Multimedia Tools and Applications

, Volume 76, Issue 8, pp 10939–10958 | Cite as

A car-face region-based image retrieval method with attention of SIFT features

  • Changyou Zhang
  • Xiaoya Wang
  • Jun Feng
  • Yu Cheng
  • Cheng Guo


A traffic still image captured by the high-definition camera located in traffic block port often contains several vehicles. It provides an important clue to solve vehicle crime cases to retrieve all these images that contain the given type of car. To enhance the performance of image retrieval, we proposed a car-face region-based image retrieval method with the attention of SIFT features. In our method, the first step is to find all the car-face regions from an original traffic image, and this original image is represented as a set of car-face regions. Secondly, a similarity measure metrics is proposed with a light intense training of the attention value of SIFT key points on a very small identified images set. Finally, according to the similarity between the input region and the target region, all the images with at least one similar region are retrieved. We carry out this method on a training set of 100 positive car-face region-images. Compared with the famous training-based SVM method, our method achieved higher precision at the same recall with lower training intensity.


Car-face image Region-based retrieval Attention SIFT features Similarity 



This paper is supported by the Natural Science Foundation of China (61379048), Hebei Province Natural Science Foundation (F2013210109). Special Project of National CAS Union – “The High Performance Cloud Service Platform for Enterprise Creative Computing”, Special Project of National CAS Union – “Car Image Retrieval on Many-core platforms”, Project of “Research and development of data mining technology in the operation of the wind turbine”. The authors also would like to express appreciation to the anonymous reviewers for their helpful comments on improving the paper.


