Search International and National Patent Collections
Some content of this application is unavailable at the moment.
If this situation persists, please contact us atFeedback&Contact
1. (WO2017134519) IMAGE CLASSIFICATION AND LABELING
Latest bibliographic data on file with the International Bureau

Pub. No.: WO/2017/134519 International Application No.: PCT/IB2017/000134
Publication Date: 10.08.2017 International Filing Date: 01.02.2017
IPC:
G06K 9/00 (2006.01) ,G06N 3/02 (2006.01) ,G06T 1/40 (2006.01)
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
K
RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9
Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
T
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
1
General purpose image data processing
20
Processor architectures; Processor configuration, e.g. pipelining
40
Neural networks
Applicants:
SEE-OUT PTY LTD. [AU/AU]; Level 5, Z1 The Works 34 Parer Place Kelvin Grove, QLD 4059, AU
Inventors:
MAU, Sandra; US
SIVAPALAN, Sabesan; AU
Priority Data:
62/289,90201.02.2016US
Title (EN) IMAGE CLASSIFICATION AND LABELING
(FR) CLASSIFICATION ET ÉTIQUETAGE D'IMAGES
Abstract:
(EN) A method of training an image classification model includes obtaining training images associated with labels, where two or more labels of the labels are associated with each of the training images and where each label of the two or more labels corresponds to an image classification class. The method further includes classifying training images into one or more classes using a deep convolutional neural network, and comparing the classification of the training images against labels associated with the training images. The method also includes updating parameters of the deep convolutional neural network based on the comparison of the classification of the training images against the labels associated with the training images.
(FR) L'invention concerne un procédé d'apprentissage d'un modèle de classification d'images. Ledit procédé consiste à obtenir des images d'apprentissage associées à des étiquettes, au moins deux des étiquettes étant associées à chacune des images d'apprentissage et chacune des au moins deux étiquettes correspondant à une classe de classification d'images. Le procédé consiste également à classer des images d'apprentissage dans une ou plusieurs classes au moyen d'un réseau neuronal convolutionnel profond, ainsi qu'à comparer la classification des images d'apprentissage avec les étiquettes associées aux images d'apprentissage. Le procédé consiste également à mettre à jour les paramètres du réseau neuronal convolutionnel profond d'après la comparaison de la classification des images d'apprentissage avec les étiquettes associées aux images d'apprentissage.
front page image
Designated States: AE, AG, AL, AM, AO, AT, AU, AZ, BA, BB, BG, BH, BN, BR, BW, BY, BZ, CA, CH, CL, CN, CO, CR, CU, CZ, DE, DJ, DK, DM, DO, DZ, EC, EE, EG, ES, FI, GB, GD, GE, GH, GM, GT, HN, HR, HU, ID, IL, IN, IR, IS, JP, KE, KG, KH, KN, KP, KR, KW, KZ, LA, LC, LK, LR, LS, LU, LY, MA, MD, ME, MG, MK, MN, MW, MX, MY, MZ, NA, NG, NI, NO, NZ, OM, PA, PE, PG, PH, PL, PT, QA, RO, RS, RU, RW, SA, SC, SD, SE, SG, SK, SL, SM, ST, SV, SY, TH, TJ, TM, TN, TR, TT, TZ, UA, UG, US, UZ, VC, VN, ZA, ZM, ZW
African Regional Intellectual Property Organization (ARIPO) (BW, GH, GM, KE, LR, LS, MW, MZ, NA, RW, SD, SL, ST, SZ, TZ, UG, ZM, ZW)
Eurasian Patent Organization (AM, AZ, BY, KG, KZ, RU, TJ, TM)
European Patent Office (AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR)
African Intellectual Property Organization (BF, BJ, CF, CG, CI, CM, GA, GN, GQ, GW, KM, ML, MR, NE, SN, TD, TG)
Publication Language: English (EN)
Filing Language: English (EN)
Also published as:
AU2017214619SG11201806541REP3411828CN109196514