Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020224406 - IMAGE CLASSIFICATION METHOD, COMPUTER READABLE STORAGE MEDIUM, AND COMPUTER DEVICE

Publication Number WO/2020/224406
Publication Date 12.11.2020
International Application No. PCT/CN2020/085062
International Filing Date 16.04.2020
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 9/6201
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
6201Matching; Proximity measures
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 9/6262
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
G06K 9/627
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
627based on distances between the pattern to be recognised and training or reference patterns
G06K 9/6272
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
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
6272based on distances to cluster centroïds
G06K 9/629
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
629of extracted features
Applicants
  • 腾讯科技(深圳)有限公司 TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED [CN]/[CN]
Inventors
  • 胡一凡 HU, Yifan
  • 郑冶枫 ZHENG, Yefeng
Agents
  • 北京三高永信知识产权代理有限责任公司 BEIJING SAN GAO YONG XIN INTELLECTUAL PROPERTY AGENCY CO., LTD.
Priority Data
201910379277.208.05.2019CN
Publication Language Chinese (zh)
Filing Language Chinese (ZH)
Designated States
Title
(EN) IMAGE CLASSIFICATION METHOD, COMPUTER READABLE STORAGE MEDIUM, AND COMPUTER DEVICE
(FR) PROCÉDÉ DE CLASSIFICATION D'IMAGE, SUPPORT D'INFORMATIONS LISIBLE PAR ORDINATEUR ET DISPOSITIF INFORMATIQUE
(ZH) 图像分类方法、计算机可读存储介质和计算机设备
Abstract
(EN) The present application relates to an image classification method, a computer readable storage medium, and a computer device, the method comprising: acquiring a medical image to be classified; on the basis of image data in an area of interest in the medical image, generating a texture image; by means of a first network model, performing feature extraction on the texture image to acquire local medical features; by means of a second network model, performing feature extraction on the medical image to acquire global medical features; on the basis of the fused features of the global medical features and the local medical features, performing image classification; thus, the accuracy of medical image classification results can be effectively improved.
(FR) La présente invention concerne un procédé de classification d'image, un support d'informations lisible par ordinateur et un dispositif informatique, le procédé consistant à : acquérir une image médicale à classifier ; générer, sur la base de données d'image dans une zone d'intérêt de l'image médicale, une image de texture ; effectuer, au moyen d'un premier modèle de réseau, une extraction de caractéristiques sur l'image de texture pour acquérir des caractéristiques médicales locales ; effectuer, au moyen d'un second modèle de réseau, une extraction de caractéristiques sur l'image médicale pour acquérir des caractéristiques médicales globales ; effectuer, sur la base des caractéristiques fusionnées des caractéristiques médicales globales et des caractéristiques médicales locales, une classification d'image ; ainsi, la précision des résultats de classification d'image médicale peut être efficacement améliorée.
(ZH) 本申请涉及一种图像分类方法、计算机可读存储介质和计算机设备,方法包括:获取待分类的医学图像;根据医学图像中感兴趣区域内的图像数据生成纹理图像;通过第一网络模型对纹理图像进行特征提取,获得局部医学特征;通过第二网络模型对医学图像进行特征提取,获得全局医学特征;基于全局医学特征和局部医学特征的融合特征进行图像分类,可以有效地提高医学图像分类结果的准确性。
Related patent documents
Latest bibliographic data on file with the International Bureau