Please use this identifier to cite or link to this item:
Title: Criminal and victim identification based on soft biometrics
Authors: Chan, Frodo Kin-Sun
Keywords: DRNTU::Engineering::Computer science and engineering
Issue Date: 2017
Source: Chan, F. K.-S. (2017). Criminal and victim identification based on soft biometrics. Doctoral thesis, Nanyang Technological University, Singapore.
Abstract: Criminal and victim identification is always important in forensic investigation. However, it can be a very challenging problem for identifying criminals and victims in digital media when only their non-facial body sites are available in evidence images. These criminals and victims can be masked gunmen, paedophiles, and victims in child pornographic and voyeur images. To solve the above problem, several novel alignment and identification approaches are proposed in this thesis. Firstly, lower leg geometry is proposed as a soft biometric trait for criminal and victim identification. This study provides a foundation for further research based on body geometry. Secondly, leg geometry and hair follicles are proposed to align the androgenic hair patterns in consideration of viewpoint and pose variations, which were ignored by a recent paper suggesting androgenic hair patterns for identification. Experiments on 1,138 high and low resolution images from 283 different legs show that the proposed alignment algorithms provide improvements of 5%-10% on different experimental settings. Thirdly, a new approach is developed to improve the identification of androgenic hair patterns significantly. In the past, it was believed that androgenic hair patterns in low resolution images are not a distinctive biometric trait because of the previous result. A new algorithm, which makes use of leg geometry to align lower leg images, large feature sets (about 60,000 features) extracted through multi-directional gridding systems to increase discriminative power and robustness, the partial least squares (PLS) method to handle imbalanced training data and to perform the multi-grid feature fusion, and scheme generating more positive samples to increase robustness against viewpoint and pose variation, is proposed. Experimental results on 1,493 low resolution leg images with large viewpoint and pose variations from 412 legs demonstrate the proposed multi-grid feature fusion algorithm provides a significant improvement. Fourthly, estimation of soft biometric traits (e.g. height, BMI, age) is proposed. Recent studies demonstrated that soft biometric traits can be effectively estimated through comparative verbal descriptions (e.g. taller and shorter) given by witnesses. The usage of descriptions is extended to non-verbal comparative features extracted from legs for soft biometrics estimation. The proposed algorithm is examined on more than 2000 front and side leg images. The experimental results demonstrate that the proposed algorithm offers comparable performance with the existing methods. Fifthly, the distinctiveness of human skin texture is evaluated by comparing with blood vessels. Recent studies show that blood vessel patterns can be visualized in different body parts. However, their visualization methods have limitations on images with low quality and subjects with high concentration of body fat, high concentration of melanin, and dense hair. In this study, more than 6000 inner forearm and thigh images were collected from a laboratory environment and the Internet with large pose, viewpoint, resolution, and illumination variations. The experimental results indicate the potential use of skin texture for criminal and victim identification.
DOI: 10.32657/10356/70576
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Theses

Files in This Item:
File Description SizeFormat 
Thesis_Frodo_revise.pdfThesis of Frodo8.25 MBAdobe PDFThumbnail

Page view(s)

Updated on Jun 19, 2021

Download(s) 50

Updated on Jun 19, 2021

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.