Intelligent electric meter chip image binarization processing method based on adaptive mixed threshold
An image binarization, smart meter technology, applied in image data processing, image enhancement, image analysis and other directions, can solve the problems of binarization, uneven image brightness, inability to achieve rapid processing and improve efficiency.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0055] This embodiment includes steps: S1, acquiring the original image, and preprocessing the original image to obtain a grayscale image; S2, calculating the global threshold T according to the grayscale value of the entire grayscale image g ; S3. Calculate the stroke width corresponding to each pixel in the grayscale image, and adaptively calculate the window width corresponding to each pixel, and calculate the local threshold T of each pixel according to the pixel value in each window w ; S4, the global threshold T g and a local threshold T w Combining calculations to obtain a blending threshold T; S5, performing a binarization operation on the grayscale image according to the blending threshold T to obtain a binarized image.
[0056] Preferably, the preprocessing of the original image in S1 includes: S1.1, performing median filtering on the original image, and the preferred specific method for performing median filtering on the original image in S1.1 is: S1.1.1, first usi...
Embodiment 2
[0059] Such as figure 1 As shown, the present embodiment also includes on the basis of Embodiment 1: S2 is specifically: set the grayscale image f(x, y) to have N pixels and L gray levels; divide f(x, y) into for C 0 and C 1 Two categories, C 0 class by f(x,y) in grayscale [0,T g ] in the composition of pixels, C 1 class by f(x,y) in grayscale [T g+1, L] in the pixel points, the variance between the two classes is: σ 2 =μ 0 (m 0 -m) 2 +μ 1 (m 1 -m) 2 , where μ 0 and μ 1 respectively C 0 and C 1 Probability of two classes, m 0 and m 1 respectively C 0 and C 1 The gray mean value of the two classes, m is the gray mean value of the entire gray scale image; in the L-level gray scale range, the threshold corresponding to the maximum variance between classes is selected by traversal method, which is the global threshold T g . S3 includes steps: S3.1, calculate the stroke width corresponding to each pixel, and adaptively calculate the window width corresponding t...
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