  1. 1.
    Bagarinao E, Kurita T, Higashikubo M (2010) Adapting SVM image classifiers to changes in imaging conditions using incremental SVM: an application to car detection. Lect Notes Comput Sci 5996:363–372CrossRefGoogle Scholar
  2. 2.
    Budiharto W (2014) Robust vision-based detection and grasping object for manipulator using SIFT keypoint detector. In: Proceedings of IEEE 2014 International Conference on Advanced Mechatronic Systems (ICAMechS), pp 448–452Google Scholar
  3. 3.
    Chen Z, Pears NE, Freeman M, Austin J (2009) Road vehicle classification using support vector machines. In: IEEE International Conference on Intelligent Computing and Intelligent Systems, pp 214–218Google Scholar
  4. 4.
    Feng SH, Xu D, Yang X, Wu AM (2005) A novel region-based image retrieval algorithm using selective visual attention model. In: Proceedings of the ACIVS 2005, LNCS 3708, pp 235–242Google Scholar
  5. 5.
    Ferencz A, Learned-Miller EG, Malik J (2005) Building a classification cascade for visual identification from one example. In: Proceedings of IEEE International Conference on Computer Vision (ICCV 05), Wash, DC, pp 286–293Google Scholar
  6. 6.
    Gao HL, Dou LH, Chen WJ, Sun J (2013) Image classification with Bag-of-Words model based on Improved SIFT Algorithm. 2013 9th Asian Control Conference, ASCC 2013, Istanbul, Turkey, pp 1–6Google Scholar
  7. 7.
    Gevers T, Smeulders A (1997) PicToSeek: a content based image search engine for the WWW. In: Proceedings of international conference on visual information systems, pp 93–100Google Scholar
  8. 8.
    Hinton GE, Teh Y, Osindero S (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    Hua LQ, Xu W, Wang T, Ma RF, Xu B (2013) Vehicle recognition using improved SIFT and multi-view model. J Xi’an Jiaotong Univ 47(4):92–99Google Scholar
  10. 10.
    Huang W, Gao Y, Chan KL (2010) A review of region-based image retrieval. Sign Process Syst 59(59):143–161CrossRefGoogle Scholar
  11. 11.
    Huang KQ, Ren WQ, Tan TN (2014) A review on image object classification and detection. Chin J Comput 37(6):1225–1240Google Scholar
  12. 12.
    Inoue M (2004) On the need for annotation-based image retrieval. In: Proceedings of the ACM-SIGIR Workshop on Information Retrieval in Context, Sheffield, UK, pp 44–46Google Scholar
  13. 13.
    Itti L, Koch C (2001) Computational modelling of visual attention. Nat Rev Neurosci 2(3):194–203CrossRefGoogle Scholar
  14. 14.
    Itti L, Koch C, Niebur E (1998) A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell 20(11):1254–1259CrossRefGoogle Scholar
  15. 15.
    Jang DM, Turk M (2011) Car-Rec: a real time car recognition system. In: Proceedings of 2011 I.E. Workshop on Applications of Computer Vision (WACV). Kona, HI, USA, pp 599–605Google Scholar
  16. 16.
    LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324CrossRefGoogle Scholar
  17. 17.
    Liu JW, Liu Y, Luo XL (2014) Research and development on deep learning. Appl Res Comput 31(7):1921–1942Google Scholar
  18. 18.
    Lowe GD (2004) Distinctive image features from scale-invariant key points. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  19. 19.
    Manipoonchelvi P, Muneeswaran K. Significant region-based image retrieval. Signal Image Video Process 9(8): 1795–1804Google Scholar
  20. 20.
    Miao QG, Cao Y, Xia G, Gong MG, Liu JC, Song JF (2015) RBoost: label noise robust boosting algorithm based on a non-convex loss function and the numerically stable base learners. IEEE Trans Neural Netw Learn Syst. doi: 10.1109/TNNLS.2015.2475750 Google Scholar
  21. 21.
    Miao QG, Cheng S, Xu PF, Mei Y, Shi YB (2011) A novel algorithm of image fusion using shearlets. Opt Commun 284(6):1540–1547CrossRefGoogle Scholar
  22. 22.
    Miao QG, Xu PF, Liu TG, Yang Y, Zhang JY, Li WS (2013) Linear feature separation from topographic maps using energy density and shear transform. IEEE Trans Image Process 22(4):1548–1558MathSciNetCrossRefGoogle Scholar
  23. 23.
    Muja M, Lowe DG (2009) Fast approximate nearest neighbors with automatic algorithm configuration. In: Visapp International Conference on Computer Vision Theory & Applications, pp 331–340Google Scholar
  24. 24.
    Niblack C, Barber R, Equitz W, Flickner M, Glasman E, Petkovic D et al (1993) The QBIC project: Querying images by content using color, texture, and shape. In: Proceedings of SPIE, pp 173–187Google Scholar
  25. 25.
    Ogle V, Stonebraker M (1995) Chabot: retrieval from a relational database of images. IEEE Comput 28(9):40–48CrossRefGoogle Scholar
  26. 26.
    Pearce G, Pears, N (2011) Automatic make and model recognition from frontal images of cars. In: Proceedings of 8th IEEE International Conference on Advanced Video and Signal-Based Surveillance, pp 373–378Google Scholar
  27. 27.
    Raveaux R, Burie JC, Ogier JM (2013) Structured representations in a content based image retrieval context. J Vis Commun Image Represent 24(8):1252–1268CrossRefGoogle Scholar
  28. 28.
    Santhanam T, Radhika S (2010) A novel approach to classify noises in images using artificial neural network. J Comput Sci 6(5):506–510CrossRefGoogle Scholar
  29. 29.
    Santos D, Correia PL (2009) Car recognition based on back lights and rear view features. In: Proceedings of 2009 10th Workshop on Image Analysis for Multimedia Interactive Services. London, United Kingdom, pp 137–140Google Scholar
  30. 30.
    Sclaroff S, Taycher L, Cascia M (1997) ImageRover: a content-based image browser for the world wide web. In: Proceedings of IEEE international workshop on contentbased access of image and video libraries, pp 2–9Google Scholar
  31. 31.
    Smeulders A, Worring M, Santini S, Gupta A, Jain R (2000) Content-based image retrieval at the end of the early years. IEEE Trans Pattern Anal Mach Intell 22(12):1349–1380CrossRefGoogle Scholar
  32. 32.
    Sun ZH, Ronald Miller, George Bebis et al (2002) A real-time precrash vehicle detection system. In: Proceedings of Sixth IEEE Workshop on Applications of Computer Vision. Orlando, Florida, pp 171–182Google Scholar
  33. 33.
    Wang Q, Kim L, Boyer (2013) Feature learning by multidimensional scaling and its applications in object recognition. In: Proceedings of 2013 XXVI Conference on Graphics, Patterns and Images, pp 8–15Google Scholar
  34. 34.
    Wang Z, Zhang FS. Shi QR (2013) Topic models for image localization. In: Proceedings of 2013 International Conference on Computer and Robot Vision (CRV), pp 136–143Google Scholar
  35. 35.
    Yu G, Yuan J, Liu Z. Unsupervised random forest indexing for fast action search. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp 865–872Google Scholar
  36. 36.
    Zhang CY, Wang F, Huang K, Liu ZY, Chen YF (2015) UniDegree: a GPU-based Graph Representation for SSSP. In: Proceedings of 15th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2015), Zhangjiajie, ChinaGoogle Scholar
  37. 37.
    Zheng W, Liang L (2009) Fast car detection using image strip features. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2009), pp 2703–2710. doi: 10.1109/CVPR.2009.5206642

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Changyou Zhang
    • 1
    • 2
  • Xiaoya Wang
    • 2
  • Jun Feng
    • 2
  • Yu Cheng
    • 3
  • Cheng Guo
    • 4
  1. 1.Laboratory of Parallel Software and Computational Science, Institute of SoftwareChinese Academy of SciencesBeijingChina
  2. 2.School of Infomatics Science and TechnologyShijiazhuang Tiedao UniversityShijiazhuangChina
  3. 3.Institute of Applied MathematicsHebei Academy of SciencesShijiazhuangChina
  4. 4.Yunnan Electric Power Research InstituteYunnan Power Grid Co., Ltd.KunmingChina

Personalised recommendations