摘要
为了提高机器视觉系统的图像分割精度,提出了一种以小波变换为分类特征的多神经网络(Multi-Neural Network,MNN)图像分割算法,该算法包括小波特征提取、MNN区域划分和MNN分类3个阶段。其中,小波特征提取根据小波变换的各层图像扩展得到分类特征;MNN区域划分将初分割边界附近区域分为训练样本区域和待分类区域(待分区域),并用多边形拟合算法将待分区域划分为多个局部待分区域;MNN分类将每个局部待分区域的像素用区域内的神经网络分类器进行分类,确定目标像素和背景像素,将目标像素合并后再进行一定的后处理即可得到分割结果。以轴承表面缺陷检测系统采集的轴承缺陷图像为对象,对MNN算法和阈值分割算法进行了对比试验,结果显示MNN算法的像素数量误差(Pixel Error,PE)相比阈值分割算法降低了75%,分割精度显著提高。
To improve the image segmentation accuracy of machine vision system,a Multi-Neural Network( MNN) segmentation algorithm based on wavelet transform is proposed. The algorithm consists of three phases: multi-neural network region division,feature extraction and classification. The training region and the region to be classified near the boundary of the initial segmentation are divided into several small regions by the polygon fitting algorithm. The feature extraction is achieved by the extension of images which are the result of wavelet transform of the original image. The neural network classifier classifies the pixels in the region to be classified to target pixels and background pixels,and to obtain the segmentation results,some post-processing are performed. The multi-neural network algorithm and the threshold segmentation algorithm are compared with the segmentation accuracy of bearing defect image. The result shows that the Pixel Error( PE) of the multi-neural network algorithm is reduced by 75 %than the threshold segmentation algorithm. Segmentation accuracy is improved significantly.
引文
[1]王爱民,沈兰荪.图像分割研究综述[J].测控技术,2000(5):1-6,16.
[2]曾永林.神经网络方法在图像分割中的应用[D].成都:电子科技大学,2005.
[3]吴冰,魏建,刘艳昌,等.粗糙集神经网络在图像分割中的应用[J].河南理工大学学报(自然科学版),2007(5):550-554.
[4]杨治明,王晓蓉,彭军,等. BP人工神经网络在图像分割中的应用[J].计算机科学,2007(3):234-236.
[5]张亚静,李民赞,乔军,等.一种基于图像特征和神经网络的苹果图像分割算法[J].光学学报,2008(11):2104-2108.
[6]何伟,蒋加伏,齐琦.基于粗糙集理论和神经网络的图像分割方法[J].计算机工程与应用,2009(1):188-190.
[7]周长英.基于改进的模糊BP神经网络图像分割算法[J].计算机仿真,2011(4):287-290.
[8]朱宗花. Spiking神经网络的研究及其在图像分割中的应用[D].成都:电子科技大学,2013.
[9]周鹏飞,张月琴.基于模糊BP神经网络的图像分割方法研究[J].计算机工程与设计,2014(7):2423-2426.
[10]吴高洪,章毓晋,林行刚.利用小波变换和特征加权进行纹理分割[J].中国图像图形学报,2001(4):28-32.
[11] SALARI E,LING Z. Texture segmentation using hierarchical wavelet decomposition[J]. Pattern Recognition,1995,28(12):216-220.
[12] COHEN A,DAUBECHIES I,FEAUVEAU J. Biorthogonal bases of compactly supported wavelets[J]. Communications on Pure and Applied Mathematics,2010,45(5):485-560.
[13] LU C S,CHUNG P C,CHEN C F. Unsupervised texture segmentation via wavelet transform[J]. Pattern Recognition,1997,30(5):729-742.
[14] RAFAEL C Gonzalez.数字图像处理[M]. 3版.北京:电子工业出版社,2011:289-331.
[15]张毓晋.图像工程(中册)[M]. 3版.北京:清华大学出版社,2012:104-126.