Title:
IMAGE RECOGNITION EVALUATION PROGRAM, IMAGE RECOGNITION EVALUATION METHOD, EVALUATION DEVICE, AND EVALUATION SYSTEM
Document Type and Number:
WIPO Patent Application WO/2021/014809
Kind Code:
A1
Abstract:
This image recognition evaluation program is executed by an evaluation device that evaluates the recognition accuracy of an image recognition device for performing image segmentation. The evaluation device is made to perform image processing on an input image input to the image recognition device and generate a plurality of processed input images. The evaluation device is subsequently made to input the generated plurality of processed input images to the image recognition device and obtain a plurality of output images that are classified as a result of the image processing device performing image segmentation. The evaluation device is then made to calculate a variance value for the output images on the basis of the acquired plurality of output images.
More Like This:
| WO/2021/072484 | DIFFERENTIAL BRAIN NETWORK ANALYSIS |
| WO/2020/168934 | MEDICAL IMAGE SEGMENTATION METHOD, APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM |
| WO/2020/015822 | PARTITIONING A MEDICAL IMAGE |
Inventors:
SUGAHARA SHUN (JP)
TAGUCHI KENSUKE (JP)
TAGUCHI KENSUKE (JP)
Application Number:
PCT/JP2020/022928
Publication Date:
January 28, 2021
Filing Date:
June 10, 2020
Export Citation:
Assignee:
KYOCERA CORP (JP)
International Classes:
G06T7/11
Foreign References:
| JP2018097807A | 2018-06-21 | |||
| JP2018535491A | 2018-11-29 | |||
| JP2019109691A | 2019-07-04 |
Other References:
IKU SHIMIZU, MASAKI SAMEJIMA, YUSUKE KANNO, YASUYUKI MATSUSHITA : "Semantic segmentation using label likelihood as a global feature", IEICE TECHNICAL REPORT, vol. 117, no. 513 (PRMU2017-190), 16 April 2018 (2018-04-16), JP , pages 109 - 114, XP009532967, ISSN: 0913-5685
HENGSHUANG ZHAO ET AL.: "Pyramid scene parsing network", IEEE CONF. ON COMPUTER VISION AND PATTERN RECOGNITION, 2017
ALEX KENDALL ET AL.: "Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding", ARXIV: 1511.02680V2, 10 October 2016 (2016-10-10)
See also references of EP 4002270A4
HENGSHUANG ZHAO ET AL.: "Pyramid scene parsing network", IEEE CONF. ON COMPUTER VISION AND PATTERN RECOGNITION, 2017
ALEX KENDALL ET AL.: "Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding", ARXIV: 1511.02680V2, 10 October 2016 (2016-10-10)
See also references of EP 4002270A4
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: