Abstract：At the low contrast defects of the workpiece surface, a new method for grayscale statistical analysis and recognition based on image grid is proposed. First, construct the filtering method using the spatial and range information to process the original image; then carries on the grid division of the image, and the gray value of the image of grid entropy statistical analysis, to achieve recognition of defect targets. The experimental results show that the accuracy rate of low contrast defect recognition reaches 97.1%.
［1］郭皓然, 邵伟, 周阿维, 等. 全局阈值自适应的高亮金属表面缺陷识别新方法［J］. 仪器仪表学报, 2017, 38(11): 2797-2804.
Guo H R, Shao W, Zhou A W, et al. Novel defect recognition method based on adaptive global threshold for highlight metal surface［J］. Chinese Journal of Scientific Instrument, 2017, 38(11): 2797-2804.
［2］艾长胜, 于润祥, 孙选, 等. 轴承钢球质量在线检测与分选系统的研究［J］. 测控技术, 2009, 28(10): 4-7.
Ai C S, Yu Y X, Sun X, et al. Research on Quality Inspection and Sorting On-Line System for Bearing Steel Ball ［J］. Measurement & Control Technology, 2009, 28(10): 4-7.
［3］张学武, 丁燕琼, 闫萍. 一种基于红外成像的强反射金属表面缺陷视觉检测方法［J］. 光学学报, 2011, 31(03): 1-9.
Zhang X W, Ding Y Q, Yan P. Vision Inspection of Metal Surface Defects Based on Infrared Imaging［J］. Acta Optica Sinica, 2011, 31(03): 1-9.
［4］杨玉, 陈昕, 金纪勇. U75V钢轨轨腰探伤不合原因的分析［J］. 钢铁, 2011, 46(02): 91-95.
Yang Y, Chen X, Jin J Y. Analysis of the Failed Detection on U75V Rail Waists ［J］. IRON & STEEL, 2011, 46(02): 91-95.
［5］潘洪平, 董申, 梁迎春, 等. 钢球表面缺陷的自动检测与识别［J］. 中国机械工程, 2001, 12 (4): 369-371.
Pan H P, Dong S, Liang Y C, et al. Automatic Detection and Recogition of Steel Balls Surface Flaws［J］. China Mechanical Engineering, 2001, 12 (4): 369-371.
［6］张竟月,孙斌,谢玄达, 等. 基于激光和机器视觉的微量液体容量计量方法［J］. 计量学报, 2018, 39(4): 504-509.
Zhang J Y, Sun B, Xie X D, et al. Volume Metrology Method for Micro Liquid Based on Laser and Machine Vision［J］. Acta Metrologica Sinica, 2018, 39(4): 504-509.
［7］吴凤和. 基于计算机视觉测量技术的图像轮廓提取方法研究［J］. 计量学报, 2007, 28 (1): 18-22.
Wu F R. A Study on Contour Extraction Method in Computer Vision Measurement Technology［J］. Acta Metrologica Sinica, 2007, 28(1): 18-22.
［8］Cheng H D, Chen Y H, Jiang X H. Thresholding using two-dimensional histogram and fuzzy entropy principle［J］. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2000, 9(4): 732-735.
［9］罗菁, 董婷婷, 宋丹, 等. 表面缺陷检测综述［J］. 计算机科学与探索, 2014,8 (09): 1041-1048.
Luo J, Dong T T, Song D, et al. A Review on Surface Defect Detection ［J］. Journal of Frontiers of Computer Science and Technology, 2014, 8 (09): 1041-1048.
［10］Sagar A V, Balasubramaniam S, Chandrasekaran V. A Novel Integrated Approach Using Dynamic Thresholding and Edge Detection (IDTED) for Automatic Detection of Exudates in Digital Fundus Retinal Images［C］// International Conference on Computing: Theory and Applications. Kolkata,India, 2007: 705-710.
［11］Liu B H, Li B, Jiang Z D. Segmentation algorithm based on edge-searching for multi-linear structured light images［J］. Chinese Journal of Mechanical Engineering, 2006, 19 (03): 468-470.
［12］唐亮, 赵春红, 胡继明, 等. 基于边缘检测算子的图像边缘检测研究与应用［J］. 科技广场, 2017, (06): 22-25.
Tang L, Zhao C H, Hu J M, et al. Research and Application of Image Edge Detection Based on Edge Detection Operator［J］. Science Mosaic, 2017, (06): 22-25.
［13］程淑红, 尚果超. 基于视觉的答题卡自动判分系统设计［J］. 计量学报, 2018, 39(6): 804-810.
Cheng S H, Shang G C. Design of Automatic Judgment System of Answer Card Based on Vision［J］. Acta Metrologica Sinica, 2018, 39(6): 804-810.
［14］Tomasi C, Manduchi R. Bilateral filtering for gray and color images［C］//Sixth International Conference on Computer Vision. Bombay, India, 1998: 839-846.
2019, Vol. 40 
