Footprint automatic alignment algorithm fusing texture features and depth information

LING Jian-yong; HE Xin; WEI Zhong-hui; LI Yi-mang; LIANG Guo-long

doi:10.3788/OPE.20142207.1946

您当前的位置：

首页 >

文章列表页 >

Footprint automatic alignment algorithm fusing texture features and depth information

更新时间：2020-08-13

- Footprint automatic alignment algorithm fusing texture features and depth information
- Optics and Precision Engineering Vol. 22, Issue 7, Pages: 1946-1954(2014)
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院大学北京,中国,100049
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20142207.1946
  CLC： TP391
- Received：16 May 2013，
  
  Revised：13 June 2013，
  
  Published：25 July 2014
- 稿件说明：
移动端阅览
凌剑勇, 何昕, 魏仲慧等. 融合纹理特征与深度信息的足迹自动比对算法[J]. 光学精密工程, 2014,22(7): 1946-1954

LING Jian-yong, HE Xin, WEI Zhong-hui etc. Footprint automatic alignment algorithm fusing texture features and depth information[J]. Editorial Office of Optics and Precision Engineering, 2014,22(7): 1946-1954
凌剑勇, 何昕, 魏仲慧等. 融合纹理特征与深度信息的足迹自动比对算法[J]. 光学精密工程, 2014,22(7): 1946-1954 DOI： 10.3788/OPE.20142207.1946.

LING Jian-yong, HE Xin, WEI Zhong-hui etc. Footprint automatic alignment algorithm fusing texture features and depth information[J]. Editorial Office of Optics and Precision Engineering, 2014,22(7): 1946-1954 DOI： 10.3788/OPE.20142207.1946.

摘要

讨论了刑事案件侦破过程涉及的足迹检验方法。考虑现有的足迹比对研究没有将足迹的深度信息与纹理信息分离后进行比对，提出了一种融合纹理特征与深度信息的比对方法来实现足迹的自动比对功能。该方法通过四步相移补偿法来获取真实足迹特征的三维信息；利用改进的二维高斯滤波器分离足迹的表面纹理特征与深度信息。最后，采用区域互相关测度分别计算不同三维足迹信息中纹理信息之间和深度信息之间的相似度，并按一定策略将量化的相似度信息转化为定性的判别结果。实验结果表明，提出的方法能够有效分离足迹中的纹理信息和深度信息，并能通过软件编程实现计算机对足迹的自动比对。与传统的针对二维图像灰度信息的足迹对比方法相比，提出的算法能够描述真实的足迹形貌，在现有数据集范围内，自动比对正确率不低于90%；加入人工干预后，比对正确率可达100%。得到的结果验证了提出方法的有效性。

Abstract

The footprint detection methods in criminal cases were discussed.As existing footprint comparison does not separate the footprint depth information and texture information

a comparison method fusing texture features and depth information was proposed to achieve automatic comparison of footprints.First

3-D information of a footprint was obtained through four-step phase shift compensation method to retain much 3-D information of the footprint

and a 2-D variable-scale Gaussian filter was designed to separate footprint surface texture features and depth information.Finally

the regional cross-correlation measurement method was used to calculate the similarity of texture information and the depth information of the 3-D footprint

and the similarity information was quantized and translated in qualitative results by proposed strategy.Experimental results show that the proposed method can separate the texture and depth information of footprints effectively

and footprint comparison is realized automatically by computer software.Comparing to the traditional method of 2-D image grayscale information

the proposed algorithm describes the footprint information more completely.The accuracy rate of automatic comparison is higher than 90%

and the accuracy rate of comparison reaches 100% after adding human intervention based on the existing database

which verifies the effectiveness of the proposed method.

关键词

Keywords

references

RAINER G,BJRN E,HEIKO S,JOACHIM H. Comparison and classification of 3D objects surface point clouds on the example of feet[J]. Machine Vision and Applications,2011,22:235-243.

