Edge Detection of Ferrography Image Based on Lifting Wavelet
-
摘要: 利用小波多尺度特性提取图像边缘是目前研究热点之一。铁谱图像磨粒边缘作为铁谱图像中最基本的特征,为铁谱图像特征提取提供了非常有价值的重要特征参数,在基于铁谱分析的机器故障诊断技术中有着重要的地位。将第二代提升小波算法应用于铁谱图像边缘检测:首先将彩色铁谱图像分解为R、G、B单通道图像,对三通道图像分别进行预处理,并利用直方图处理和图像深度转换实现磨粒和背景的分离;然后对各个通道图像进行D4提升小波变换,在小波域中,通过阈值判断提取高频子图中的边缘像素;最后通过或运算将各个通道的边缘进行融合得到最终的磨粒边缘图像。本文结果与Sobel算子和Canny算子的结果进行比较表明:本文中算法能有效的抑制噪声,较好地再现铁谱图像的磨粒边缘信息,是一种有效的铁谱图像边缘检测算法。Abstract: Multiscale wavelet analysis to image edge detection is a current research focus.The edge of grain is the basic feature in the ferrography image,providing important characteristic parameters for ferrography image's feature extraction and playing a very important role in failure analysis based on ferrographic analysis technology.In this article,the lifting wavelet transforms is used to edge detection of ferrograghy image.First,the color image of ferrography is segmented into RGB single channel images,preconditioning each single image and separating grains from the background by histogram and image depth conversion; Then,D4 lifting wavelet is used to each single channel image,extracting pixels of edge from the sub-image in wavelet domain by threshold; Lastly,the final edge images are obtained through OR operation.Compared with the Soble algorithm and the Canny algorithm,this article's algorithm is more efficient at reducing noise for the edge detection of ferrography image.
-
Key words:
- edge detection /
- grain boundavries /
- pixels /
- wavelet analysis
-
[9] 冈萨雷斯. 数字图像处理( 第二版) [M]. 电子工业出版社，2005 [2] 王汉功，陈桂明. 铁谱图像分析理论与技术[M]. 科学出版社，2005 [3] Song F J，Jutamulia S. New wavelet transforms for noise-insensitive edge detection[J]. Optical Engineering，2004，41 (1):50～54 [4] Lee Y，Kozaitis S P. Multiresolution gradient-based edge deted-tion in noisy images using wavelet domain filters[J]. OpticalEngineering，2004，39(9):2405～2414 [5] Shih M Y，Tseng D. A wavelet-based multiresolution edge detec-tion and tracking[J]. Image and Vision Computer，2005，23(4):441～451 [6] Sweldens W. The lifting scheme: a new philosophy in biorthogo-nal wavelet constructions[A]. Proceedings of SPIE[C]，1995，2569:68～79 [7] Sweldens W. The lifting scheme: a custom-design construction ofbiorthogonal wavelet[J]. Applied and Computational Har-monic Analysis，1996，3(2):186～200 [8] Daubechies I，Sweldens W. Factoring wavelet transforms into lift-ing steps[J]. Journal of Fourier Analysis and Applications，1998，4(3):247～268 [9] 詹松. 磨损磨粒的计算机识别分析系统研究[D]. 合肥:合肥工业大学，2004:8～9 [10] Bradski & Kaehler 著. 于仕琪，刘瑞祯译. 学习 Opencv(中文版)[M]. 清华大学出版社，2009 [11] 倪林. 小波变换与图像处理[M]. 中国科学技术大学出版社，2010 [12] 孟军，魏同立. 一种新型基于提升算法的二维离散小波变换结构的实现[J]. 电路与系统学报，2003，8(6) [13] 张建科. 基于小波提升的图像边缘检测算法[J]. 浙江海洋学院学报，2005，(4) -
点击查看大图
计量
- 文章访问数: 196
- HTML全文浏览量: 33
- PDF下载量: 4
- 被引次数: 0
下载:
