基于多尺度多结构形态学火焰图像边缘检测

Flame Image Edge Detection Based on Multi-scale and Multi-structuring Elements Morphology

针对从工业锅炉采集到的火焰图像边缘形态和噪声的不同,以数学形态学梯度边缘检测算子为基础,结合多结构元素和多尺度的特性,提出了一种基于多尺度多结构数学形态学图像边缘检测算法,并将其应用于火焰图像的边缘检测。仿真结果表明,与经典的Sobel算子、Canny算子和传统的算法相比,提出的算法具有边缘定位准确、轮廓清晰、图像细节保留较多、噪声不敏感等显著优点。

According to the edge shape and noises of flame image from industrial boiler image sampling system, combined with the characteristics of multi-scale and muhi-structttring elements, an image edge detection algorithm based on multi-scale and multi-structuring elements morphology is pres- ented, which using mathematical morphological edge detection operators is applied in flame image edge detection. The simulation results show that the proposed algorithm has the following advantages： accuracy of edge locating, clear outline of image, more image details preserved and insensitive to noise, compared with classical Sobel operators, Canny operators and traditional algorithm.