基于图像处理的飞机零件定位与识别研究

Research on Aircraft Part Localization and Recognition Based on Image Processing

为了满足某军工企业对飞机零件的定位与识别需求,提出一种优化的图像定位与识别算法。在零件识别方面,采用改进的高斯滤波算法以降低图像噪声,利用改进的Canny算法进行零件边缘检测处理,采用改进的阈值分割算法获取零件的边缘轮廓,最后利用改进的SIFT算法完成零件的识别处理。在零件定位方面,通过对零件进行多角度旋转操作,记录每个角度的最小外接矩形面积和质心坐标,以满足不同角度零件的定位要求。实验结果表明,该方法定位与识别准确率可以达到100%。

In order to meet the positioning and recognition requirements of aircraft parts for a military enterprise,an optimized image positioning and recognition algorithm is proposed in this paper.In terms of part recognition,an improved Gaussian filtering algorithm is used to reduce image noise,the improved Canny algorithm is used for part edge detection processing,the improved threshold segmentation algorithm is used to obtain the edge contour of the part,and finally,the improved SIFT algorithm is used to complete the part recognition processing.In terms of part positioning,by performing multi angle rotation operations on the parts,the minimum outer rectangular area and centroid coordinates of each angle are recorded to meet the positioning requirements of parts with different angles.The experimental results show that the positioning and recognition accuracy of this method can reach 100%。