首页 > 论文 > 激光与光电子学进展 > 56卷 > 23期(pp:231002--1)

基于改进卷积神经网络的毛发显微图像自动分类

Automatic Classification of Microscopic Hair Images Based on Improved Convolutional Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

利用卷积神经网络对毛发物证显微图像进行自动分类,为进一步提高显微检验技术的自动化程度和毛发物证检验提供技术参考。采用徕卡DVM6数码显微镜在1400倍放大条件下采集6类毛发共60000张样本图像,构建毛发分类数据集。基于卷积神经网络搭建Hair-Net模型,通过该模型对毛发分类数据集进行样本训练和测试验证。实验研究表明,经过参数调试和优化手段的改进后,新的Hair-Net分类精度最高可达97.82%,成功实现了毛发物证显微图像的自动分类,增强了稳健性。

Abstract

This paper uses a convolutional neural network to automatically classify microscopic images of hair evidence with the aim of enhancing the automation of microscopic technology and providing technical reference for test efficiency. Six kinds of microscopic hair images are collected via Leica DVM6 microscope and are magnified 1400 times to form the sample image dataset which contains 60000 images. The network model Hair-Net based on the convolutional neural network is used to conduct sample training and testing using different parameters. Experimental results show that the classification accuracy of improved Hair-Net can reach 97.82% after parameter testing and optimization, demonstrating that this method can realize automatic classification of microscopic hair images and enhance the robustness.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.231002

所属栏目:图像处理

基金项目:中国人民公安大学基本科研业务费、上海市现场物证重点实验室开放课题基金;

收稿日期:2019-04-29

修改稿日期:2019-05-27

网络出版日期:2019-12-01

作者单位    点击查看

姜晓佳:中国人民公安大学刑事科学技术学院, 北京 102623
高树辉:中国人民公安大学刑事科学技术学院, 北京 102623

联系人作者:高树辉(gaoshuhui@ppsuc.edu.cn)

备注:中国人民公安大学基本科研业务费、上海市现场物证重点实验室开放课题基金;

【1】Zhang W, Xu Y C. A review and prospects of the research on hair microstructure [J]. Acta Theriologica Sinica. 2003, 23(4): 339-345.
张伟, 徐艳春. 毛发微观结构研究的回顾与展望 [J]. 兽类学报. 2003, 23(4): 339-345.

【2】Gan Y L, Guo Z W, Liu M H, et al. Scanning electron microscopy study of animal hair in criminal cases [J]. Journal of Chinese Electron Microscopy Society. 2003, 22(6): 489.
甘雅玲, 郭中伟, 刘明辉, 等. 刑事案件中动物毛发的扫描电镜研究 [J]. 电子显微学报. 2003, 22(6): 489.

【3】Zou Y, Quan Y K, Zhu Y C, et al. A study on the microtopography of gunshot damaged hair using ESEM [J]. Chinese Journal of Forensic Medicine. 2006, 21(6): 325-327.
邹友, 权养科, 朱永春, 等. 毛发枪弹损伤的环境扫描电镜研究 [J]. 中国法医学杂志. 2006, 21(6): 325-327.

【4】Zou Y, Tao K M, Li L X, et al. A study on the morphological characterizations of hair physical damage using ESEM Forensic Science and Technology[J]. 0, 2006(1): 4-6.
邹友, 陶克明, 李立新, 等. 毛发常见机械性损伤形态的环境扫描电镜研究 刑事技术[J]. 0, 2006(1): 4-6.

【5】Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 2818-2826.

【6】Zhou F Y, Jin L P, Dong J. Review of convolutional neural network [J]. Chinese Journal of Computers. 2017, 40(6): 1229-1251.
周飞燕, 金林鹏, 董军. 卷积神经网络研究综述 [J]. 计算机学报. 2017, 40(6): 1229-1251.

【7】Li Y D, Hao Z B, Lei H. Survey of convolutional neural network [J]. Journal of Computer Applications. 2016, 36(9): 2508-2515, 2565.
李彦冬, 郝宗波, 雷航. 卷积神经网络研究综述 [J]. 计算机应用. 2016, 36(9): 2508-2515, 2565.

【8】Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks [J]. Science. 2006, 313(5786): 504-507.

【9】He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition . [C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 27-30, 2016, Las Vegas, NV, USA. New York: IEEE. 2016, 770-778.

【10】Chen X, Zhu R, Wang Z Y. Handwritten digits recognition based on fused convolutional neural network model [J]. Computer Engineering. 2017, 43(11): 187-192.
陈玄, 朱荣, 王中元. 基于融合卷积神经网络模型的手写数字识别 [J]. 计算机工程. 2017, 43(11): 187-192.

