Gait recognition by fusing direct cross-view matching scores for criminal investigation

被引：0

作者：

机构：

[1] Institute of Scientific and Industrial Research, Osaka University, Ibaraki

来源：

| 1600年 / Information Processing Society of Japan卷 / 05期

基金：

日本学术振兴会;

关键词：

Biometrics; Criminal investication; Cross-view; Fusion; Gait recognition;

D O I：

10.2197/ipsjtcva.5.35

中图分类号：

学科分类号：

摘要：

We focus on gait recognition for criminal investigation. In criminal investigation, person authentication is performed by comparing target data at the crime scene and multiple gait data with slightly different views from that of the target data. For this task, we propose fusion of direct cross-view matching. Cross-view matching generally produces worse result than those of same-view matching when view-variant features are used. However, the correlation between cross-view matching with different view pairs is low and it provides improved accuracy. Experimental results performed utilizing large-scale dataset under settings resembling actual criminal investigation cases, show that the proposed approach works well. © 2013 Information Processing Society of Japan.

引用

页码：35 / 39

页数：4

共 14 条

[1]

Alonso-Fernandez F., Fierrez J., Ramos D., Ortega-Garcia J., Dealing with sensor interoperability in multi-biometrics: The UPM experience at the biosecure multimodal evaluation 2007, Proc. SPIE 6994, Biometric Technologies for Human Identification IV, (2008)

[2]

Bouchrika I., Goffredo M., Carter J., Nixon M., On using gait in forensic biometrics, Journal of Forensic Science, 56, 4, pp. 882-889, (2011)

[3]

Han J., Bhanu B., Individual recognition using gait energy image, IEEE Trans. Pattern Analysis and Machine Intelligence, 28, 2, pp. 316-322, (2006)

[4]

Han J., Bhanu B., Roy-Chowdhury A., A study on view-insensitive gait recognition, Proc. IEEE Int. Conf. Image Processing, 3, pp. 297-300, (2005)

[5]

Iwama H., Okumura M., Makihara Y., Yagi Y., The OU-ISIR gait database comprising the large population dataset and performance evaluation of gait recognition, IEEE Trans. Information Forensics and Security, 7, 5, pp. 1511-1521, (2012)

[6]

Kusakunniran W., Wu Q., Zhang J., Li H., Gait recognition under various viewing angles based on correlated motion regression, IEEE Trans. Circuits and Systems for Video Technology, 22, 6, pp. 966-980, (2012)

[7]

Lam T.H.W., Cheung K.H., Liu J.N.K., Gait flow image: A silhouette-based gait representation for human identification, Pattern Recogn., 44, pp. 973-987, (2011)

[8]

Larsen P.K., Simonsen E.B., Lynnerup N., Gait analysis in forensic medicine, Journal of Forensic Sciences, 53, 5, pp. 1149-1153, (2008)

[9]

Lynnerup N., Vedel J., Person identification by gait analysis and photogrammetry, Journal of Forensic Science, 50, 1, pp. 112-118, (2005)

[10]

Makihara Y., Sagawa R., Mukaigawa Y., Echigo T., Yagi Y., Gait recognition using a view transformation model in the frequency domain, Proc. 9th European Conf. Computer Vision, pp. 151-163, (2006)

← 1 2 →