- 专利标题: Image analysis neural network systems
-
申请号: US15495313申请日: 2017-04-24
-
公开(公告)号: US10546242B2公开(公告)日: 2020-01-28
- 发明人: Arpit Jain , Swaminathan Sankaranarayanan , David Scott Diwinsky , Ser Nam Lim , Kari Thompson
- 申请人: General Electric Company
- 申请人地址: US NY Schenectady
- 专利权人: GENERAL ELECTRIC COMPANY
- 当前专利权人: GENERAL ELECTRIC COMPANY
- 当前专利权人地址: US NY Schenectady
- 代理机构: The Small Patent Law Group LLC
- 代理商 Christopher R. Carroll
- 主分类号: G06N7/00
- IPC分类号: G06N7/00 ; G06K9/62 ; G06N3/08
摘要:
A method includes determining object class probabilities of pixels in a first input image by examining the first input image in a forward propagation direction through layers of artificial neurons of an artificial neural network. The object class probabilities indicate likelihoods that the pixels represent different types of objects in the first input image. The method also includes selecting, for each of two or more of the pixels, an object class represented by the pixel by comparing the object class probabilities of the pixels with each other, determining an error associated with the object class that is selected for each pixel of the two or more pixels, determining one or more image perturbations by back-propagating the errors associated with the object classes selected for the pixels of the first input image through the layers of the neural network without modifying the neural network, and modifying a second input image by applying the one or more image perturbations to one or more of the first input image or the second input image prior to providing the second input image to the neural network for examination by the neurons in the neural network for automated object recognition in the second input image.
公开/授权文献
- US20180253866A1 IMAGE ANALYSIS NEURAL NETWORK SYSTEMS 公开/授权日:2018-09-06
信息查询
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06N | 基于特定计算模型的计算机系统 |
G06N7/00 | 基于特定数学模式的计算机系统 |