Method and program

JP7600581B2Active Publication Date: 2024-12-17FUJIFILM BUSINESS INNOVATION CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2020153253
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-03-12
Filing Date
2020-09-11
Publication Date
2024-12-17
Estimated Expiration
2040-09-11

Smart Images

  • Figure 0007600581000012
    Figure 0007600581000012
  • Figure 0007600581000013
    Figure 0007600581000013
  • Figure 0007600581000014
    Figure 0007600581000014
Patent Text Reader

Abstract

To provide a method and a program for classifying image features using a neural network.SOLUTION: A method includes training a neural network using triplet loss processes. Training the neural network includes acquiring an anchor image, selecting a positive image and a negative image, generating an image embedding associated with each of the anchor image, the positive image, and the negative image, classifying image features extracted from the anchor image on the basis of the image embedding of the anchor image, determining an image label location associated with the classified image features, extracting features associated with the determined image label location, and combining the multi-label loss with localized image classification loss and the triplet loss using a weighted loss sum.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Pedestrian re-identification method based on strong discriminant feature learning of distance selection

    CN110728263A

  • Improved font recognition using triplet loss neural network training

    JP2019083002A

  • Surgical video retrieval based on preoperative images

    US20190286652A1

  • Similar Image Search for Radiology

    US20200019617A1