基于DSP+FPGA的元器件焊接垂直度识别方法

为实现电路板上柱状元器件焊接垂直度的精准检测,设计了一款基于DSP+FPGA的垂直度识别系统。DSP承担核心算法任务,FPGA作为数据预处理单元,完成接口的逻辑、系统的互连以及数据通道。在硬件平台上嵌入了基于元器件形心配准的垂直度识别算法。首先对预处理的图像利用改进的Canny算法提取元器件的像素级边缘,并采用边缘跟踪算法去除噪点和干扰边缘并对元器件进行编号,在粗提取的边缘上用Zernike矩算法来精确定位元器件亚像素级边缘。在此基础上,提取元器件轮廓的最小外接矩形来修正边缘并得到每个元器件的形心坐标,最后根据形心的偏移距离来完成每个元器件垂直度的识别。实验结果表明,该垂直度识别系统的设计方案识别结果精度高,检测速度快,满足实时性要求,具有重要的实际工程意义。

Identification Method of Welding Perpendicularity for Components Based on DSP+FPGA

In order to accurately detect the welding perpendicularity of column components on circuit board, a perpendicularity identification system based on DSP+FPGA was developed, in which DSP is responsible for core algorithms and FPGA functions as a unit of data preprocessing for the purpose interface logics, system interconnection and data channel. An algorithm of verticality recognition based on centroid registration of components is embedded in the hardware platform. This method, first obtains element''s pixel edge of pre-treated pictures using improved Canny algorithm, then rejects noise point and interference edge through edge track method and numbers the elements at last. The element''s sub-pixel edge is obtained at the edge subject to crude extraction with the aid of Zernike moment algorithm. On the basis of this, the minimum circumscribed rectangle of the element''s contour is obtained to correct the edge and get the areal coordinate. so as to inspect and measure perpendicularity of each element according to displacement of the centroid. The experimental results show that the design scheme of the verticality recognition results recognition system with high accuracy, fast detection speed and meet the real-time requirement, it has important practical engineering significance.