Video image distortion effect model construction method based on improved dice loss function

A loss function and video image technology, applied in video data retrieval, neural learning methods, biological neural network models, etc., to achieve the effect of improving recognition and detection accuracy and wide application prospects

Pending Publication Date: 2019-07-19
FUZHOU UNIVERSITY
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, many studies have found that when the network structure reaches a certain depth, its performance will tend to the average accuracy.

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
  • Video image distortion effect model construction method based on improved dice loss function
  • Video image distortion effect model construction method based on improved dice loss function
  • Video image distortion effect model construction method based on improved dice loss function

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.

[0031] The invention provides a method for building a video image distortion effect model based on an improved dice loss function, comprising the steps of:

[0032] Step S1, improving the function based on the Dice loss function, adding a weight factor and a smoothing factor to better adapt to the characteristics of the sample data set;

[0033] Step S2, using an improved loss function to train the data in the dense convolutional neural network of DenseNet to realize the classification construction of the model;

[0034] Step S3, using the trained model to classify and predict existing video images, and determine whether the video images are distorted.

[0035] The following is a specific embodiment of the present invention.

[0036] This implementation provides a method for building a video image distortion effect classification and de...

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 relates to a video image distortion effect model construction method based on an improved dice loss function. The method comprises: firstly, performing function improvement based on a Dice loss function, and a weight factor and a smoothing factor are added to better adapt to the characteristics of a sample data set; secondly, training data in the dense convolutional neural network ofthe DenseNet by adopting an improved loss function to realize classified construction of the model; and finally, carrying out classification prediction on the existing video image by using the trained model, and judging whether the video image is distorted or not. Compared with a traditional loss function training model, the identification and detection precision of the improved loss function insix common video image distortion effect data sets is improved, and the advantages are obvious.

Description

technical field [0001] The invention relates to the technical field of video image distortion effects, in particular to a method for constructing a video image distortion effect model based on an improved dice loss function. Background technique [0002] With the development of computer software and hardware technology and the rapid growth of network users, video images have become a mainstream way for people to express and convey information. However, the quality of video images from acquisition to final presentation to users will cause various distortion problems due to equipment damage, environmental factors, conversion coding, etc., especially the hybrid MC / DPCM / DCT video coding algorithm [ITU90, The compression coding distortion produced by ITU95, SEC91, SEC92] will hinder the user from obtaining clear information from the video image to a large extent, and greatly affect the user's visual quality. [0003] In order to eliminate the problem of distortion effects in vid...

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): G06F16/75G06N3/04G06N3/08
CPCG06F16/75G06N3/08G06N3/045G06N3/044
Inventor 林丽群陈柏林
Owner FUZHOU UNIVERSITY
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