Processing

Please wait...

Settings

Settings

Goto Application

1. CN110321920 - Image classification method and device, computer readable storage medium and computer equipment

Office
China
Application Number 201910379277.2
Application Date 08.05.2019
Publication Number 110321920
Publication Date 11.10.2019
Grant Number 110321920
Grant Date 22.10.2021
Publication Kind B
IPC
G06K 9/62
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
G06K 9/34
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
20Image acquisition
34Segmentation of touching or overlapping patterns in the image field
CPC
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 9/629
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
G06V 10/267
G16H 50/20
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
20for computer-aided diagnosis, e.g. based on medical expert systems
G16H 30/40
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
30ICT specially adapted for the handling or processing of medical images
40for processing medical images, e.g. editing
G06V 2201/03
Applicants TENCENT TECHNOLOGY (SHENZHEN) CO., LTD.
腾讯科技(深圳)有限公司
Inventors HU YIFAN
胡一凡
ZHENG YEFENG
郑冶枫
Agents 广州华进联合专利商标代理有限公司 44224
广州华进联合专利商标代理有限公司 44224
Title
(EN) Image classification method and device, computer readable storage medium and computer equipment
(ZH) 图像分类方法、装置、计算机可读存储介质和计算机设备
Abstract
(EN) The invention relates to an image classification method and device, a computer readable storage medium and a computer device. The method comprises the steps of obtaining a to-be-classified medical image; generating a texture image according to the image data in the region of interest in the medical image; performing feature extraction on the texture image through a first network model to obtain local medical features; performing feature extraction on the medical image through a second network model to obtain global medical features; and performing image classification based on the fusion features of the global medical features and the local medical features. According to the scheme provided by the invention, the accuracy of the medical image classification result can be effectively improved.
(ZH) 本申请涉及一种图像分类方法、装置、计算机可读存储介质和计算机设备,该方法包括:获取待分类的医学图像;根据所述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所述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所述医学图像进行特征提取,获得全局医学特征;基于所述全局医学特征和所述局部医学特征的融合特征进行图像分类。本申请提供的方案可以有效地提高医学图像分类结果的准确性。
Related patent documents