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

All-focus image generation method based on interactive adversarial learning

An all-focus image and non-focus technology, applied in the field of all-focus image generation, can solve problems such as difficult to extract deep features, low model complexity, and poor robustness

Pending Publication Date: 2021-11-05
DALIAN UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the document "Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes", Golestaneh et al. proposed a spatially varying blur detection method based on high-frequency multi-scale fusion and gradient size sorting transformation, and performed local calculations at each pixel. , to determine the fuzzy level, and set the parameters to build the model by manually designing the feature extraction method, so the complexity of the model is low, but there are also problems that it is difficult to extract deep features and poor robustness; deep learning based on convolutional neural network method, in these methods, most of them use the source image as input, use the non-focus area detection truth value as supervision, and use information such as multi-scale or multi-level feature fusion to obtain the final detection result map

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
  • All-focus image generation method based on interactive adversarial learning
  • All-focus image generation method based on interactive adversarial learning
  • All-focus image generation method based on interactive adversarial learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The specific implementation manners of the present invention will be further described below in conjunction with the accompanying drawings and technical solutions.

[0036] Figure 1The flow chart of the overall training method of the omni-focus image generation network, first builds the non-focus blur detection network, obtains the intermediate output, that is, the non-focus blur detection map, and then inputs it into the omni-focus image generation network together with the input image to obtain the full Focus on the image, use formula (1-6) as the loss function for supervision, and when the generator and the discriminator reach the final dynamic equilibrium point, the training of this model ends. After this process, we can get an omni-focus image generator with good performance.

[0037] In general, this method designs an omni-focus image generation method based on interactive adversarial learning, which can effectively complete the global consistent and natural omn...

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 belongs to the technical field of image information processing, and provides a full-focus image generation method based on interactive adversarial learning. According to the full-focus image generation method, an interactive adversarial learning mode is utilized, firstly, the complementary relation between a non-focus fuzzy detection task and an edge detection task is utilized, and a boundary focused to a non-focus transition area and a homogeneous area with little detection texture information are better located; secondly, paired non-focusing images and corresponding full-focusing true-value images are needed in most of the current common methods, and the paired images are difficult to obtain. However, the problem does not exist in the method disclosed by the invention, and the natural all-focus image generation network with global consistency can be realized only by using all-focus images which are not paired as references.

Description

technical field [0001] The invention belongs to the technical field of image information processing, in particular to a method for generating an all-focus image. Background technique [0002] At present, the methods related to this patent include two aspects: the first is an out-of-focus blur detection algorithm; the second is an image generation algorithm based on generative confrontation. [0003] Non-focus blur detection methods are mainly divided into two categories: Traditional methods based on artificial design, which mostly extract features through manual design, usually use image gradient, frequency and other features to construct detectors to complete non-focus blur area detection . In the document "Spatially-varying blur detection based on multiscale fused and sorted transform coefficients of gradient magnitudes", Golestaneh et al. proposed a spatially varying blur detection method based on high-frequency multi-scale fusion and gradient size sorting transformation...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T7/13G06N3/04G06N3/08
CPCG06T7/13G06N3/08G06T2207/10004G06T2207/20084G06T2207/20081G06N3/045G06T5/70Y02T10/40
Inventor 赵文达魏菲徐从安姚力波刘瑜何友卢湖川
Owner DALIAN UNIV OF TECH
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