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

Method for increasing accurate image recognition of edge recognition points based on gray threshold segmentation method

A grayscale threshold and edge recognition technology, which is applied in the field of image recognition, can solve problems that are only applicable to specific ones, and achieve the effects of small amount of calculation, enhanced accuracy, and high accuracy rate

Inactive Publication Date: 2019-07-12
JIANGSU UNIV OF TECH
View PDF2 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Various scenes or images can be used as the image data to be segmented. Some segmentation algorithms are only suitable for specific segmentation objects, and some segmentation algorithms are effective for all images. Therefore, only a comprehensive understanding of the differences between each algorithm, Only then can we make the best choice for different situations

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
  • Method for increasing accurate image recognition of edge recognition points based on gray threshold segmentation method
  • Method for increasing accurate image recognition of edge recognition points based on gray threshold segmentation method
  • Method for increasing accurate image recognition of edge recognition points based on gray threshold segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0037] In step 101, the image is preprocessed to remove noise, and the image is first output as a signal spectrum. The low frequency part is the slowly changing part of the signal in the frequency domain, and the high frequency part is the fast changing part of the signal in the frequency domain. Then, the convolution of the stimulus-response matrix and the input image is carried out through the spatial domain filter to realize the filtering in the frequency domain, so as to remove the noise in the image.

[0038]Step 102, draw the grayscale histogram of the image, first traverse the pixels of the image, count the number of each grayscale, and divide the histogram by the area of ​​the image to obtain the probability density function of the image, for the area function The cumulative distribution function of the image can be obtained by performing the same normalization process, and the grayscale histogram is drawn using the function in OpenCV.

[0039] Step 103, select the opt...

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 increasing edge recognition points and improving image recognition accuracy based on a gray threshold segmentation method. The method comprises: firstly, preprocessing an image to remove noise; using a frequency domain method to process useful information of a low-frequency part in the digital image to eliminate noise; secondly, traversing pixels of the image,summarizing the number of the pixels belonging to each gray level, drawing a gray histogram in the OpenCV by utilizing a calculation function, selecting an optimal threshold for image segmentation, then adding identification points in the segmented gray map, and finally outputting a threshold identification point distribution image. According to the method, the accuracy of image recognition is improved through a method of increasing recognition points by using a gray threshold segmentation method.

Description

technical field [0001] The invention belongs to the field of image recognition, and in particular relates to a method for increasing the accuracy of image recognition by adding edge recognition points based on a gray threshold segmentation method, especially a method for increasing recognition points by using an edge algorithm. Background technique [0002] 1. Image segmentation algorithm [0003] The image segmentation algorithm refers to dividing the whole image into several regions with different characteristics according to the characteristics of the image's edge, texture, color, gray value, etc. The characteristics of the same region are consistent and there are obvious characteristic differences between different regions. Image segmentation algorithms are mainly used in the fields of image recognition and augmented reality. Effective image segmentation can improve the speed of image recognition, separate objects from images more quickly, effectively save system time, a...

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): G06T7/136G06T7/12G06T7/13G06T5/40
CPCG06T5/40G06T7/12G06T7/13G06T7/136G06T2207/10004
Inventor 高伟狄瑞陆康康
Owner JIANGSU 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