Title:
画像分類装置、方法およびプログラム
Document Type and Number:
Japanese Patent JP6525912
Kind Code:
B2
Abstract:
A three dimensional image is classified into a plurality of classes by a convolutional neural network, in which a plurality of processing layers are connected hierarchically. The convolutional neural network includes: a convoluting layer that administers a convoluting process on each of a plurality of two dimensional images, which are generated by the neural network administering a projection process on the three dimensional image according to a plurality of processing parameters; and a pooling layer that pools the values of the same position within each of the plurality of two dimensional images which have undergone the convoluting process.
Inventors:
Kitamura Yoshiro
Application Number:
JP2016057865A
Publication Date:
June 05, 2019
Filing Date:
March 23, 2016
Export Citation:
Assignee:
FUJIFILM Corporation
International Classes:
G06T7/00; A61B6/03; G06T1/00; G06V10/764
Domestic Patent References:
| JP2015215837A | ||||
| JP2009207677A | ||||
| JP2014008402A | ||||
| JP2011227870A | ||||
| JP2007014706A |
Foreign References:
| WO2015066628A1 |
Other References:
近藤 正、上野 淳二,“最適なネットワーク構造の自己組織化能力を備えた改良形GMDH-typeニューラルネットワークと心臓領域の3次元医用画像認識への応用”,電子情報通信学会技術研究報告,日本,社団法人電子情報通信学会,2009年 7月 8日,Vol.109, No.127,pp.57-62
Attorney, Agent or Firm:
Patent Service Corporation Taiyo International Patent Office