基于彩色边缘与十字型加权模板的马赛克检测  

Mosaic detection method based on color edge and crossed weighted template

作　　者：易宇晖 林志贤[1] 郭太良[1] 

机构地区：[1]福州大学物理与信息工程学院,福建福州350002

出　　处：《电视技术》2016年第11期121-125,共5页Video Engineering

基　　金：国家"863"重大专项(2013AA030601);福建省资助省属高校专项(JK2014002);福建省科技重大专项(2014HZ0003-1)

摘　　要：为了解决高分辨率视频马赛克检测识别率不高的问题,提出了一种基于彩色边缘与十字型加权模板的视频马赛克检测算法。该算法先通过基于CIELab色彩空间的彩色边缘检测检出更多马赛克边缘,再采用十字型加权模板进行模板匹配以识别出马赛克块。采用本文算法以及传统算法对高分辨率视频进行马赛克检测,实验结果表明本文算法对视频中马赛克检测的识别率高达98.2%,相比于传统算法识别率提高了7.1%。In order to solve the problem of low recognition rate of mosaic detection in high resolution videos, a mosaic detection method based on color edge and crossed weighted template is proposed. The algorithm first detects more mosaic edges through the color edge detection based on CIELab color space, and recognizes the mosaic pieces by template matching with crossed weighted template. The mosaic detection to high resolution videos is conducted through the algorithm proposed here and traditional algorithm, The result of experiment shows that the recognition rate gained through the algorithm proposed here is up to 98.2%, which is 7.1% higher than that of traditional algorithm.

关 键 词：马赛克 彩色边缘检测 CIELab色彩空间 模板匹配 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]