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

Method for identifying and positioning circular transparent lens

A transparent lens, identification and positioning technology, applied in image data processing, instruments, calculations, etc., can solve the problem of inaccurate identification of circular transparent lenses and achieve good results

Active Publication Date: 2020-09-01
SOUTH CHINA NORMAL UNIVERSITY
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] This method proposes a circular transparent lens recognition and positioning method

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 identifying and positioning circular transparent lens
  • Method for identifying and positioning circular transparent lens
  • Method for identifying and positioning circular transparent lens

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] The transparent lens is innovatively installed at a certain angle from the side. The camera used is a high-quality cmos camera with 3 million pixels and a metal shell. It can be used by connecting the usb to the pc end. The camera is built-in The 32M memory is used as a frame buffer, and the transmission is more stable. The lens is a C-mount lens, which can adjust the focus and aperture, so that the image of the subject becomes clear.

[0071] The diameter of the transparent lens to be identified is 9mm, the thickness is 2mm, the shape is circular, the upper and lower surfaces are transparent, and the surrounding is frosted. The physical picture of the circular transparent lens is as follows Image 6 shown.

[0072] Driven by the camera, the center point of the circular transparent lens is identified and positioned. After the camera is calibrated, information such as the outline and center point of the circular transparent lens can be found and accurately positioned in ...

Embodiment 2

[0113] The only difference from Example 1 is that the object implemented this time is a transparent lens with a diameter of 7mm, so as to test the applicability of the method, the specific steps are as follows:

[0114] (1) Convert the image to a grayscale image, according to the grayscale mathematical formula Gray=0.299*R+0.587*G+ 0.114*B, that is, the mathematical formula for converting the original color image into a grayscale image, and each image has R, G , B channels of three colors.

[0115] (2) The image is filtered, that is, the noise of the target image is suppressed under the condition of retaining the image details as much as possible, and the processing effect will directly affect the effectiveness and reliability of the subsequent image processing and analysis.

[0116] (3) Use the adaptive threshold segmentation method (Otsu) to segment the image and background of the object, that is, Otsu can adapt to the image background, set a reasonable threshold, and obtain...

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 identifying and positioning a circular transparent lens, which comprises the following steps: an image acquisition step: shooting a lens from a side inclination angle to generate a picture frame; identifying and positioning the circular transparent lens: preprocessing the picture, calculating the outline of the transparent lens by using the improved canny, andsolving the central point of the transparent lens: firstly, finding out all detected outlines by using the found outlines, traversing all the found outlines, and removing useless outlines; solving a central coordinate of the binary image through the first moment; and finally, carrying out spatial rotation and translation on the pixel coordinates of the image by utilizing calibrated parameters to obtain coordinates under a world coordinate system; and an image pixel correction step: performing calibration correction on the camera by using a Zhang Zhengyou calibration method, and providing calibration parameters for converting pixel coordinates into world coordinates. According to the method, the outline of the transparent lens can be accurately recognized, and the center point of the circular transparent lens can be positioned.

Description

technical field [0001] The invention is applied to the field of machine vision, and is applied to the machine vision recognition and positioning of transparent sheet objects, and in particular relates to a method for recognition and positioning of circular transparent lenses. Background technique [0002] Machine vision technology has been widely used in industry, medicine, aerospace, agriculture and other fields because of its non-contact, low-cost, and easy-to-implement advantages. research and application. Generally, the recognized target object has obvious outline information, which can be easily recognized by machine vision. However, for colorless and transparent objects such as optical lenses, due to their blurred outline or lack of three-dimensional information, when applying machine vision recognition There is a certain degree of difficulty. The present invention aims at this situation, and on the basis of analyzing the colorless and transparent contour features of...

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): G06T7/00G06T7/11G06T7/13G06T7/70G06T5/00G06T5/30
CPCG06T7/0004G06T7/11G06T7/13G06T7/70G06T5/30G06T5/70Y02P90/30
Inventor 周斌张渊方董濠向拓闻
Owner SOUTH CHINA NORMAL UNIVERSITY
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