Imputing human descriptions in semantic biometrics

Human identification at a distance has received significant interest due to the ever increasing surveillance infrastructure. Biometrics such as face and gait offer a suitable physical attribute to uniquely identify people from a distance. When linking this with human perception, these biometrics suffer from the semantic gap which is the difference between how people and how biometrics represent and describe humans. Semantic biometrics bridges this gap, allowing conversions between gait biometrics and semantic descriptions. One possible application of semantic biometrics is to automatically search surveillance footage for a person who best matches a given semantic description - possibly obtained from an eyewitness report. We now exploit patterns and structure within the physical descriptions to be able to predict occluded or erroneous data, thereby widening application potential. We show how imputation techniques can be used to increase accuracy and robustness of automatic semantic annotation of gait signatures.

[1]  J. Shepherd,et al.  Adult Eyewitness Testimony: Whole body information: Its relevance to eyewitnesses , 1994 .

[2]  Ito Wasito,et al.  Nearest neighbour approach in the least-squares data imputation algorithms , 2005, Inf. Sci..

[3]  Johannes Peltola,et al.  Soft biometrics - combining body weight and fat measurements with fingerprint biometrics , 2006, Pattern Recognit. Lett..

[4]  N. Hamdy,et al.  Soft and hard biometrics fusion for improved identity verification , 2004, The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04..

[5]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[6]  Anil K. Jain,et al.  Soft Biometric Traits for Personal Recognition Systems , 2004, ICBA.

[7]  Mark S. Nixon,et al.  Performing content-based retrieval of humans using gait biometrics , 2008, Multimedia Tools and Applications.

[8]  Russ B. Altman,et al.  Missing value estimation methods for DNA microarrays , 2001, Bioinform..

[9]  Peter J. van Koppen,et al.  Portraying Perpetrators; The Validity of Offender Descriptions by Witnesses , 1997 .

[10]  Jill Rowan Adult Eyewitness Testimony: Current Trends and Developments , 1995 .

[11]  Mark S. Nixon,et al.  Automatic Recognition by Gait , 2006, Proceedings of the IEEE.

[12]  Mark S. Nixon,et al.  On a Large Sequence-Based Human Gait Database , 2004 .

[13]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[14]  J. Schooler,et al.  Person Descriptions as Eyewitness Evidence , 2006 .

[15]  M.S. Nixon,et al.  The Use of Semantic Human Description as a Soft Biometric , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.