闫旭琴. 自动鞋印分析与比对系统中的关键技术的研究与实现. 青岛:山东科技大学,2007. YAN X Q. The research and implementation of the major techniques in automatic shoeprint analyzing and matching system. Qingdao:Shandong University of Science and Technology,2007. (in Chinese)

董菲菲. 基于三维鞋印的鞋底花纹分类及模块设计. 南昌:南昌大学,2010. DONG F F. Classification of sole patterns from a 3-Dimensional shoe model and module design. Nanchang:The University of Nanchang,2010. (in Chinese)

蒋晓玲. 基于图像处理技术的足迹检验系统的设计与实现. 南京:南京理工大学,2011. JIANG X L. Design and implementation of footmark technology. Nanjing:Nanjing University of Science and Technology,2011. (in Chinese)

YI T,SARGUR N S,HARISH K,JASON J C. Footwear print retrieval system for real crime scene marks. IWCF 2010,2011,88-100.

SARAH R,SIMON R,WESLEY V,et al. . Reliability of a two-dimensional footprint measur-ement approach[J]. Science and Justice,2010,113-118.

郭威. 立体痕迹三维数据化检验初探[J]. 中国人民公安大学学报:自然科学版,2008,4:12-13. GUO W. 3D-based digitalized examination on stereoscopic traces[J]. Journal o f Chinese People's Public Security University:Science and Technology,2012,4:12-13. (in Chinese)

郭威,丁锰,杜春勇. 一种三维测量和检验枪弹痕迹的方法[J]. 中国人民公安大学学报:自然科学版,2009,2:5-7. GUO W,DING M,DU CH Y. 3D-based measurement and examination of firearms traces[J]. Journal of Chinese People's Public Security University:Science and Techno logy,2009,2:5-7. (in Chinese)

王欣,张明明,于晓,等. 应用改进迭代最近点方法的点云数据配准[J]. 光学精密工程,2012,20 (9):2068-2077. WANG X,ZHANG M M,YU X,et al. Point cloud registration based on improved iterative closest point method[J]. Opt. Precision Eng. ,2012,20(9):2068-2077. (in Chinese)

孙军华,谢萍,刘震,等. 基于分层块状全局搜索的三维点云自动匹配[J]. 光学精密工程,2013,21(1):174-180. SUN J H,XIE P,LIU ZH,et al. Automatic 3D point cloud registration based on hierarchical block global secrch[J]. Opt. Precision Eng. ,2013,21(1):174-180. (in Chinese)

A Superior Solution:What Makes Forensic Technology's IBIS TRAX-3D the Most Advanced Ballistic Imaging Solution in the World Today. http://www. forensictechnology. com,2009.

乔培玉. 基于三维形貌的弹痕比对系统的研究. 长春:中国科学院长春光学精密机械与物理研究所,2012. QIAO P Y. Research on ballisitics of bullet comparing system based on 3-D surface topography. Changchun:Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,China,2012. (in Chinese)

李平,魏仲慧,何昕,等. 基于自适应互信息测度法的弹壳比对[J]. 光电工程,2012,39(12):42-48. LI P,WEI ZH ZH,HE X,et al. Catridge case comparison based on adaptive mutual information measure method[J]. Opto-Electronic Engineering,2012,39(12):42-48. (in Chinese)

SHEIDA H,RIAN M S,JOHN B. The interpretation of shoeprint comparison class correspondences[J]. Science and Justice,2012,52:243-248.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Low-light image enhancement algorithm based on light scattering attenuation model

Detection and classification of welding defects by magneto-optical imaging under alternating/rotating magnetic field

Multi-features manifold discriminant embedding for hyperspectral image classification

Hardware friendly stereo matching by employing weighted support region

Related Author

SHI Jihao

ZHONG Yuzhong

ZHENG Xiujuan

DIAN Songyi

Yan-feng LI

Xiang-dong GAO

Yu-kun JI

Chun-cao WANG

Related Institution

College of Electrical Engineering， Sichuan University

Guangdong Provincial Welding Engineering Technology Research Center, Guangdong University of Technology

Key Laboratory of Optoelectronic Technique System of the Ministry of Education, Chongqing University

Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