Quality inspection of a PCB （Printed Circuit Board） always requires us to stitch some separated images into an integral one. However, during image acquisition, some environmental influences such as vibration, noise ...Quality inspection of a PCB （Printed Circuit Board） always requires us to stitch some separated images into an integral one. However, during image acquisition, some environmental influences such as vibration, noise and illumination will cause image degradation. An efficient image mosaic method has been urgently required to obtain a high-quality PCB panorama. Hence, an image mosaic method based on Gaussian-Hermite moments is presented in this paper. The characteristic points in the neighborhood of a PCB are represented by Gaussian-Hermite moment in- variants. They are characterized by independence to translation or rotation transformations. Meanwhile, such feature representation shows better noise robustness. Experimental results show that the proposed method produces a qualified mosaic of PCB image.展开更多
马尔可夫随机场(MRF)在SAR图像分割中有着广泛的应用。由于合成孔径雷达(SAR)图像本身所固有的相干斑噪声的影响,传统方法很难获得准确的分割,因此提出了一种新的基于MRF(Markov Random Field)融合Gaussian-Hermite矩(GHM)的SAR图像无...马尔可夫随机场(MRF)在SAR图像分割中有着广泛的应用。由于合成孔径雷达(SAR)图像本身所固有的相干斑噪声的影响,传统方法很难获得准确的分割,因此提出了一种新的基于MRF(Markov Random Field)融合Gaussian-Hermite矩(GHM)的SAR图像无监督分割算法。利用Gaussian-Hermite矩的不同阶矩作为SAR图像特征得到初始分割;将得到的初始分割结果作为MRF随机场的先验模型,通过引入一个基于两成分权重参数的能量函数,利用最大后验概率(MAP)得到最终的分割结果。通过对合成图像及SAR图像分割实验结果的比较,表明了该方法在误分率、抗噪性以及视觉效果上具有更好的效果。展开更多
文摘提出一种基于Gaussian-Hermite矩的虹膜识别算法.首先由粗到精定位出虹膜,并归一化为多个一维信号,然后利用1阶和2阶Gaussian-Hermite矩提取一维信号的局部特征并进行0-1编码,最后用汉明距离分类.该算法只需单个训练样本,识别速度快,容易实现,并具有平移、旋转和缩放不变性.基于CASIA虹膜数据库的实验表明,算法的识别正确率达98.55%,单次平均识别时间为0.5 s.
基金Supported by the National Natural Science Foundation of China(61502389)the Foundation Research Funds for Central University(3102015ZY047)
文摘Quality inspection of a PCB （Printed Circuit Board） always requires us to stitch some separated images into an integral one. However, during image acquisition, some environmental influences such as vibration, noise and illumination will cause image degradation. An efficient image mosaic method has been urgently required to obtain a high-quality PCB panorama. Hence, an image mosaic method based on Gaussian-Hermite moments is presented in this paper. The characteristic points in the neighborhood of a PCB are represented by Gaussian-Hermite moment in- variants. They are characterized by independence to translation or rotation transformations. Meanwhile, such feature representation shows better noise robustness. Experimental results show that the proposed method produces a qualified mosaic of PCB image.
文摘马尔可夫随机场(MRF)在SAR图像分割中有着广泛的应用。由于合成孔径雷达(SAR)图像本身所固有的相干斑噪声的影响,传统方法很难获得准确的分割,因此提出了一种新的基于MRF(Markov Random Field)融合Gaussian-Hermite矩(GHM)的SAR图像无监督分割算法。利用Gaussian-Hermite矩的不同阶矩作为SAR图像特征得到初始分割;将得到的初始分割结果作为MRF随机场的先验模型,通过引入一个基于两成分权重参数的能量函数,利用最大后验概率(MAP)得到最终的分割结果。通过对合成图像及SAR图像分割实验结果的比较,表明了该方法在误分率、抗噪性以及视觉效果上具有更好的效果。
