Fragmented image matching degree analysis method based on boundary straight line features

A straight-line feature and fragmentation technology, applied in image analysis, details involving image stitching, image enhancement, etc., to achieve the effect of novel angles

Pending Publication Date: 2022-02-18
XIAN UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for analyzing the matching degree of fragmented images based on boundary line features, which solves the splicing problem of fragmented images rich in line features, and realizes the restoration of fragmented table images

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
  • Fragmented image matching degree analysis method based on boundary straight line features
  • Fragmented image matching degree analysis method based on boundary straight line features
  • Fragmented image matching degree analysis method based on boundary straight line features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0071] Perform 2*2 segmentation processing on 300 structural images rich in linear features to construct a fragmented image dataset. There are 1200 images in the fragmented image dataset. Figure 4 An example of the original image.

[0072] Divide the fragmented images in the fragmented image data set according to their relative positions, and divide them into four categories: left_up, left_bottom, right_up, and right_bottom. Put the divided data sets into Alexnet classification model training, set batch_size to 32, and set epochs to 20 .

[0073] by Figure 4 Take the structure diagram as an example, enter Figure 4 A fragmented image at the left_up position in the Figure 5 , Gaussian denoising is performed on the image, the edge line detection of the processed image is performed, and only the feature information of the edge line at the stitching point is retained according to the classification result of the image position.

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 a method for carrying out fragmented image matching degree analysis based on boundary straight line features. The method comprises the following steps: step 1, constructing a fragmented image data set; step 2, fragmented images in the fragmented image data set are divided according to relative positions; step 3, performing Gaussian denoising preprocessing operation on an input fragmented image; 4, according to the position classification result and the edge straight line information in the step 3, calculating the matching degree of the edge straight line features between the fragmented images, arranging the matching results in a descending order, and taking the image with the maximum matching degree as the matching result; and 5, carrying out fragmented image splicing restoration on the optimal splicing result in the step 4, and comparing with the original image to calculate the accuracy. According to the method, the splicing problem of fragmented images rich in linear features is solved, and the restoration of fragmented table images is realized.

Description

technical field [0001] The invention belongs to the technical field of image data processing, and in particular relates to a method for analyzing the matching degree of fragmented images based on boundary line features. Background technique [0002] With the rapid development of big data and the Internet of Things, the data that people can apply is no longer just simple values. Text, images, voice, and video are the main channels of current data transmission. The amount of data contained in them is immeasurable and urgently needs to be developed and utilized. On the one hand, in-depth analysis of various types of data information for information combination can enhance human understanding of natural information; on the other hand, further analysis of data can fully tap potential correlations and increase the economic value of information. [0003] At present, a large amount of fragmented information has not been recycled. How to analyze the correlation of fragmented informat...

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): G06V10/74G06T3/40G06T5/00G06T7/13
CPCG06T7/13G06T3/4038G06T2200/32G06F18/22G06T5/00G06T5/70
Inventor 魏嵬牛少温张贝贝
Owner XIAN UNIV OF TECH
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