Abstract
Shoeprints are frequently acquired at crime scenes and can provide vital clues for investigation. How to retrieve the most similar shoeprints available in the dataset to the highly degraded query crime scene shoeprint is a challenging work. Some existing shoeprint retrieval algorithms cannot work well with highly degraded shoeprint image on a large scale dataset, and the results are not well correlated with the forensic experts. This study proposes a manifold ranking based method using hybrid features of region and appearance to improve the retrieval performance. Manifold ranking method is introduced to narrow the well-known gap between visual features and semantic concepts. We define the ranking cost function from three perspectives: (i) the feature similarity between the query and the dataset images, (ii) the relationship between every two shoeprints in the dataset, (iii) the assigned opinion scores for multiple shoeprints left in one crime scene by the forensic expert. Experiments on the real crime scene datasets show that the cumulative match score of the proposed method is more than 93.5 % on the top 2 % of the dataset composed of 10096 crime scene shoeprints.
Similar content being viewed by others
References
Algarni G, Amiane M (2008) A novel technique for automatic shoeprint image retrieval. Forensic Sci Int 181(1–3):10–14
Bouridane A, Alexander A, Nibouche M, Crookes D (2000) Application of fractals to the detection and classification of shoeprints. International conference on image processing, Vancouver, BC, pp 474–477
Camps-Valls G, Marsheva TVB, Zhou D (2007) Semi-supervised graph-based hyper spectral image classification. IEEE Trans Geosci Remote Sens 45(10):3044–3054. doi:10.1109/TGRS.2007.895416
Cervelli F, Dardi F, Carrato S (2009) An automatic footwear retrieval system for shoe marks from real crime scenes. International symposium on image and signal processing and analysis, Salzburg, pp 668–672
Cervelli F, Dardi F, Carrato S (2009) A texture based shoe retrieval system for shoe marks of real crime scenes. International conference on image analysis and processing, Italy, pp 384–393
Cervelli F, Dardi F, Carrato S (2010) A translational and rotational invariant descriptor for automatic footwear retrieval of real cases shoe marks. European signal processing conference, Aalborg, pp 1665–1669
Chazal PD, Flynn J, Reilly RB (2005) Automated processing of shoeprint images based on the Fourier transform for use in forensic science. IEEE Trans Pattern Anal Mach Intell 27(3):341–350. doi:10.1109/TPAMI.2005.48
Crookes D, Bouridane A, Su H, Gueham M (2007) Following the footsteps of others: techniques for automatic shoeprint classification. Second NASA/ESA conference on, Edinburgh, pp 67–74
Datta R, Joshi D, Li J, Wang JZ (2008) Image retrieval: ideas, influences, and trends of the new age. ACM Comput Surv (CSUR) 40(2):1–60. doi:10.1145/1348246.1348248
Deshmukh MP, Patil PM (2009) Automatic shoeprint matching system for crime scene investigation. Int J Comput Sci Commun Technol 2(1):281–287
Gueham M, Bouridane A, Crookes D (2007) Automatic recognition of partial shoeprints based on phase-only correlation. IEEE International Conference on Image Processing (ICIP), San Antonio, TX, pp 441–444
Gueham M, Bouridane A, Crookes D (2008) Automatic classification of partial shoeprints using advanced correlation filters for use in forensic science. International conference on pattern recognition, Tampa, FL, pp 1–4
He J, Li M, Zhang H, Tong H et al (2004) Manifold-ranking based image retrieval. The ACM international conference on multimedia, New York, USA, pp 9–16
He J, Li M, Zhang H, Tong H et al (2006) Generalized manifold-ranking-based image retrieval. IEEE Trans Image Process 15(10):3170–3177. doi:10.1109/TIP.2006.877491
