Soft biometric retrieval to describe and identify surveillance images

Soft biometrics are human describable, distinguishing human characteristics. We present a baseline solution to the problem of identifying individuals solely from human descriptions, by automatically retrieving soft biometric labels from images. Probe images are then identified from a gallery of known soft biometric signatures, using their predicted labels. We investigate four labelling techniques and a number of challenging re-identification scenarios with this method. We also present a novel dataset, SoBiR, consisting of 8 camera viewpoints, 100 subjects and 4 forms of comprehensive human annotation to facilitate soft biometric retrieval. We report the increased retrieval accuracy of binary labels, the generalising capability of continuous measurements and the overall performance improvement of comparative annotations over categorical annotations.

[1]  D. Sagi,et al.  Gabor filters as texture discriminator , 1989, Biological Cybernetics.

[2]  Daniel Martinho-Corbishley,et al.  Soft biometric recognition from comparative crowdsourced annotations , 2015, ICDP.

[3]  Xiang Li,et al.  Towards more reliable matching for person re-identification , 2015, IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2015).

[4]  Nanning Zheng,et al.  Similarity learning on an explicit polynomial kernel feature map for person re-identification , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[6]  Mark S. Nixon,et al.  Enriching Texture Analysis with Semantic Data , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Shree K. Nayar,et al.  Attribute and simile classifiers for face verification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[8]  Xiaoming Liu,et al.  Demographic Estimation from Face Images: Human vs. Machine Performance , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Shaogang Gong,et al.  Attributes-Based Re-identification , 2014, Person Re-Identification.

[10]  Shengcai Liao,et al.  Multi-label CNN based pedestrian attribute learning for soft biometrics , 2015, 2015 International Conference on Biometrics (ICB).

[11]  Shaogang Gong,et al.  Person Re-Identification by Support Vector Ranking , 2010, BMVC.

[12]  Mark S. Nixon,et al.  Using comparative human descriptions for soft biometrics , 2011, 2011 International Joint Conference on Biometrics (IJCB).

[13]  M. Lee,et al.  The University of Southampton Multi-Biometric Tunnel and introducing a novel 3D gait dataset , 2008, 2008 IEEE Second International Conference on Biometrics: Theory, Applications and Systems.

[14]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Mark S. Nixon,et al.  Soft biometrics for subject identification using clothing attributes , 2014, IEEE International Joint Conference on Biometrics.

[16]  Heitor Silvério Lopes,et al.  Extracting human attributes using a convolutional neural network approach , 2015, Pattern Recognit. Lett..

[17]  Jean-Luc Dugelay,et al.  Bag of soft biometrics for person identification , 2010, Multimedia Tools and Applications.

[18]  Kristen Grauman,et al.  Relative attributes , 2011, 2011 International Conference on Computer Vision.

[19]  Xiaogang Wang,et al.  Person Re-identification: System Design and Evaluation Overview , 2014, Person Re-Identification.

[20]  Mark S. Nixon,et al.  On Semantic Soft-Biometric Labels , 2014, BIOMET.

[21]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[22]  Hai Tao,et al.  Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features , 2008, ECCV.

[23]  Rita Cucchiara,et al.  People reidentification in surveillance and forensics , 2013, ACM Comput. Surv..

[24]  Xiaojing Chen,et al.  Improving person re-identification by soft biometrics based reranking , 2013, 2013 Seventh International Conference on Distributed Smart Cameras (ICDSC).

[25]  Chunxiao Liu,et al.  Person Re-identification: What Features Are Important? , 2012, ECCV Workshops.

[26]  Thomas B. Moeslund,et al.  On soft biometrics , 2015, Pattern Recognit. Lett..

[27]  Bok-Min Goi,et al.  Recognizing Human Gender in Computer Vision: A Survey , 2012, PRICAI.

[28]  Arun Ross,et al.  What Else Does Your Biometric Data Reveal? A Survey on Soft Biometrics , 2016, IEEE Transactions on Information Forensics and Security.