Image Segmentation Method Based on Context Regularized Recurrent Deep Learning

A technology of deep learning and image segmentation, applied in instruments, biological neural network models, calculations, etc., can solve problems such as large-area errors in predicted images, unclear edge segmentation, etc., to improve accuracy, solve large-area errors and edge segmentation unclear effect

Active Publication Date: 2021-07-16
HENAN UNIVERSITY
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image segmentation method based on contextual regularization cycle deep learning, which can solve the problems of large-area errors in predicted pictures and unclear edge segmentation when CN performs semantic segmentation operations on image areas and non-image areas

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 Segmentation Method Based on Context Regularized Recurrent Deep Learning
  • Image Segmentation Method Based on Context Regularized Recurrent Deep Learning
  • Image Segmentation Method Based on Context Regularized Recurrent Deep Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] The technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0079] Such as figure 1 Shown: a kind of image semantic segmentation method based on context regularization of the present invention, comprises the following steps:

[0080] Step 1: Perform a convolution operation in the VGG19-FCN network, where the VGG19-FCN network consists of 18 convolutional layers, 5 pooling layers, and 3 deconvolutional layers; specifically, the following steps are included:

[0081] Step 1.1: Assumptions Is the i-th layer feature map of the I-th convolutional layer, feature map is ...

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 present invention provides an image segmentation method based on context regularization cycle depth learning, which solves the problem of inaccurate segmentation of image areas and non-image areas in existing similar algorithms through convolution operations, context regularization operations and loop iteration operations, especially solves the problem of The problem of large-area errors in predicting pictures and unclear edge segmentation improves the accuracy of image segmentation.

Description

technical field [0001] The invention relates to the field of image semantic segmentation, in particular to an image segmentation method based on context regularization cycle deep learning. Background technique [0002] In today's society, smart mobile devices such as mobile phones and tablet computers have been widely used. As an indispensable interface for human-computer interaction in smart mobile devices, displays are mainly divided into non-self-luminous displays and self-luminous displays. Organic Light-Emitting Diode (Organic Light-Emitting, OLED) is an emerging self-luminous display technology, which is different from traditional non-self-luminous displays. Each pixel can provide a light source and can be adjusted individually, which is easy to effectively control battery consumption. There is an obvious deficiency in the existing power-constrained image enhancement algorithms. The existing methods are to directly adjust the entire image, which will lose the detaile...

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 Patents(China)
IPC IPC(8): G06K9/34G06N3/04
CPCG06V10/267G06N3/045
Inventor 渠慎明苏靖刘颜红张东生刘珊渠梦瑶王青博张济仕
Owner HENAN 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