该方法首先基于邻域灰度极值提取边界候选图像，然后以边界候选象素及其邻域象素的二值模式作为样本集，输入边缘检测神经网络进行训练。
The method uses a logical judgment algorithm to get edge candidate images, and then edge pixels and their neighbor pixels compose the binary samples of the BP neural network.
对于边缘区域，用较大的码书去量化当前输入矢量以保证图像质量。
For edge areas, the input vectors are quantized with large-size codebook to maintain the image quality.
相应地，它的测量电路采用具有三个输入端的变压器电桥，从而免除了电极边缘和外界干扰的影响。
A transformer-ratio arm bridge with three terminals is adopted as its measuring circuit to eliminate the influence of electrode edges and exterior interference.
应用推荐