【11】Zhong J Y, Yang B, Li Y H, et al. Image fusion and super-resolution with convolutional neural network [M]. ∥Tan T, Li X, Chen X, et al. Pattern recognition. CCPR 2016. Communications in computer and information science. Singapore: Springer. 2016, 663: 78-88.

【12】Xiao J S, Liu E Y, Zhu L, et al. Improved image super-resolution algorithm based on convolutional neural network [J]. Acta Optica Sinica. 2017, 37(3): 0318011.
肖进胜, 刘恩雨, 朱力, 等. 改进的基于卷积神经网络的图像超分辨率算法 [J]. 光学学报. 2017, 37(3): 0318011.

【13】Dong J F, Zheng B C, Yang Z J. Character recognition of license plate based on convolution neural network [J]. Journal of Computer Applications. 2017, 37(7): 2014-2018.
董峻妃, 郑伯川, 杨泽静. 基于卷积神经网络的车牌字符识别 [J]. 计算机应用. 2017, 37(7): 2014-2018.

【14】Nguyen N G, Tran V A, Ngo D L, et al. DNA sequence classification by convolutional neural network [J]. Journal of Biomedical Science and Engineering. 2016, 9(5): 280-286.

【15】Jiang S. Image recognition based on convolutional neural networks [D]. Changchun: Jilin University. 2017.
蒋帅. 基于卷积神经网络的图像识别 [D]. 长春: 吉林大学. 2017.

【16】Gao H L. Military image classification based on convolutional neural network [J]. Application Research of Computers. 2017, 34(11): 3518-3520.
高惠琳. 基于卷积神经网络的军事图像分类 [J]. 计算机应用研究. 2017, 34(11): 3518-3520.

【17】Wang X, Liu Y, Li G Y. Moving object detection algorithm based on improved visual background extractor algorithm [J]. Laser & Optoelectronics Progress. 2019, 56(1): 011007.
王旭, 刘毅, 李国燕. 基于改进视觉背景提取算法的运动目标检测方法 [J]. 激光与光电子学进展. 2019, 56(1): 011007.

【18】Schroff F, Kalenichenko D, Philbin J. FaceNet: a unified embedding for face recognition and clustering . [C]∥2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 7-12, 2015, Boston, MA, USA. New York: IEEE. 2015, 815-823.

【19】Sun Y, Liang D, Wang X G, et al. -02-03)[2019-04-28] . https:∥arxiv. 2015, org/abs/1502: 00873.

【20】Hafemann L G, Sabourin R, Oliveira L S. Learning features for offline handwritten signature verification using deep convolutional neural networks [J]. Pattern Recognition. 2017, 70: 163-176.

【21】Liang X L. Verification of off-line handwritten signature based on the improved neural network [D]. Beijing: China University of Political Science and Law. 2017.
梁曦璐. 基于改进神经网络的离线签名笔迹识别 [D]. 北京: 中国政法大学. 2017.

【22】Abdel-Hamid O, Mohamed A R, Jiang H, et al. Convolutional neural networks for speech recognition [J]. ACM Transactions on Audio, Speech, and Language Processing. 2014, 22(10): 1533-1545.

【23】Karpathy A, Toderici G, Shetty S, et al. Large-scale video classification with convolutional neural networks . [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition, June 23-28, 2014, Columbus, OH, USA. New York: IEEE. 2014, 1725-1732.

【24】Li Y. Research on gait recognition based on three-dimensional convolutional neural network [D]. Beijing: Beijing Jiaotong University. 2018.
李影. 基于三维卷积神经网络步态识别方法的研究 [D]. 北京: 北京交通大学. 2018.

【25】Zhao Y J, Zhou S P. Wearable device-based gait recognition using angle embedded gait dynamic images and a convolutional neural network [J]. Sensors. 2017, 17(3): 478.

【26】Wen Y D, Zhang K P, Li Z F, et al. A discriminative feature learning approach for deep face recognition [M]. ∥Leibe B, Matas J, Sebe N, et al. Computer vision-ECCV 2016. Lecture notes in computer science. Cham: Springer. 2016, 9911: 499-515.

【27】Yu C B, Tian T, Xiong D E, et al. Joint supervision of center loss and Softmax loss for face recognition [J]. Journal of Chongqing University. 2018, 41(5): 92-100.
余成波, 田桐, 熊递恩, 等. 中心损失与Softmax损失联合监督下的人脸识别 [J]. 重庆大学学报. 2018, 41(5): 92-100.

引用该论文

Jiang Xiaojia,Gao Shuhui. Automatic Classification of Microscopic Hair Images Based on Improved Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(23): 231002

姜晓佳,高树辉. 基于改进卷积神经网络的毛发显微图像自动分类[J]. 激光与光电子学进展, 2019, 56(23): 231002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF