Extraction method of gear interference image foreground region based on adaptive threshold
-
摘要:
齿面物体像灰度法是激光移相干涉测量中提取齿轮干涉图像前景区域的重要方法之一，针对该方法因人工设定阈值且忽略不同图像边缘特征从而导致的测量效率及精度受限问题，提出了一种基于自适应阈值的齿轮干涉图像前景区域提取方法。首先分析齿轮齿面形貌特征与各边缘顶点差异，对图像进行区域划分；然后根据边缘灰度变化规律通过邻域窗口筛选合格像素点并获取掩模结果，实现前景区域提取；最后根据5类图像评价指标分别对4组算法分割结果与传统方法分割结果进行数据对比。结果表明：算法在实现图像自动处理的基础上与参考结果匹配精确度提升约3.5%～4.5%，PRI(probabilistic rand index)提升约3%～4%，VOI(variation of information)提高约15%～25%，GCE(global consistency error)降低约2.5%～3.5%，最终相位信息准确度提升9 μm～15 μm。结果符合精度要求，该方法可广泛应用于齿轮干涉图像前景提取中。
Abstract:Gray method of tooth surface objects is one of the important methods to extract the gear interference image foreground region in laser phase-shifting interferometry. In view of the problem of limited measurement efficiency and limited accuracy caused by the manual threshold setting and neglect of different image edge features, a foreground region extraction method of gear interference image based on adaptive threshold was proposed. Firstly, the morphological characteristics of gear tooth surface and difference of each edge vertex were analyzed, and the image was divided into regions. Then, according to the changing rule of edge gray scale, the mask results were obtained by selecting qualified pixels through neighborhood window, so as to realize the foreground region extraction. Finally, the segmentation results of four groups of algorithms and traditional methods were compared according to five kinds of image evaluation indexes. The results show that the matching accuracy between the algorithm and reference results is improved by about 3.5%～4.5% based on the automatic image processing, the probabilistic rand index (PRI) is improved by about 3%～4%, the variation of information (VOI) is improved by 15%～25%, the global consistency error (GCE) is reduced by 2.5%～3.5%, and the final phase information accuracy is increased by 9 μm～15 μm. The results meet the requirements of accuracy, and the method can be widely used in foreground extraction of gear interference image.
-
Keywords:
- gear tooth flank /
- image segmentation /
- image gray value /
- image evaluation
-
-
表 1 待测量齿轮参数
Table 1 Parameters of gears to be measured
待测齿轮 模数 齿数 齿宽/mm 螺旋角/(°) 压力角/(°) 斜齿轮 $ 3 $ $ 60 $ $15$ $20$ $20$ 直齿轮 $ 2.5 $ $ 50 $ $20$ — $20$ 
下载: 导出CSV
表 2 像素匹配准确度评价
Table 2 Accuracy evaluation of pixel matching
待评价
图像组自适应
阈值法传统
算法匹配度
差值准确度
提升比/%A组各算法
提取结果401 710 385 003 16 707 4.09 B组各算法
提取结果400 450 385 586 14 864 3.64 C组各算法
提取结果402 359 384 120 18 239 4.47 D组各算法
提取结果381 479 367 201 14296 3.50
下载: 导出CSV
表 3 图像分割定量评价
Table 3 Quantitative evaluation of image segmentation
待评价图像组 PRI GCE VOI A组自适应阈值法 0.986 6 0.223 5 0.768 9 A组传统算法 0.947 3 0.257 7 1.085 6 B组自适应阈值法 0.979 5 0.231 8 0.926 1 B组传统算法 0.946 1 0.259 4 1.104 1 C组自适应阈值法 0.981 4 0.227 5 0.836 0 C组传统算法 0.939 8 0.260 1 1.093 4 D组自适应阈值法 0.923 7 0.311 9 1.147 5 D组传统算法 0.901 4 0.358 6 1.390 3
下载: 导出CSV
表 4 相位误差对比
Table 4 Comparison of phase errors
μm 待测图像 自适应阈值法 传统算法 提升值 A组 5 15 10 B组 7 22 15 C组 5 14 9 D组 4 15 11
下载: 导出CSV
-
[1] 郭东明. 高性能精密制造[J]. 中国机械工程,2018,29(7):757-765. doi: 10.3969/j.issn.1004-132X.2018.07.001 GUO Dongming. High-performance precision manufacturing[J]. China Mechanical Engineering,2018,29(7):757-765. doi: 10.3969/j.issn.1004-132X.2018.07.001
[2] 戴雨志, 盛晓超, 杨鹏程, 等. 齿面形状误差测量中干涉图像有效测量区域分割方法的对比研究[J]. 机械与电子,2021,39(5):3-7. doi: 10.3969/j.issn.1001-2257.2021.05.001 DAI Yuzhi, SHENG Xiaochao, YANG Pengcheng, et al. Comparison and analysis of effective measurement area segmentation methods in tooth surface interference fringe pattern[J]. Machinery & Electronics,2021,39(5):3-7. doi: 10.3969/j.issn.1001-2257.2021.05.001
[3] 常林, 何婷婷, 闫恪涛, 等. 考虑移相参数匹配的任意腔长下多表面干涉测量[J]. 仪器仪表学报,2021,42(9):181-191. doi: 10.19650/j.cnki.cjsi.J2108042 CHANG Lin, HE Tingting, YAN Ketao, et al. Multi-surface interference measurement with arbitrary cavity lengths considering phase-shifting parameter matching[J]. Chinese Journal of Scientific Instrument,2021,42(9):181-191. doi: 10.19650/j.cnki.cjsi.J2108042
[4] INO T, YATAGAI T. Oblique incidence interferometry for gear-tooth surface profiling[J]. Univiversity of Tsukuba (Japan),1992,1720:464-469.
