Title:
仮想３次元深層ニューラルネットワークを利用する画像解析装置及び方法
Document Type and Number:
Japanese Patent JP6979664
Kind Code:
B2
Abstract:
Disclosed are an apparatus and a method for image analysis using a virtual three-dimensional deep neural network. The apparatus for image analysis comprises: an image acquisition unit for stacking a plurality of two-dimensional image data in a predetermined order; a three-dimensional image generation unit for generating a plurality of three-dimensional data on the basis of different types of multiple items of information for the plurality of two-dimensional image data in a stacked form from the image acquisition unit; and a deep learning algorithm analysis unit for applying a two-dimensional convolutional neural network to each of the plurality of three-dimensional data from the three-dimensional image generation unit, and combining results of applying the two-dimensional convolutional neural network to the plurality of three-dimensional data.
More Like This:
| WO/2019/102072 | METHOD AND SYSTEM FOR IDENTIFYING AUTHENTICITY OF AN OBJECT |
| WO/2021/176106 | A SYSTEM FOR PRODUCING A BIOPHARMACEUTICAL PRODUCT |
| WO/2017/091833 | AUTOMATED CARDIAC VOLUME SEGMENTATION |
Inventors:
Kim, Dong Min
Baek, John Fan
Lee, Myeong Jae
Son, This
Kang, Shin Wook
Kim, Wante
Kim, Don-Og
Baek, John Fan
Lee, Myeong Jae
Son, This
Kang, Shin Wook
Kim, Wante
Kim, Don-Og
Application Number:
JP2019552542A
Publication Date:
December 15, 2021
Filing Date:
March 23, 2018
Export Citation:
Assignee:
JLC Inspection
International Classes:
G06N3/02; G06T7/00
Other References:
P. Wang et al.,"Action Recognition From Depth Maps Using Deep Convolutional Neural Networks",IEEE Transactions on Human-Machine Systems,米国,IEEE,2016年08月,vol. 46, no. 4,pp. 498-509
Attorney, Agent or Firm:
▲吉▼川 俊雄
Kana Ichikawa
Kana Ichikawa