基于OCT成像的淡水无核珍珠内部缺陷自动检测方法

石龙杰; 周扬; 岑岗; 刘铁兵; 施秧; 陈正伟; 黄俊; 汪凤林; 岑跃峰

doi:10.3969/j.issn.1000-1158.2020.10.08

PDF(3421 KB)

计量学报 ›› 2020, Vol. 41 ›› Issue (10) : 1226-1233. DOI: 10.3969/j.issn.1000-1158.2020.10.08

光学计量

基于OCT成像的淡水无核珍珠内部缺陷自动检测方法

石龙杰,周扬,岑岗,刘铁兵,施秧,陈正伟,黄俊,汪凤林,岑跃峰

作者信息 +

Automatic Detection of Internal Defects in Freshwater Nucle-free Pearls Based on OCT

SHI Long-jie,ZHOU Yang,CEN Gang,LIU Tie-bing,SHI Yang,CHEN Zheng-wei,HUANG Jun,WANG Feng-lin,CEN Yue-feng

Author information +

文章历史 +

摘要

光学相干层析技术(OCT)作为一种高分辨率的无损光学检测手段,已被用于珍珠的内部质量检测。针对淡水无核珍珠质层内部缺陷检测的需求,提出一种通过光学相干层析图像实现淡水无核珍珠内部缺陷自动检测的方法。根据珠层灰度变化的特点,识别图像中缺陷区域的梯度特征和缺陷位置变化特征,并利用缺陷特征建立反向传播神经网络模型。实验中采集了内部无缺陷和内部有多种类型缺陷淡水无核珍珠的光学相干层析图像各20幅,对图像进行预处理并提取特征,利用K-means算法检测样本类型与所提取特征的匹配度,用特征与类型相匹配的样本特征训练反向传播神经网络模型,使用反向传播网络模型对淡水无核珍珠内部缺陷层进行分类识别。实验结果表明该方法提取特征的匹配度为92.5%,分类准确率达到100%,验证了该方法的可行性和有效性,提出的方法能够作为淡水无核珍珠内部缺陷识别和自动分类的有效手段。

Abstract

Optical coherence tomography(OCT)isthe high resolution and nondestructive optical inspection method whichhas been used to evaluate the internal quality of pearls. In order to expand the range of applications of optical coherence tomography technique, an automatic detection method for internal defects of freshwater nucleated pearls by optical coherence tomography is proposed. According to the grayscale change of defect layer, the proposed method extracted the gradient feature and defect location feature of the defect region in the image, and then established the back propagation neural network(BPNN)model for defection prediction based on the extracted feature. Twenty optical coherence tomography images of defect pearls and twenty optical coherence tomography of images of health pearls were collected for image preprocessing and feature extraction in experiments, and K-means algorithm test was used to test the feature compatibility, andthe compatible features were the input of the back propagation neural network model which finally classified the defect recognition. The experimental results show that the matching degree of feature extraction is 92.5%, and the classification accuracy is up to 100%, which proved the feasibility and effectiveness of proposed method, and showed the proposed method can be used as an effective method for the identification and classification of internal defects of freshwater pearls.

导出引用

石龙杰,周扬,岑岗,刘铁兵,施秧,陈正伟,黄俊,汪凤林,岑跃峰. 基于OCT成像的淡水无核珍珠内部缺陷自动检测方法[J]. 计量学报. 2020, 41(10): 1226-1233 https://doi.org/10.3969/j.issn.1000-1158.2020.10.08

SHI Long-jie,ZHOU Yang,CEN Gang,LIU Tie-bing,SHI Yang,CHEN Zheng-wei,HUANG Jun,WANG Feng-lin,CEN Yue-feng. Automatic Detection of Internal Defects in Freshwater Nucle-free Pearls Based on OCT[J]. Acta Metrologica Sinica. 2020, 41(10): 1226-1233 https://doi.org/10.3969/j.issn.1000-1158.2020.10.08

中图分类号： TB96

参考文献

［1］刘晓军. 推动淡水珍珠养殖业转型升级的思考和建议［J］. 中国水产, 2018, (5): 46-49.
Liu X J. Thoughts and Suggestions on Promoting the Transformation and Upgrading of Freshwater Pearl Aquaculture［J］. Chinese Aquatic Product, 2018, (5): 46-49.
［2］梁靓, 石润润. 全面推进珍珠产业提质增效［J］. 浙江经济, 2017,(20): 50-51.
Liang L, Shi R R. Comprehensively Carrying Forward the Quality Improving and Benefit Increasing of the Pearl Industry［J］. Zhejiang Economy, 2017,(20): 50-51.
［3］Zhu F, Wu K, Ma L, et al. Research on real-time measurement and grading method for pearl color［C］// Proceedings of SPIE-The International Society for Optical Engineering, 2007.
［4］马丹丹, 王鹏程, 刘基宏. 基于机器视觉的条码尺精确测量技术在落纱小车中的应用［J］. 计量学报, 2019, 40(3): 409-415.
Ma D D, Wang P C, Liu J H. Application of Accurate Measurement Technology of Barcode Scale in Doffing Vehicle Based on Machine Vision［J］. Acta Metrologica Sinica, 2019, 40(3): 409-415.
［5］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): 504-506.
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): 504-506.
［6］Tang Y P, Xia S J, Zhu Z L. Research on Pearl Detecting and Grading Based on Monocular Multi-view Machine Vision［J］. British Journal of Applied Science & Technology, 2014, 4(15): 2136-2151.
［7］Xuan Q, Fang B W, Liu Y, et al. Automatic Pearl Classification Machine Based on Multi-Stream Convolutional Neural Network［J］. IEEE Transactions on Industrial Electronics, 2018, 65(8): 6538-6547.
［8］欧阳茜茜, 杨磊, 罗剑秋, 等. 珍珠的成分、结构及呈色机理研究进展［J］. 广州化工, 2012, 40(12): 23-26.
Ouyang Q Q, Yang L, Luo J Q, et al. Components and Structure with its Color Generation Mechanism of Pearl［J］. Guangzhou Chemical Industry, 2012, 40(12): 23-26.
［9］罗永安, 楚世辰, 陈蓉娜. 中国北方珍珠的特征研究［J］. 湖北农业科学, 2017, 56(2): 111-115.
Luo Y A, Chu S C, Chen R N. Characteristics Research of the North Pearl of China［J］. Hubei Agricultural Sciences, 2017, 56(2): 111-115.
［10］Huang D, Swanson E A, Lin C P, et al. Optical coherence tomography［J］. Science, 1991, 254(5035): 1178-1181.
［11］Antony B J, Kim B J, Lang A, et al. Automated segmentation of mouse OCT volumes (ASiMOV): Validation & clinical study of a light damage model［J］. Plos One, 2017, 12(8): e0181059.
［12］Cakir B, Reich M, Lang S, et al. OCT Angiography of the Choriocapillaris in Central Serous Chorioretinopathy: A Quantitative Subgroup Analysis［J］. Ophthalmology and Therapy, 2019, 8(1): 75-86.
［13］Vuong V S, Moisseiev E, Cunefare D, et al. Repeatability of Choroidal Thickness Measurements on Enhanced Depth Imaging OCT using Different Posterior Boundaries［J］. American Journal of Ophthalmology, 2016, 57(12): 104-112.
［14］Sousedik C, Breithaupt R. Full-fingerprint volumetric subsurface imaging using Fourier-domain Optical Coherence Tomography［C］//International Workshop on Biometrics & Forensics, 2017, Coventry, UK. New York: IEEE, 16917452.
［15］Chang S, Schriemer H P, Kleiman R N, et al. Detection and analysis of jade material using optical coherence tomography［C］//SPIE Photonics North 2010, Niagara Falls, Canada. 7750: 77500I.
［16］董俊卿, 李青会, 严鑫. 基于OCT成像技术对常见陶瓷文物断面结构的无损分析［J］. 自然杂志, 2015, 37(5): 325-331.
Dong J Q, Li Q H, Yan X. Nondestructive analysis of section structure of common ceramic cultural relics based on OCT imaging technology［J］. Chinese Journal of Nature, 2015, 37(5): 325-331.
［17］杨珊珊, 朱锐, 米磊, 等. 光学相干层析成像技术对壁画的检测研究［J］. 光学学报, 2015, 35(5): 147-152.
Yang S S, Zhu R, Mi L, et al. Application of optical coherence tomography in the detection of the mural［J］. ActaOpticaSinica, 2015, 35(5): 147-152.
［18］曾楠, 何永红, 马辉, 等. 应用于珍珠检测的光学相干层析技术［J］. 中国激光, 2007, 34(8): 1140-1145.
Zeng N, He Y H, Ma H, et al. Pearl Detection with Optical Coherence Tomography［J］. Chinese Journal of Lasers, 2007, 34(8): 1140-1145.
［19］Yang Z, Yang Z, Sanghoon K, et al. Spectroscopic OCT: towards an effective tool for distinguishing authentic and artificial Chinese freshwater pearls［J］. Optical Materials Express, 2018, 8(3): 622-628.
［20］Lee J H, Shin J G, Kim H Y, et al. Quantitative discrimination of pearls using polarization-sensitive optical coherence tomography［J］. Applied Optics, 2018, 57(9): 2197.
［21］国家质量监督检验检疫总局. GB/T 23886-2009珍珠珠层厚度测定方法-光学相干层析法［S］. 2009.
［22］董俊卿, 李青会. 应用OCT成像技术对海水珍珠的无损测量研究［J］. 红外与激光工程, 2018, 47(4): 30-40.
Dong J Q, Li Q H. Research on nondestructive measurement of sea pearls using optical coherence tomography technique［J］. Infrared and Laser Engineering, 2018, 47(4): 30-40.
［23］Zhou Y, Liu T B, Shi Y, et al. Automated Internal Classification of Beadless Chinese ZhuJiFleshwater Pearls based on Optical Coherence Tomography Images［J］. Scientific Reports, 2016, (6): 33819.
［24］Dandu J R, Thiyagarajan A P, Murugan P R, et al. Brain and pancreatic tumor segmentation using SRM and K-MEANS classification［J］. Health and Technology, 2019, 10: 1-9.
［25］Hartigan J A, Wong M A. Algorithm AS 136: A K-means clustering algorithm［J］. Journal of the Royal Statistical Society, 1979, 28(1): 100-108.
［26］Ju M J, Lee S J, Min E J, et al. Evaluating and identifying pearls and their nuclei by using optical coherence tomography［J］. Optics Express, 2010, 18(13): 13468.
［27］张刚生, 谢先德, 戚绍祺, 等. 贝壳珍珠层的X射线衍射研究［J］. 矿物岩石. 2002, 22(4): 8-11.
Zhang G S, Xie X D, Qi S Q, et al. X-Ray Diffraction Study of Nacre in Shell of Hyriopsis CumingII(Lea)［J］. Journal of Mineralogy & Petrology, 2002. 22(4): 8-11.