Image generation method and device, computer equipment and storage medium

An image generation and image technology, applied in the field of machine learning, can solve the problems of low DNN accuracy and insufficient data volume in DNN training set, and achieve the effect of improving accuracy and increasing data volume

Active Publication Date: 2019-07-30
TENCENT TECH (SHENZHEN) CO LTD
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides an image generation method, device, computer equipment and storag

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image generation method and device, computer equipment and storage medium
  • Image generation method and device, computer equipment and storage medium
  • Image generation method and device, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0062] In order to make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0063] figure 1 It is a schematic diagram of an implementation environment of an image generation method provided by an embodiment of the present invention. See figure 1 , The server 101 can be included in the implementation environment:

[0064] The server 101 can separately train the initial condition generation network and the initial active learning model to obtain the condition generation network and the active learning model, so that the server 101 can filter out a large number of candidate images based on the active learning model and the uncertainty conforms to the preset Conditional to-be-annotated images enable technicians to annotate only the filtered images to be annotated to obtain the original image, thereby reducing the cost of m...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an image generation method and device, computer equipment and a storage medium, and belongs to the technical field of machine learning. The method comprises the following stepsof: obtaining at least one original image, and inputting the at least one original image into a condition generation network, extracting style information of the at least one original image through the condition generation network, and generating at least one target image carrying the classification tag based on the style information of the at least one original image and at least one mask comprising the target type of the second object. According to the method, a certain kind of images lacking in training can be enhanced in a customized mode, the data size in the DNN training set is increased, and the accuracy of the DNN is improved.

Description

technical field [0001] The present invention relates to the technical field of machine learning, in particular to an image generation method, device, computer equipment and storage medium. Background technique [0002] The screening of breast diseases in my country mainly relies on ultrasonography. The breast images taken by ultrasonography can be input into a deep neural network (DNN), and the breast images can be analyzed and processed by DNN, such as breast layer segmentation and breast cancer classification, so as to realize Automated screening for breast disease. [0003] In the above process, the accuracy of mammary gland analysis depends on the accuracy of DNN, while the accuracy of DNN based on supervised learning at this stage is heavily dependent on the amount of breast image data contained in the training set, and due to the total number of breast disease patients It is far less than the number of healthy people, so that the DNN training set lacks images of diseas...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/00G06T7/11G06T5/50
CPCG06T7/0014G06T7/11G06T5/50G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/20221G06T2207/30068
Inventor 蓝晨曦马锴郑冶枫
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap