复杂背景下边缘提取与目标识别方法研究.pdfVIP

第 14卷 第 3期 光学精密工程 Vol. 14 No.3 2006 年6 月 Optics and Precision Engineering Jun. 2006 (2006) 032 05092 04 1 1,2 1 林玉池 , 崔彦平 , 黄银国 (1.天津大学精密测试技术及仪器国家重点实验室, 天津300072; 2. 河北科技大学 械电子工程学院, 河北 石家庄050054) :通过对传统形态学边缘提取方法的分析,提出了基于形态学 结构元边缘提取算子,该算子既有良好的边缘提取 特性,又很好地解决了噪声抑制和保持图像边缘细节之间的矛盾, 通过灰度加权平均值作为阈值进行二值化, 更加突出 了边缘效果。针对目标成像特点,在提取图像中边缘的像素数、复杂度和最小外接矩形长宽比等 个特征的基础上, 通 过计算图像中目标边缘的特征评价函数和隶属度函数, 利用模糊综合评判技术进行了目标识别。模拟试验表明:基于形 态学的 结构元算子具有较强的噪声抑制能力, 可以很好地提取复杂背景下的目标边缘;模糊综合评判技术可准确提取 目标,较好地解决了复杂背景下的目标识别的难题。 :; ; ; ; :TP391. 4 :A Study on edge det ection and tar get r ecogn it ion in complex back ground 1 1,2 1 LIN Yu2chi , CUI Yan2ping , HUANG Yin2guo ( 1.StateKey Laboratory of Precision Measuring Technology and Instrument , Tianjin University, Tianjin 300072, hina; 2.School of Mechanical and ElectronicEngineering, H ebei University of Science and Technology, Shij iazhuang 050054, hina) Abstr act : Based on the analysis of traditional edge detection operator of mathematical morphology, a multi2structuring elements edge detection operator of mathematical morphology was proposed, which could suppress noise as much as possible while preserving fine details. The threshold acquired by weighted average of gray levelswasused tobinarize the image to improveimageedge. On the basis of characters of edge pixels, complexity and aspect ratio ofminimum enclosingrectangle, a overall fuzzy evaluating technique was utilized to recoginize the target by calculating the characteristic evaluating function and membership degree function. The results of simulation experiments demons