Processing

Please wait...

Settings

Settings

Goto Application

1. WO2016149881 - OBJECT RECOGNTION BASED ON BOOSTING BINARY CONVOLUTIONAL NEURAL NETWORK FEATURES

Publication Number WO/2016/149881
Publication Date 29.09.2016
International Application No. PCT/CN2015/074757
International Filing Date 20.03.2015
IPC
G06K 9/00 2006.01
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
CPC
G06K 9/00362
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
00362Recognising human body or animal bodies, e.g. vehicle occupant, pedestrian; Recognising body parts, e.g. hand
G06K 9/4619
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
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4604Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections
4609by matching or filtering
4619Biologically-inspired filters, e.g. receptive fields
G06K 9/6256
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
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
G06K 9/6269
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
6269based on the distance between the decision surface and training patterns lying on the boundary of the class cluster, e.g. support vector machines
G06K 9/6286
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
6285relating to the decision surface
6286Linear, e.g. hyperplane
G06K 9/66
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
64using simultaneous comparisons or correlations of the image signals with a plurality of references, e.g. resistor matrix
66references adjustable by an adaptive method, e.g. learning
Applicants
  • INTEL CORPORATION [US]/[US]
  • YAO, Anbang [CN]/[CN] (BZ)
  • XU, Lin [CN]/[CN] (BZ)
  • LI, Jianguo [CN]/[CN] (BZ)
  • CHEN, Yurong [CN]/[CN] (BZ)
Inventors
  • YAO, Anbang
  • XU, Lin
  • LI, Jianguo
  • CHEN, Yurong
Agents
  • NTD PATENT AND TRADEMARK AGENCY LIMITED
Priority Data
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) OBJECT RECOGNTION BASED ON BOOSTING BINARY CONVOLUTIONAL NEURAL NETWORK FEATURES
(FR) RECONNAISSANCE D'OBJET SUR LA BASE DE CARACTÉRISTIQUES DE RÉSEAU NEURONAL À CONVOLUTION BINAIRE D'AMPLIFICATION
Abstract
(EN)
Techniques related to implementing convolutional neural networks for object recognition are discussed. Such techniques may include generating a set of binary neural features via convolutional neural network layers based on input image data(601) and applying a strong classifier to the set of binary neural features to generate an object label for the input image data(602).
(FR)
Des techniques liées à l'implémentation de réseaux neuronaux à convolution pour la reconnaissance d'objet sont discutées. De telles techniques peuvent comprendre la génération d'un ensemble de caractéristiques neuronales binaires par le biais de couches de réseau neuronaux à convolution sur la base de données d'image d'entrée (601), et l'application d'un classificateur fort pour l'ensemble de caractéristiques neuronales binaires pour générer une étiquette d'objet pour les données d'image d'entrée (602).
Also published as
Latest bibliographic data on file with the International Bureau