Open AccessMosaic Method for Insulator Images Based on Region Characteristics
Author(s) -
Zhihui Wang,
Licai Zhang,
Chen Yao,
Xiaoyan Sun
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1453/1/012135
Subject(s) - pixel , artificial intelligence , rgb color model , computer science , computer vision , mosaic , brightness , grayscale , adaptability , standard deviation , enhanced data rates for gsm evolution , pattern recognition (psychology) , feature (linguistics) , mathematics , geography , statistics , ecology , linguistics , physics , philosophy , archaeology , optics , biology
Based on the analysis of image registration methods based on region and feature, an image mosaic method based on edge statistical features is proposed. By using the mean and mean square deviation of RGB parameters of edge region pixels as matching criteria, this method improves the shortcomings of general region registration algorithm, such as large computational complexity, sensitivity to brightness and scale changes, poor real-time performance and adaptability, and simplifies the calculation of global region features of images to that of local region features. This method makes full use of the relevant information of the RGB parameters of the pixels. Compared with the registration calculation based on gray level, it has the characteristics of abundant optional features and high practicability.