Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image processing method

An image processing and image technology, applied in the field of image processing, can solve the problems of inability to focus, the overall color of the picture changes, changes, etc.

Active Publication Date: 2019-07-12
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The cyclic generative confrontation network is suitable for dealing with image style transfer, but it is often unable to focus on local features and the existence of stripe noise in the process of image local feature transfer similar to face removal glasses, and it is prone to the overall color of the image. Changes, that is, changes in other areas of the face may appear after the glasses are removed from the face

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 processing method
  • Image processing method
  • Image processing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] An image processing method, comprising the steps of:

[0046] Step 1: Set the target image to be processed as a face image, and the feature to be processed as glasses, log in to the picture website, and collect 2000 pictures of faces with glasses and pictures of faces without glasses.

[0047] Step 2: Preprocessing the collected pictures. First, remove blurred and inconsistent images; then, use the convolutional neural network-based cascaded multi-task face detection algorithm (MTCNN) to obtain five key points of the face, and uniformly crop the photo to 128× according to the key points The size is 128 pixels; finally, it is divided into two types: the face with glasses and the face without glasses, and each is saved as a training sample.

[0048] Step 3: Input the preprocessed training samples into the recurrent generative confrontation network for training. The cyclic generative confrontation network includes a first generator, a second generator, a first discrimina...

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 conversion processing method in the technical field of image processing. The image processing method aims to solve the technical problems in the prior art that an image processing method based on the cyclic generative adversarial network often cannot focus on local features and has stripe-shaped noise in the image local feature migration process, and the overall color of a picture is easily changed. The method comprises the following steps: acquiring a real image containing processing characteristics and a real image not containing the processing characteristics, and constructing a training sample; inputting a training sample into the cyclic generative adversarial network, and training the cyclic generative adversarial network by taking a pre-constructed loss function minimization as a target, the loss function comprising a total variation regularization loss function; and processing the to-be-processed image by adopting the trained cyclic generative adversarial network.

Description

technical field [0001] The invention relates to an image processing method and belongs to the technical field of image processing. Background technique [0002] In recent years, with the rapid development of artificial intelligence, deep learning has also become a popular research field, especially the proposal of generative confrontation network has accelerated the process of deep learning. The generative confrontation network consists of a generator and a discriminator. The generator can learn through the potential distribution of real data and generate fake data distribution to fit and approximate the real data; the discriminator is a classifier that can judge whether the data distribution is is true. Through continuous competitive learning, the generator can generate more and more realistic fake data distributions, and finally achieve the effect of confusing real ones. [0003] The cyclic generative adversarial network is a combination of a generative adversarial netwo...

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): G06K9/00
CPCG06V40/172
Inventor 金晨凯郭国安吴晨
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com