Skull identification based on least square canonical correlation analysis

Ming-quan ZHOU; Wen YANG; Peng-yue LIN; Guo-hua GENG; Xiao-ning LIU; Kang LI

doi:10.37188/OPE.20212901.0201

您当前的位置：

首页 >

文章列表页 >

Skull identification based on least square canonical correlation analysis

Information Sciences | 更新时间：2021-02-04

- Skull identification based on least square canonical correlation analysis
- Optics and Precision Engineering Vol. 29, Issue 1, Pages: 201-210(2021)
- 作者机构：
  
  1.西北大学信息科学与技术学院，陕西西安 710127
  2.北京师范大学信息科学与技术学院，北京 100875
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20212901.0201
  CLC： TP394.1;TH691.9
- Received：03 August 2020，
  
  Revised：30 September 2020，
  
  Published：15 January 2021
- 稿件说明：
移动端阅览
周明全,杨稳,林芃樾等.基于最小二乘正则相关性分析的颅骨身份识别[J].光学精密工程,2021,29(01):201-210.

ZHOU Ming-quan,YANG Wen,LIN Peng-yue,et al.Skull identification based on least square canonical correlation analysis[J].Optics and Precision Engineering,2021,29(01):201-210.
周明全,杨稳,林芃樾等.基于最小二乘正则相关性分析的颅骨身份识别[J].光学精密工程,2021,29(01):201-210. DOI： 10.37188/OPE.20212901.0201.

ZHOU Ming-quan,YANG Wen,LIN Peng-yue,et al.Skull identification based on least square canonical correlation analysis[J].Optics and Precision Engineering,2021,29(01):201-210. DOI： 10.37188/OPE.20212901.0201.

摘要

为了可靠地测量颅骨与面皮之间的相关性，提高颅骨识别能力，本文提出了一种基于最小二乘正则相关性分析的颅骨识别方法。构建颅骨和面皮的统计形状模型，将高维颅骨和面皮映射到低维形状参数空间；基于最小二乘正则相关性分析提取颅骨和面皮的主相关信息，构建整体相关性分析模型，用于度量颅骨与面皮的整体相关性；然后，考虑到颅骨不同区域的相关度不同，将颅骨分为前额、眼睛、鼻子、嘴巴和轮廓5个区域，基于最小二乘正则相关性分析提取颅骨和面皮的主相关信息，分区域构建区域相关性分析模型，用于度量颅骨与面皮之间的局部细节相关性；最后，分别采用整体相关性分析模型和区域相关性分析模型度量颅骨与面皮的匹配关系，计算颅骨与面皮库中每个面皮之间的匹配分数，具有最高匹配分数的面皮即为正确的识别结果，从而实现颅骨身份识别。实验结果表明，整体相关性分析模型的识别准确率为85.2%，单一区域相关性分析模型中轮廓区域的识别准确率最高，鼻子区域的识别准确率最低；通过融合5个区域建立的相关性分析模型，识别准确率高达95.2%，基于区域融合的方法优于整体相关性分析方法。

Abstract

To measure the correlation between the skull and the face reliably and improve the skull recognition ability， a skull identification method based on least squares canonical dependency analysis （LSCDA） was proposed. First， a statistical shape model of the skull and facial skin was constructed， and the high-dimensional skull and facial skin were mapped to the low-dimensional shape parameter space. Second， the main relevant information about the skull and facial skin was extracted based on LSCDA， and an overall correlation analysis model was constructed to measure the relationship between the skull and the skin. By considering the difference in the correlations between different regions of the skull， the skull was divided into five regions： the forehead， eyes， nose， mouth， and contour. Based on LSCDA， the main relevant information about the skull and facial skin was extracted and constructed by region. A regional correlation analysis model was used to measure the local detail correlation between the skull and the face. Finally， a global correlation analysis model and a regional correlation analysis model were used to measure the matching relationship between the skull and facial skin， and the matching score between each face in the skull and facial skin database was calculated. The face with the highest matching score yielded the correct recognition result for achieving skull identification. The experimental results reveal that the recognition accuracy of the overall correlation analysis model is 85.2%. The recognition accuracy of the contour region in the single region correlation analysis model is the highest， whereas that of the nose region is the lowest. The correlation analysis established by fusing the five regional models indicates that the recognition accuracy rate is as high as 95.2% and that the method based on regional fusion is better than the overall correlation analysis method.

关键词

Keywords

references

BRINKMANN B . Forensic anthropology ［J］. International Journal of Legal Medicine ， 2007 ， 121 （ 6 ）： 431 - 432 .

DAMAS S ， CORDÓNOSCAR ， IBÁÑEZÓSCAR ， et al . . Forensic identification by computer-aided craniofacial superimposition： A survey ［J］. ACM Computing Surveys ， 2011 ， 43 （ 4 ）： 1 - 27 .

HU Y ， DUAN F ， YIN B ， et al . . A hierarchical dense deformable model for 3D face reconstruction from skull ［J］. Multimedia Tools & Applications ， 2013 ， 64 （ 2 ）： 345 - 364 .

BAI F ， CHENG Z ， QIAO X ， et al .. Face reconstruction from skull based on least squares canonical dependency analysis ［C］. IEEE International Conference on Systems . IEEE ， 2016 ： 3612 - 3615 .

LUO L ， WANG MY ， TIAN Y ， et al . . Automatic sex determination of skulls based on a statistical shape model ［J］. Computational & Mathematical Methods in Medicine ， 2013 ： 251628 .

LI Y ， CHANG L ， QIAO X ， et al .. Craniofacial reconstruction based on least square support vector regression ［C］. IEEE International Conference on Systems ， 2014 ： 1147 - 1151 .

