Reordering and segmenting method based on pixel points of large-size image

A technology for reordering image pixels, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as restricting image recognition work, achieve the effect of reduced operation, convenient post-processing, and reduced image size

Active Publication Date: 2021-08-24
CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At the same time, in some images, the central area of ​​the image contains more important feature information than the edge area of ​​the image. Conventional large image segmentation cannot sequentially segment these pixels from the central area to the edge area, which restricts the subsequent image recognition work.

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
  • Reordering and segmenting method based on pixel points of large-size image
  • Reordering and segmenting method based on pixel points of large-size image
  • Reordering and segmenting method based on pixel points of large-size image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be further described below in conjunction with embodiment and accompanying drawing.

[0041] A reordering and segmentation method based on large-scale image pixels, combined with figure 1 As can be seen, the following steps are involved:

[0042] S1: Determine that the pixels in the image P include N rows and M columns, and number the coordinates of all the pixels in the image P to obtain the coordinate set S of all the pixels in the image; calculate the center pixel coordinates of the image P as (a 1 ,b 1 );

[0043] The specific steps of step S1 are:

[0044] S11: Acquire the image P to be divided, and determine the number of rows N and the number of columns M of pixels in the image P in units of pixels;

[0045] S12: Coordinate numbering of the number of rows and columns where each pixel is located, and the coordinates of all pixels of the image P can be expressed as a set S={(i,j)|1≤i≤N,1≤j≤M,i ,j∈Z};

[0046] S13: According to the n...

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 reordering and segmenting method based on pixel points of a large-size image, which comprises the following steps of: determining that the pixel points in an image P comprise N rows and M columns, and numbering coordinates of all the pixel points of the image P to obtain a coordinate set S of all the pixel points of the image; calculating a center pixel point coordinate of the image P; determining an influence field of a central pixel point of the image P, and calculating to obtain a vector P2 after all pixel points in the image P are reordered; and S4, setting the size of the image after the image P is segmented, dividing the vector P2 into c vectors with the same size, and storing the c vectors as segmented image data of the image P. And segmentation from the center to the edge is realized, the picture is stored in a datamation manner, and random division can be realized according to the required size.

Description

technical field [0001] The invention relates to the technical field of large-scale image processing, in particular to a reordering and segmentation method based on large-scale image pixels. Background technique [0002] Image recognition technology refers to a technology that uses computers to process and analyze original images to identify targets and objects in different patterns. Image preprocessing of the collected original images is the primary task of image recognition. In order to obtain more image features and cover a larger target area, the collected original images are often required to be large-scale images. [0003] Although large-scale images can obtain more picture details, these images cannot meet the system input size requirements, cannot be directly used in image recognition systems, and do not use image storage. For example, in the cellular neural network, to realize the associative memory of images, images of different sizes need to be processed into the...

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): G06T3/00G06T7/10
CPCG06T3/0093G06T7/10G06T2207/10004
Inventor 韩琦杨恒翁腾飞陈国荣解燕张澳侯明阳武宸王洪艺田升
Owner CHONGQING UNIVERSITY OF SCIENCE AND TECHNOLOGY
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