主管:中华人民共和国司法部
主办:司法鉴定科学研究院
ISSN 1671-2072  CN 31-1863/N

中国司法鉴定 ›› 2023 ›› Issue (4): 57-65.DOI: 10.3969/j.issn.1671-2072.2023.04.008

• 鉴定科学 • 上一篇    下一篇

混合式现场变形指纹的校正方法研究

高 畅1,沙良潇1,赵雪珺2,等   

  1. 1.上海市公安局刑事侦查总队,上海 200083; 2.上海市刑事科学技术研究院 上海市现场物证重点实验室,上海 200083; 3.上海理工大学,上海 200093
  • 收稿日期:2022-02-16 出版日期:2023-07-15 发布日期:2023-07-16
  • 通讯作者: 赵雪珺(1987—),女,副研究员,硕士,主要从事现场物证光学探测技术。E-mail:xjzhao1201@163.com 包清(1989—),男,高级工程师,博士,主要从事物证技术学及模式识别。E-mail:2459083965@qq.com
  • 作者简介:高畅(1992—),男,工程师,主要从事痕迹检验。E-mail:1013815197@qq.com
  • 基金资助:
    上海市刑事科学技术研究院现场物证重点实验室开放课题项目(2023XCWZK02)。

A Combined Method to Rectify Distorted Fingerprints Left at Crime Scene

GAO Chang1, SHA Liangxiao1, ZHAO Xuejun2, et al   

  1. 1.Criminal Investigation Department of Shanghai Public Security Bureau, Shanghai 200083, China; 2.Shanghai Key Laboratory of Scene Evidence, Shanghai Resenrch Institute of Criminal Science and Technology, Shanghai 200083, China; 3.University of Shanghai for Science and Technology, Shanghai 200093, China
  • Received:2022-02-16 Published:2023-07-15 Online:2023-07-16

摘要: 目的 探索一种适用于刑事案件现场勘查的曲面客体上变形指纹的校正方法,以提高疑难指纹在案件中的作用率。方法 提出一种由粗到细的校正方法,以传统模式识别复原曲面畸变的结果为基础,在保证其外框架形状不变的条件下对内部图像依照神经网络校正结果进行优化,结合了传统模式识别的鲁棒性和深度卷积神经网络(deep convolutional neural network,DCNN)的精准性。结果 制作了40枚模拟现场潜在变形指纹,在库容量为2 000万的上海市公安局物证鉴定中心指纹测试库检索比较的实验中,所提的新型混合式校正方法效果显著优于DCNN校正方法,50名内比中率从85 %上升至100 %。 结论 该新型混合式校正方法对现场变形指纹的校正有积极意义,尤其是对低质量的变形指纹效果显著,校正后排位提升明显,有助于提高现场勘查中疑难物证的作用率。

关键词: 现场潜在指纹, 变形指纹校正, 混合式方法, 深度卷积神经网络

Abstract: Objective This paper put forward a method for rectifying distorted latent fingerprints left on curved objects at crime scene to improve the application rate of evidence. Methods We proposed a coarse to fine approach, modifying inner image based on fixed frame computed by traditional pattern recognition. It combines the advantages of traditional pattern recognition and deep learning network considering robustness and accuracy. Results We conducted several experiments with forty simulation samples to compare our approach with deep convolutional neural network(DCNN) based approach. The experiments usied the test database of Shanghai Public Security Bureau, which contains twenty million different fingerprints. The proposed approach presented remarkable improvement in fingerprints matching. The hit rate in top fifty candidates rose from 85 % to 100 %. Conclusion The proposed method is promising in handling distorted latent fingerprints, especially for low quality latent fingerprints. The ranks of genuine match rose obviously after rectification, which would improve the usage rate of distorted fingerprint evidence in crime scene investigation.

Key words: latent fingerprint at scene, distortion rectification, combined method, deep convolutional neural network(DCNN)

中图分类号: