CAJ | 학술논문

针对火焰图像的边缘提取问题，论文提出了基于完整局部二值和阈值调节的边缘检测方法，该方法具有稳定，简约的优点。首先通过完整局部二值技术对火焰图像的主要边缘特征进行提取，然后利用二次阈值优化使提取的边缘更清晰化。实验结果表明在图像被噪声污染情况下，该方法仍然有效，经合成图像和现场拍摄图像分析验证，证明该方法比当前主流图像边缘提取方法具有更好的效果，为火焰图像后续分析奠定了基础。
침대화염도상적변연제취문제，논문제출료기우완정국부이치화역치조절적변연검측방법，해방법구유은정，간약적우점。수선통과완정국부이치기술대화염도상적주요변연특정진행제취，연후이용이차역치우화사제취적변연경청석화。실험결과표명재도상피조성오염정황하，해방법잉연유효，경합성도상화현장박섭도상분석험증，증명해방법비당전주류도상변연제취방법구유경호적효과，위화염도상후속분석전정료기출。
A simple and robust approach for flame image edge extraction is presented in this paper ,which is based on completed local binary patterns and thresholding techniques .Firstly ,completed local binary patterns is utilized to obtain The main features of an image ,and then the two level thresholding is used to make the edges more clear .The results show that in the case of the image is polluted by noise ,the approach is still valid ,Various experimentations are implemented on syn-thetic as well as real images .The results show the proposed approach gives good localization and effective edge detection as compared to the existing methods .