Processing

Please wait...

Settings

Settings

Goto Application

1. WO2019049365 - INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING PROGRAM

Publication Number WO/2019/049365
Publication Date 14.03.2019
International Application No. PCT/JP2017/032672
International Filing Date 11.09.2017
IPC
G06T 7/00 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
CPC
G06K 9/6217
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
G06K 9/6227
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6227Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
G06K 9/6229
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6228Selecting the most significant subset of features
6229by using evolutionary computational techniques, e.g. genetic algorithms
G06K 9/6262
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6262Validation, performance evaluation or active pattern learning techniques
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
G06N 3/126
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
12using genetic models
126Genetic algorithms, i.e. information processing using digital simulations of the genetic system
Applicants
  • 富士通株式会社 FUJITSU LIMITED [JP]/[JP]
Inventors
  • 長門毅 NAGATO, Tsuyoshi
  • 岡本浩明 OKAMOTO, Hiroaki
  • 肥塚哲男 KOEZUKA, Tetsuo
Agents
  • 片山修平 KATAYAMA, Shuhei
Priority Data
Publication Language Japanese (JA)
Filing Language Japanese (JA)
Designated States
Title
(EN) INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING PROGRAM
(FR) DISPOSITIF, PROCÉDÉ ET PROGRAMME DE TRAITEMENT D'INFORMATIONS
(JA) 情報処理装置、情報処理方法及び情報処理プログラム
Abstract
(EN)
According to the present invention, in order to shorten a time required to relearn an image processing program, a determination unit 121 determines a plurality of initial individuals and includes the determined initial individuals in a population 11, and an extraction unit 122 extracts at least two master individuals from the population 11. In addition, a generation unit 123 generates a slave individual from the extracted master individuals on the basis of genetic programming, and a processing unit 124 calculates the fitness of the slave individual by using learning data, and determines an image processing program to be used for image processing or updates the population 11 on the basis of the calculated fitness. Then, the determination unit 121 determines, as a part of initial individuals in a relearning process, at least a portion of the individuals that have been included in the population 11 when the image processing program to be used for the image processing has been determined immediately before.
(FR)
Selon la présente invention, afin de raccourcir le temps nécessaire au réapprentissage d'un programme de traitement d'image, une unité de détermination (121) détermine une pluralité d'individus initiaux et comprend les individus initiaux déterminés dans une population (11), et une unité d'extraction (122) extrait au moins deux individus maîtres à partir de la population (11). En outre, une unité de génération (123) génère un individu esclave à partir des individus maîtres extraits sur la base d'une programmation génétique, et une unité de traitement (124) calcule la condition physique de l'individu esclave à l'aide de données d'apprentissage, et détermine un programme de traitement d'image à utiliser pour le traitement d'image ou met à jour la population sur la base de la condition physique calculée. Ensuite, l'unité de détermination (121) détermine, en tant que partie d'individus initiaux dans un processus de réapprentissage, au moins une partie des individus qui ont été inclus dans la population lorsque le programme de traitement d'image à utiliser pour le traitement d'image a été déterminé immédiatement avant.
(JA)
画像処理プログラムの再学習に要する時間を短縮するため、決定部121は、複数の初期個体を決定して母集団11に含め、抽出部122は、母集団11から少なくとも2つの親個体を抽出する。また、生成部123は、遺伝的プログラミングに基づき、抽出した親個体から子個体を生成し、処理部124は、学習用データを用いて、子個体の適応度を算出し、算出した適応度に基づいて、画像処理に用いる画像処理プログラムを決定する、又は母集団11を更新する。そして、決定部121は、直前に画像処理に用いる画像処理プログラムを決定したときに母集団11に含まれていた個体の少なくとも一部を、再学習処理における初期個体の一部として決定する。
Latest bibliographic data on file with the International Bureau