Total views : 396

Survey on Colour, Texture and Shape Features for Person Re-Identification

Affiliations

  • Department of Computer Science and Engineering, Manonmaniam Sundaranar University, Tirunelveli - 627012, Tamil Nadu, India

Abstract


Background: Re-identification is the pattern recognition problem which helps to identify the person in surveillance network. Feature plays an important role in person re-identification. Objective: The main objective of this paper is to analyze the properties of few existing features for person re-identification. Methods/Statistical Analysis: The features for re-identification is categorized into three groups namely colour, texture and shape. In this work various methods for extracting these features and their challenges are considered for survey and their properties, advantages disadvantages and applications are presented as a summary. Findings: From the analysis we found that colour and texture features outperform the shape feature. Application/Improvements: This analysis helps to understand the characteristics of the existing features and develop the new robust feature for improving the matching rate for person re-identification.

Keywords

Colour, Re-identification, Shape Feature, Texture.

Full Text:

 |  (PDF views: 399)

References


  • Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y. Locality constrained linear coding for image classification. Proc IEEE Int Conf Comput Vis Pattern Recognit; Jun 2010. p. 3360–7.
  • Saminathan K, Chakravarthy T, Devi MC. Comparative study on biometric iris recognition based on hamming distance and multi block local binary pattern. Indian Journal of Science and Technology. 2015; 8(11):1.
  • Urbach E, Roerdink JBTM, Wilkinson MHF. Connected shape-size pattern spectra for rotation and scale-invariant classification of gray-scale images. IEEE Trans Pattern Anal Mach Intell. 2007 Feb; 29(2):272–85.
  • Khedher MI, El Yacoubi MA, Dorizzi B. Multi-shot surf-based person re-identification via sparse representation. 2013 10th IEEE International Conference on IEEE Advanced Video and Signal based Surveillance (AVSS); 2013. Layne R, Hospedales TM, Gong S. Person re-identification by attributes. British Machine Vision Conference; 2012.
  • Dalal N, Triggs B. Histograms of oriented gradients for human detection. Proc IEEE Int Conf Comput Vis Pattern Recognit; 2005 Jun. p. 886–93.
  • Satpathy A, Jiang X, Eng H-L. Human detection by quadratic classification on subspace of extended histogram of gradients. IEEE Trans Image Process. 2014 Jan; 23(1):287–97.
  • Satpathy A, Jiang X, Eng H-L. Extended histogram of gradients feature for human detection. Proc IEEE Int Conf Image Process; 2010 Sep. p. 3473–6.
  • Satpathy A, Jiang X, Eng H-L. Extended histogram of gradients with asymmetric principal component and discriminant analysis for human detection. Proc IEEE Can Conf Comput Robot Vis; 2011 May. p. 64–71.
  • Wang X, Bai X, Liu W, Latecki L. Feature context for image classification and object detection. Proc IEEE Int Conf Comput Vis Pattern Recognit; 2011 Jun. p. 961–8.
  • Guo Z, Zhang L, Zhang D. A completed modeling of local binary pattern operator for texture classification. IEEE Trans Image Process. 2010 Jun; 19(6):1657–63.
  • Chunxiao L, et al. Person re-identification: What features are important? Computer Vision–ECCV 2012. Workshops and Demonstrations. Springer Berlin Heidelberg; 2012.
  • Liao S, Law M, Chung A. Dominant local binary patterns for texture classification. IEEE Trans Image Process. 2009 May; 18(5):1107–18.
  • Miao, Jiang X. Interest point detection using rank order log filter. Pattern Recognition. 2013; 46(11):2890–01.
  • Zheng W-S, Gong S, Xiang T. Reidentification by relative distance comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2013; 35(3):653–68.
  • Gray D, Tao H. Viewpoint invariant pedestrian recognition with an ensemble of localized features. Proceedings of the European Conference on Computer Vision; 2008.
  • Kostinger M, Hirzer M, Wohlhart P, Roth PM, Bischof H. Large scale metric learning from equivalence constraints. Proc Int Conf Comput Vis Pattern Recognit; 2012. p. 2288–95.
  • Zhang G, Wang Y, Kato J, Marutani T, Kenji M. Local distance comparison for multiple-shot people re-identification. Proc Asian Conf Comput Vis; 2013. p. 677–90.
  • Ma B, Su Y, Jurie F. Local descriptors encoded by fisher vectors for person re-identification. Computer Vision–ECCV 2012 Workshops and Demonstrations; Springer Berlin Heidelberg. 2012.
  • Yang L, Jin R. Distance metric learning: A comprehensive survey. East Lansing, MI, USA: Michigan State Univ; 2006,
  • Satpathy A, Jiang X, Eng H-L. Human detection by quadratic classification on subspace of extended histogram of gradients. IEEE Trans Image Process. 2014 Jan; 23(1):287–97.
  • Jawad LM, Sulong G. A survey on emerging challenges in selective color image encryption techniques. Indian Journal of Science and Technology. 2015; 8(27).
  • Liu C, Wang G, Lin X. Personre-identification by spatial pyramid color representation and local region matching. IEICE Trans Inf Syst. 2012; E95-D(8):2154–7.
  • Wang J, Liu C. Color image discriminant models and algorithms for face recognition. IEEE Trans Neural Netw. 2008 Dec; 19(12):2088–98.
  • Zhu C, Bichot CE, Chen L. Multi-scale color local binary patterns for visual object classes recognition. Proc IEEE ICPR; 2010. p. 3065–8.
  • Liu Z, Liu C. Fusion of color, local spatial and global frequency information for face recognition. Pattern Recognit. 2010 Aug; 43(8):2882–90.
  • Binu D, Malathi P. Multi model based biometric image retrieval for enhancing security. Indian Journal of Science and Technology. 2016; 8(35).
  • Varior RR, Wang G, Lu J, Liu T. Learning invariant color features for person re-identification. IEEE Transactions on Image Processing. 2016; 25(7):3395–410.
  • Vezzani R, Cucchiara R. Benchmarking for person re-identification. Person Re-Identification. London: Springer; 2014. p. 333–49.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.