Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 25.01.2022 at 9:00 AM CET
Settings

Settings

Goto Application

1. WO2021242319 - SYSTEMS AND METHODS FOR FEATURE EXTRACTION AND ARTIFICIAL DECISION EXPLAINABILITY

Publication Number WO/2021/242319
Publication Date 02.12.2021
International Application No. PCT/US2020/066299
International Filing Date 21.12.2020
IPC
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR 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
CPC
G06K 9/6268
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
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
G06K 9/6281
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
6267Classification techniques
6279relating to the number of classes
628Multiple classes
6281Piecewise classification, i.e. whereby each classification requires several discriminant rules
G06K 9/6282
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
6267Classification techniques
6279relating to the number of classes
628Multiple classes
6281Piecewise classification, i.e. whereby each classification requires several discriminant rules
6282Tree-organised sequential classifiers
G06K 9/6292
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
6288Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
6292of classification results, e.g. of classification results related to same input data
G06K 9/6293
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
6288Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
6292of classification results, e.g. of classification results related to same input data
6293of classification results relating to different input data, e.g. multimodal recognition
G06K 9/6296
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
6296Graphical models, e.g. Bayesian networks
Applicants
  • RAYTHEON COMPANY [US]/[US]
Inventors
  • PILCHER, Christopher M.
  • HARRIS, Christopher
  • GOULDING, John R.
  • WEAVER, William D.
Agents
  • MARAIA, Joseph M.
  • CHACLAS, George N.
  • COHEN, Jerry
  • COWLES, Christopher R.
  • EMMONS, Richard B.
  • FOLEY, Shawn P.
  • GOLDMAN, Gabriel
  • JOBSE, Bruce D.
  • CLARKE, Daniel W.
  • MCGRATH, Daniel
  • MILLS, Steven M.
  • QUINN, Joseph P.
  • SCHEPPER, Marlo M.
  • SERIO, John C.
  • SORKIN, Paul D.
  • SUSAN, Janine M.
  • KARIMI, Pegah
  • PYSHER, Paul
  • CARROLL, Christopher
  • SCHULTZ, Christopher
Priority Data
16/887,50829.05.2020US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) SYSTEMS AND METHODS FOR FEATURE EXTRACTION AND ARTIFICIAL DECISION EXPLAINABILITY
(FR) SYSTÈMES ET PROCÉDÉS D'EXTRACTION DE CARACTÉRISTIQUES ET D'EXPLICABILITÉ DE DÉCISION ARTIFICIELLE
Abstract
(EN) Automatic target recognizer system including: a database that stores target recognition data including multiple reference features associated with each of multiple reference targets; a pre-selector that selects a portion of the target recognition data based on a reference gating feature of the multiple reference features; a preprocessor that processes an image received from an image acquisition system which is associated with an acquired target and determines an acquired gating feature of the acquired target; a feature extractor and processor that discriminates the acquired gating feature with the reference gating feature and, if there is a match, extracts multiple segments of the image and detects the presence, absence, probability or likelihood of one of multiple features of each of the multiple reference targets; a classifier that generates a classification decision report based on a determined classification of the acquired target; and a user interface that displays the classification decision report.
(FR) La présente invention concerne un système de reconnaissance automatique de cibles comprenant : une base de données qui stocke des données de reconnaissance de cibles comprenant de multiples caractéristiques de référence associées à chacune de multiples cibles de référence ; un présélecteur qui sélectionne une partie des données de reconnaissance de cibles sur la base d'une caractéristique de synchronisation de référence parmi les multiples caractéristiques de référence ; un préprocesseur qui traite une image reçue en provenance d'un système d'acquisition d'images qui est associé à une cible acquise et détermine une caractéristique de synchronisation acquise de la cible acquise ; un extracteur de caractéristiques et un processeur qui distingue la caractéristique de synchronisation acquise de la caractéristique de synchronisation de référence et, si elles correspondent l'une à l'autre, extrait de multiples segments de l'image et détecte la présence, l'absence, la probabilité ou la chance de l'une des multiples caractéristiques de chacune des multiples cibles de référence ; un classificateur qui génère un rapport de décision de classification sur la base d'une classification déterminée de la cible acquise ; et une interface utilisateur qui affiche le rapport de décision de classification.
Related patent documents
Latest bibliographic data on file with the International Bureau