A method for visual detection of liquid crystal instrument pattern based on normalized zernike moment and grayscale matching
A grayscale matching, liquid crystal instrument technology, applied in instrumentation, image analysis, image data processing, etc., can solve the problems of high false detection rate, poor flexibility, errors, etc., to achieve less redundant information, strong image description ability, excellent Detect the effect of recognition ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0033] Specific embodiment one: a kind of liquid crystal meter pattern visual detection method based on normalized Zernike moments and grayscale matching of the present embodiment is specifically prepared according to the following steps:
[0034] Step 1. Collect the overall image to be detected from the camera such as figure 2 , set the pattern to be detected according to the overall image information to be detected, set the ROI of the image, intercept the sub-image of the detected area, and gray-scale the sub-image as the image to be detected (src_GrayImage); read from the database The corresponding template image (templ_GrayImage);
[0035] Step 2. Fill the image to be detected and the template image into a square image (the Zernike moment requires the image to be a square image), and translate the center of gravity of the detection image and the template image to the center of the square image, and perform translation normalization to generate a translation image to be de...
specific Embodiment approach 2
[0049] Specific embodiment two: the difference between this embodiment and specific embodiment one is: in step 2, the image to be detected and the template image are filled into a square image (the Zernike moment requires the image to be a square image), and the center of gravity of the detection image and the template image The specific process of translating to the center of the square image and performing translation normalization to generate a translation to-be-detected image and a translation template image is as follows:
[0050] (1) Determine whether the width and height of each image are equal, if not, square the image: compare the width and height of each image, select the larger width and height as the side length of the square image, and ensure The length of the side length is an odd number, construct a square image, and set the pixels of the square image to 0, that is, the square image is black; according to the size of the image, add some pixels to the side length ...
specific Embodiment approach 3
[0052] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is: adopt Mukundan fast algorithm to calculate the Zernike moments of image to be checked and template image in step 3. The specific process is:
[0053] (1) Use "square-circle transformation" to transform the square image g(x,y) into polar coordinates f(r,ξ), r,ξ are obtained by the following formula: γ=max{|x|,|y |}, if |x|=γ, then If |y|=γ, then The normalized polar coordinates corresponding to the pixel (r, ξ) are: r=2γ / N, θ=πξ / 4γ, where N is the number of side length pixels of the square image;
[0054] (2) Calculation of Zernike radial n-order m-order polynomial R by iterative method nm (r); Where m≥0 and n-k is an even number, B nmk = ( - 1 ) ( n - ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com