Title:
PROCESSING METHOD AND PROCESSING DEVICE USING THIS
Document Type and Number:
WIPO Patent Application WO/2019/159419
Kind Code:
A1
Abstract:
An input unit 132 inputs an image to be processed. A processing unit 114 subjects the image inputted to the image unit 132 to processing with a convolutional neural network from which fully connected layers have been removed. The convolutional neural network in said processing unit 114 comprises a convolution layer and a pooling layer. An output unit 136 outputs the processing results of the processing unit 114. Here, in the convolutional neural network in the processing unit 114, the convolutional layer filter is trained with the processing results having a 1×1 spatial dimension.
More Like This:
Inventors:
HORII TOSHIHIDE
Application Number:
PCT/JP2018/036248
Publication Date:
August 22, 2019
Filing Date:
September 28, 2018
Export Citation:
Assignee:
PANASONIC IP MAN CO LTD (JP)
International Classes:
G06T7/00
Other References:
LIN, MIN ET AL.: "Network In Network", ARXIV.ORG, 4 March 2014 (2014-03-04), pages 1 - 10, XP055632227
KRIZHEVSKY, ALEX ET AL.: "Learning multiple layers of features from tiny images", MASTER'S THESIS, DEPARTMENT OF COMPUTER SCIENCE, 8 April 2009 (2009-04-08), pages FP - 58, XP055632229, Retrieved from the Internet
KIMURA, TAKATO ET AL.: "Automatic Crack Detection in Infrastructure Inspection Using Fully Convolutional Network", RESEARCH REPORT OF INFORMATION PROCESSING SOCIETY OF JAPAN : MATHEMATICAL MODELING AND PROBLEM SOLVING(MPS, vol. 2017 -MP, no. 2, 18 September 2017 (2017-09-18), pages 1 - 6, XP055723550, Retrieved from the Internet
OKATANI, TAKAYUKI: "Research Frontiers in Neural Network, Research Trend of Deep Learning for Visual Recognition-Advances of Convolutional Neural Networks and Their Use", JOURNAL OF THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE, vol. 31, no. 2, 1 March 2016 (2016-03-01), pages 169 - 179, XP009522339
JONATHAN LONGEVAN SHELHAMERTREVOR DARRELL: "Fully Convolutional Networks for Semantic Segmentation", THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR, 2015, pages 3431 - 3440
See also references of EP 3754593A4
KRIZHEVSKY, ALEX ET AL.: "Learning multiple layers of features from tiny images", MASTER'S THESIS, DEPARTMENT OF COMPUTER SCIENCE, 8 April 2009 (2009-04-08), pages FP - 58, XP055632229, Retrieved from the Internet
KIMURA, TAKATO ET AL.: "Automatic Crack Detection in Infrastructure Inspection Using Fully Convolutional Network", RESEARCH REPORT OF INFORMATION PROCESSING SOCIETY OF JAPAN : MATHEMATICAL MODELING AND PROBLEM SOLVING(MPS, vol. 2017 -MP, no. 2, 18 September 2017 (2017-09-18), pages 1 - 6, XP055723550, Retrieved from the Internet
OKATANI, TAKAYUKI: "Research Frontiers in Neural Network, Research Trend of Deep Learning for Visual Recognition-Advances of Convolutional Neural Networks and Their Use", JOURNAL OF THE JAPANESE SOCIETY FOR ARTIFICIAL INTELLIGENCE, vol. 31, no. 2, 1 March 2016 (2016-03-01), pages 169 - 179, XP009522339
JONATHAN LONGEVAN SHELHAMERTREVOR DARRELL: "Fully Convolutional Networks for Semantic Segmentation", THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR, 2015, pages 3431 - 3440
See also references of EP 3754593A4
Attorney, Agent or Firm:
MUNETA Satoshi (JP)
Download PDF:
Previous Patent: POWER SUPPLY SYSTEM, SERVER, AND PORTABLE POWER SUPPLY DEVICE
Next Patent: MOBILE BODY OPERATION MANAGEMENT SYSTEM AND MOBILE BODIES
Next Patent: MOBILE BODY OPERATION MANAGEMENT SYSTEM AND MOBILE BODIES