Title:
モデル生成装置、モデル生成方法、画像処理装置、画像処理方法、及び、プログラム
Document Type and Number:
Japanese Patent JP7367857
Kind Code:
B2
Abstract:
In a model generation apparatus, a training data selection means selects sets of training data from a plurality of fingerprint images. A learning means trains a model that corrects a fingerprint image, by using the sets of training data. An evaluation value calculation means calculates evaluation values of results acquired by inputting the plurality of fingerprint images into the trained model. A model update means updates a model to be trained, based on the evaluation values. Next, the training data selection means determines sets of training data to be selected from the plurality of fingerprint images based on the evaluation values.
Inventors:
Satoshi Hirokawa
Application Number:
JP2022512890A
Publication Date:
October 24, 2023
Filing Date:
March 30, 2020
Export Citation:
Assignee:
NEC
International Classes:
G06T7/00; G06T1/40
Domestic Patent References:
| JP2019191913A | ||||
| JP2016045501A |
Other References:
Indu Joshi et al.,"Latent Fingerprint Enhancement Using Generative Adversarial Networks",2019 IEEE Winter Conference on Applications of Computer Vision (WACV),米国,IEEE,2019年01月07日,pp.895-903
Li Wang et al.,"Fingerprint Reference Point Detection Based on Local Ridge Orientation Patterns of Fingerprints",The 2012 International Joint Conference on Neural Networks (IJCNN),米国,IEEE,2012年06月10日,pp.1-8
Li Wang et al.,"Fingerprint Reference Point Detection Based on Local Ridge Orientation Patterns of Fingerprints",The 2012 International Joint Conference on Neural Networks (IJCNN),米国,IEEE,2012年06月10日,pp.1-8
Attorney, Agent or Firm:
Satonobu Nakamura
Tatsuo Egami
Hiroshi Miwa
Tatsuo Egami
Hiroshi Miwa
Previous Patent: Semiconductor device and semiconductor device manufacturing method
Next Patent: Imaging system, imaging method and imaging program
Next Patent: Imaging system, imaging method and imaging program