62;G06T3/40;G06K9/00;G06K9/46;H04N5/232;H04N5/235 主分类号 G06K9/62
代理机构 代理人
主权项 1. An image processing apparatus that calculates to determine one category, to which an input image data belongs, among a plurality of categories, which are provided to classify a plurality of image data, the image processing apparatus comprising: a convolution processing unit which performs a convolution process using a first coefficient used for calculating to determine the one category and previously learnt by the convolution processing unit; a plurality of total combination processing units which are prepared for each of the plurality of categories,performs a total combination process for a processing result obtained by the convolution processing unit using a second coefficient used for calculating to determine the one category and previously learnt by the total combination processing unit, andcalculates to determine the one category; and a normalization unit which performs normalization of a processing result obtained by the total combination processing unit for each of the plurality of categories, wherein the convolution processing unit performs learning of the first coefficient in common with the plurality of categories, and wherein the total combination processing unit performs learning of the second coefficient for each of the plurality of categories.
地址 Kanagawa JP