[5] YANG P C, FANG S P, WANG L J, et al. Correction method for segmenting valid measuring region of interference fringe patterns[J]. Optical Engineering,2011,50(9):095602-1-095602-6. doi: 10.1117/1.3622760
[6] WANG X, ZHU X D, KOU K, et al. Fringe direction weighted autofocusing algorithm for gear tooth flank form deviation measurement based on an interferogram[J]. Applied Optics,2021,60(36):11066-11074. doi: 10.1364/AO.442395
[7] 葛爱明, 陈磊, 陈进榜, 等. 有遮拦干涉图像的数字化处理技术研究[J]. 光学学报,2000,37(6):775-780. doi: 10.3321/j.issn:0253-2239.2000.06.010 GE Aiming, CHEN Lei, CHEN Jinbang, et al. Digitalisation processing technique for interference pattern with obstruct[J]. Acta Optica Sinica,2000,37(6):775-780. doi: 10.3321/j.issn:0253-2239.2000.06.010
[8] 杨鹏程. 齿轮齿面形状误差测量中干涉条纹图像的分割、配准及评价技术的研究[D]. 西安: 西安交通大学, 2020. YANG Pengcheng. Reasearch on segmention, registration and evalution technology for interferogram in measuring the form deviation of tooth flank[D]. Xi’an: Xi’an Jiaotong University, 2020.
[9] WANG L J, FANG S P, YANG P C, et al. Comparison of three methods for identifying fringe regions of interference fringe patterns in measuring gear tooth flanks by laser interferometry[J]. Optik - International Journal for Light and Electron Optics,2015,126(24):5668-5671. doi: 10.1016/j.ijleo.2015.08.177
[10] WANG X, FANG S P, ZHU X D, et al. Nonlinear diffusion and structure tensor based segmentation of valid measurement region from interference fringe patterns on gear systems[J]. Current Optics and Photonics,2017,1(6):587-597.
[11] 张新, 林彬, 杨夏, 等. 基于亮度先验的星图杂散光噪声去除方法[J]. 应用光学,2021,42(3):454-461. doi: 10.5768/JAO202142.0302002 ZHANG Xin, LIN Bin, YANG Xia, et al. Stray light noise removal method of star maps based on intensity prior[J]. Journal of Applied Optics,2021,42(3):454-461. doi: 10.5768/JAO202142.0302002
[12] 朱占龙, 刘永军, 李亚梅, 等. 融入图像块和类信息量的无损检测图像分割[J]. 激光与光电子学进展,2021,58(12):146-155. ZHU Zhanlong, LIU Yongjun, LI Yamei, et al. Image segmentation of non-destructive test based on image patch and cluster information quantity[J]. Laser & Optoelectronics Progress,2021,58(12):146-155.
[13] LIU J H, YANG D H, HU F. Multiscale object detection in remote sensing images combined with multi-receptive-field features and relation-connected attention[J]. Remote Sensing,2022,14(2):427-427. doi: 10.3390/rs14020427
[14] HIBA R, CHAYMAE L, HAMID T. A survey of recent interactive image segmentation methods[J]. Computational Visual Media,2020,6(4):355-384.
[15] 王玉萍. 融合改进直方图PDE和二维Tsallis熵多阈值SAR分割[J]. 应用光学,2018,39(6):839-848. WANG Yuping. Multi-threshold SAR segmentation based on improved histogram PDE and two-dimensional Tsallis entropy[J]. Journal of Applied Optics,2018,39(6):839-848.
[16] 戈乐乐, 赵银娣. 五种分割算法在高分辨率遥感图像中的适用性分析[J]. 测绘科学,2012,37(4):209-212. doi: 10.16251/j.cnki.1009-2307.2012.04.029 GE Lele, ZHAO Yindi. A method of automatically searching lever ring and calculating the misclsure[J]. Science of Surveying and Mapping,2012,37(4):209-212. doi: 10.16251/j.cnki.1009-2307.2012.04.029
[17] MEILĂ M. Comparing clusterings—an information based distance[J]. Journal of Multivariate Analysis,2006,98(5):873-895.
[18] 仲伟峰, 赵晶. 基于生成对抗网络的图像去雾算法[J]. 激光与光电子学进展,2022,59(4):337-345. ZHONG Weifeng, ZHAO Jing. Image defogging algorithm based on generative adversarial network[J]. Laser & Optoelectronics Progress,2022,59(4):337-345.
[19] 王旭初, 刘辉煌, 牛彦敏. 融合多尺度局部特征与深度特征的双目立体匹配[J]. 光学学报,2020,40(2):119-131. WANG Xuchu, LIU Huihuang, NIU Yanmin. Binocular stereo matching by combining multiscale local and deep features[J]. Acta Optica Sinica,2020,40(2):119-131.
-
期刊类型引用(1)
1. 倪晋平，崔艳，田会，谢辰浩. 减小光幕靶边缘效应的灵敏度补偿方法. 西安航空学院学报. 2024(05): 52-57 . 
百度学术
其他类型引用(0)
计量
- 文章访问数: 253
- HTML全文浏览量: 160
- PDF下载量: 46
- 被引次数: 1
陕公网安备 61011302001501号 