FENTON T W ， HEARD A N ， SAUER N J . Skull-photo superimposition and border deaths： identification through exclusion and the failure to exclude ［J］. Journal of Forensic Sciences ， 2008 ， 53 （ 1 ）： 34 - 40 .

IBÁNEZ O ， VALSECCHI A ， CAVALLI F ， et al . . Study on the criteria for assessing skull-face correspondence in craniofacial superimposition ［J］. Legal Medicine ， 2016 ， 23 ： 59 - 70 .

RICCI A ， MARELLA G L ， APOSTOL M A . A new experimental approach to computer-aided face/skull identification in forensic anthropology ［J］. Am J Forensic Med Pathol ， 2006 ， 27 （ 1 ）： 46 - 49 .

IBÁNEZ O ， CORDÓN O ， DAMAS S . A cooperative coevolutionary approach dealing with the skull-face overlay uncertainty in forensic identification by craniofacial superimposition ［J］. Soft Computing ， 2012 ， 16 （ 5 ）： 797 - 808 .

BALLERINI L ， CORDON O ， DAMAS S ， et al .. Craniofacial superimposition in forensic identification using genetic algorithms ［C］. International Symposium on Information Assurance & Security . IEEE ， 2007 ： 429 - 434 .

田中金 . 基于分区变形颅面复原算法的研究与实现［D］. 西安：西北大学， 2011 .

TIAN ZH J . Research and Implementation of Craniofacial Reconstruction Algorithm Based on Partition Deformation ［D］. Xi'an ： Northwestern University ， 2011 . （in Chinese）

DUAN F Q ， YANG S ， HUANG D H ， et al . . Craniofacial reconstruction based on multi-linear subspace analysis ［J］. Multimedia Tools & Applications ， 2014 ， 73 （ 2 ）： 809 - 823 .

SONG M ， TAO D ， HUANG X ， et al . . Three-dimensional face reconstruction from a single image by a coupled RBF network ［J］. IEEE Trans Image Process ， 2012 ， 21 （ 5 ）： 2887 - 2897 .

王俊娟，许磊，黎智辉，等 . 三维人脸图像的数据采集与预处理［J］. 刑事技术， 2015 ， 40 （ 2 ）： 98 - 101 .

WANG J J ， XU L ， LI ZH H ， et al . . Acquisition and pre-processing of 3D facial image ［J］. Forensic Science and Technology ， 2015 ， 40 （ 2 ）： 98 - 101 . （in Chinese）

DUAN F ， YANG Y ， LI Y ， et al . . Skull identification via correlation measure between skull and face shape ［J］. Information Forensics & Security IEEE Transactions on ， 2014 ， 9 （ 8 ）： 1322 - 1332 .

ROSHNARA N N P P ， JABBAR S . Efficient 3D visual hull reconstruction based on marching cube algorithm ［C］. International Conference on Innovations in Information . IEEE ， 2015 ： 1 - 6 .

朱艳芳，刘晓宁，耿国华 . 基于体素模型与多尺度约束的三维面皮点对应［J］. 西北大学学报：自然科学版， 2017 ， 47 （ 1 ）： 43 - 49 .

ZHU Y F ， LIU X N ， GENG G H . A correspondence method of 3D facial points based on voxel models and multi-scale constraints ［J］. Journal of Northwest University： Natural Science Edition ， 2017 ， 47 （ 1 ）： 43 - 49 . （in Chinese）

DENG Q Q ， ZHOU M Q ， WU Z K ， et al . . A regional method for craniofacial reconstruction based on coordinate adjustments and a new fusion strategy ［J］. Forensic Science International ， 2016 ， 259 ： 19 - 31 .

DENG Q Q ， ZHOU M Q ， WU Z K . An automatic non-rigid registration method for dense surface models ［C］. IEEE International Conference on Intelligent Computing and Intelligent Systems . IEEE ， 2010 ： 888 - 892 .

贺毅岳，马自萍，高妮，等 . 基于偏最小二乘回归局部形状关系建模的颅面复原方法［J］. 计算机应用， 2016 ， 36 （ 3 ）： 820 - 826 .

HE Y Y ， MA Z P ， GAO N ， et al . . Craniofacial reconstruction method based on partial least squares regression model of local craniofacial morphological correlation ［J］. Journal of Computer Applications ， 2016 ， 36 （ 3 ）： 820 - 826 . （in Chinese）

KARASUYAM M ， SUGIYAMA M . Canonical dependency analysis based on squared-loss mutual information ［J］. Neural Networks ， 2012 ， 34 （ 10 ）： 46 - 55 .

ZHANG Y ， XU S ， SUN N . Skull recognition based on embedded hidden markov models ［C］. World Congress on Intelligent Control & Automation . IEEE ， 2008 ： 1153 - 1158 .

Views

410

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image reconstruction based on deep compressive sensing combined with global and local features

Lens-less imaging via score-based generative model

Hyperspectral reconstruction from RGB images based on Res2-Unet deep learning network

CBCT image reconstruction using a mixed Poisson-Gaussian maximum likelihood function

X-ray luminescence computed tomography based on improved spectral projected gradient algorithm

Related Author

WANG Shanshan

ZHOU Yujie

XU Qianfeng

ZHONG Yuanhong

Hong PENG

Chunhua WU

Qiegen LIU

Wenbo WAN

Related Institution

Institute of Physical Science and Information Technology， Anhui University

School of Microelectronics and Communication Engineering， Chongqing University

School of Information Engineering， Nanchang University

School of Aerospace Science and Technology， Xidian University

School of Information Engineering， Chang'an 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