He R, Zhu Y, Zhan W (2009) Fast manifold-ranking for content-based image retrieval. ISECS international colloquium on computing, communication, control, and management, Sanya, China, pp 299–302
Kortylewski A, Albrecht T, Vetter T (2014) Unsupervised footwear impression analysis and retrieval from crime scene data. ACCV 2014 workshops, Singapore, Singapore, pp 644–658
Li ZW, Wei C, Li Y, Sun T (2011) Research of shoeprint image stream retrieval algorithm with scale-invariance feature transform. international conference on multimedia technology, Hangzhou, pp 5488–5491
Nibouche O, Bouridane A, Crookes D, Gueham M et al (2009) Rotation invariant matching of partial shoeprints. Machine vision and image processing conference, Dublin, pp 94–98
Patil PM, Kulkarni JV (2009) Rotation and intensity invariant shoeprint matching using Gabor transform with application to forensic science. Pattern Recogn 42(7):1308–1317. doi:10.1016/j.patcog.2008.11.008
Pavlou M, Allinson NM (2006) Automatic extraction and classification of footwear patterns. 7th international conference, Burgos, Spain, pp 721–728
Pavlou M, Allinson NM (2009) Automated encoding of footwear patterns for fast indexing. Image Vis Comput 27(4):402–409. doi:10.1016/j.imavis.2008.06.003
Phillips PJ, Moon H, Rizvi SA, Rauss PJ (2000) The FERET evaluation methodology for face-recognition algorithms. IEEE Trans Pattern Anal Mach Intell 22(10):1090–1104. doi:10.1109/34.879790
Qiao H, Zhang P, Wang D, Zhang B (2012) An explicit nonlinear mapping for manifold learning. IEEE Trans Cybern 43(1):51–63. doi:10.1109/TSMCB.2012.2198916
Reddy BS, Chatterji BN (1996) An FFT-based technique for translation, rotation, and scale-invariant image registration. IEEE Trans Image Process 5(8):1266–1271. doi:10.1109/83.506761
Su H, Crookes D, Bouridane A, Gueham M (2007) Local image features for shoeprint image retrieval. British machine vision conference, University of Warwick, UK, pp 1–10
Tang Y, Srihari SN, Kasiviswanathan H, Corso JJ (2011) Footwear print retrieval system for real crime scene marks. International workshop on computational forensics, Tokyo, Japan, pp 88–100
Tang Y, Srihari SN, Kasiviswanathan H (2010) Similarity and clustering of footwear prints. 2010 I.E. international conference on Granular Computing (GrC), San Jose, CA, pp 459–464
Wan X (2007) Content based image retrieval using manifold-ranking of blocks. IEEE international conference on multimedia and expo, Beijing, China, pp 2182–2185
Wang F, Zhang C (2008) Label propagation through linear neighborhoods. IEEE Trans Knowl Data Eng 20(1):55–67. doi:10.1109/TKDE.2007.190672
Wang XN, Sun HH, Yu Q, Zhang C (2015) Automatic shoeprint retrieval algorithm for real crime scenes. ACCV, Singapore, pp 399–413
Wei CH, Hsin C, Gwo CY (2014) Alignment of core point for shoeprint analysis and retrieval. Information Science, International Conference on Electronics and Electrical Engineering (ISEEE), Sapporo, pp 1069–1072
Xu B, Bu J, Chen C, Cai D et al (2011) Efficient manifold ranking for image retrieval. International ACM SIGIR conference on research and development in information retrieval, Beijing, China, pp 525–534
Zhou D, Bousquet O, Lal TN (2003) Learning with local and global consistency. In: Thrun S, Saul LK, Schölkopf B (eds) Advances in neural information processing systems 16. MIT Press, Cambridge, pp 321–328
Zhou D, Weston J, Gretton A, Bousquet O, Scholkopf B (2003) Ranking on data manifolds. In: Thrun S, Saul LK, Schölkopf B (eds) Advances in neural information processing systems 16. MIT Press, Cambridge, pp 169–176
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, X., Zhang, C., Wu, Y. et al. A manifold ranking based method using hybrid features for crime scene shoeprint retrieval. Multimed Tools Appl 76, 21629–21649 (2017). https://doi.org/10.1007/s11042-016-4029-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-4029-3