零件矩形边界框区域自动提取算法及应用

Automatic extraction-algorithm of parts bounding box and application

为了提高图像处理速度,提出了基于机器视觉的目标图像矩形边界框区域提取算法。分析了图像在含有孤立点噪声的情况下该算法的可靠性以及阈值选取对实验结果的影响;设计出了针对齿形链板和自动扶梯用链板图像的抗噪模板;利用最小二乘法和最小区域法确定链板圆孔几何参数,并从目标与背景之比和算法复杂度两个方面分析了该算法对处理速度的贡献能力。实验表明,该算法对于孤立点噪声具有良好的抑制作用,可快速、准确地找出包含目标图像的矩形区域。

A new automatic extraction-algorithm of parts bounding box is proposed for the purpose of improving the image processing speed.The reliability of this algorithm under isolated nosie and the effect of different threshold on the experimental result is analyzed.The anti-noise template is developed suitable for the chain board.The geometric parameters of circle in chain board are obtained by least square method and minimum zone reference circle method.The experiment result shows that this algorithm can inhibit isolated nosie well and the bounding box including target image can be found fast and accurately.