Machine Vision and Applications

, Volume 27, Issue 2, pp 287–301 | Cite as

Logo localization and recognition in natural images using homographic class graphs

  • Raluca Boia
  • Corneliu Florea
  • Laura FloreaEmail author
  • Radu Dogaru
Original Paper


We propose a method for localization and classification of brand logos in natural images. The system has to overcome multiple challenges such as perspective deformations, warping, variations of the shape and colors, occlusions, background variations. To deal with perspective variation, we rely on homography matching between the SIFT keypoints of logo instances of the same class. To address the changes in color, we construct a weighted graph of logo interconnections that is further analyzed to extract potentially multiple instances of the class. The main instance is built by grouping the keypoints of the graph connected logos onto the central image. The secondary instance is needed for color inverted logos and is obtained by inverting the orientation of the main instance. The constructed logo recognition system is tested on two databases (FlickrLogos-32 and BelgaLogos), outperforming state of the art with more than 10 % accuracy.


Logo Localization Recognition Class model  Homography 



This work was supported by the Romanian Sectoral Operational Programme Human Resources Development 2007–2013 through the European Social Fund Financial Agreements POSDRU/159/1.5/S/132395 and POSDRU /159/1.5/S/134398.


  1. 1.
    Bagdanov, A., Ballan, L., Bertini, M., Del Bimbo, A.: Trademark matching and retrieval in sports video databases. In: ACM MIR, pp. 79–86 (2007)Google Scholar
  2. 2.
    Boia, R., Florea, C.: Homographic class template for logo localization and recognition. In: Proc. of IbPRIA (2015)Google Scholar
  3. 3.
    Brown, M., Lowe, D.: Recognising panoramas. In: ICCV, pp. 1218–1225 (2003)Google Scholar
  4. 4.
    Brown, M., Lowe, D.: Automatic panoramic image stitching using invariant features. Int. J. Comput. Vis. 74(1), 59–73 (2007)CrossRefGoogle Scholar
  5. 5.
    Chan, D., Ge, R., Gershony, O., Hesterberg, T., Lambert, D.: Evaluating online ad campaigns in a pipeline: causal models at scale. In: ACM SIGKDD Int. Conf. on Knowledge discovery and data mining, pp. 7–16 (2010)Google Scholar
  6. 6.
    Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR, pp. 886–893 (2005)Google Scholar
  7. 7.
    Dorko, G., Schmid, C.: Object class recognition using discriminative local features. Tech. rep, INRIA (2005)Google Scholar
  8. 8.
    Dubout, C., Fleuret, F.: Exact acceleration of linear object detectors. In: ECCV, pp. 310 – 311 (2012)Google Scholar
  9. 9.
    Dubrofsky, E.: Homography estimation. Master’s thesis, Carleton University (2009)Google Scholar
  10. 10.
    Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vis. 1, 303–338 (2010)CrossRefGoogle Scholar
  11. 11.
    Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, pp. 264–271 (2003)Google Scholar
  12. 12.
    Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with application to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981)CrossRefMathSciNetGoogle Scholar
  13. 13.
    Florea, L., Florea, C., Vranceanu, R., Vertan, C.: Can your eyes tell me how you think? a gaze directed estimation of the mental activity. In: BMVC (2013)Google Scholar
  14. 14.
    Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press (2004)Google Scholar
  15. 15.
    Hauagge, D.C., Snavely, N.: Image matching using local symmetry features. In: CVPR, pp. 206–213 (2012)Google Scholar
  16. 16.
    Jin, Y., Tao, L., Di, H., Rao, N., Xu, G.: Background modeling from a free-moving camera by multi-layer homography algorithm. In: ICIP, pp. 1572–1575 (2008)Google Scholar
  17. 17.
    Joly, A., Buisson, O.: Logo retrieval with a contrario visual query expansion. In: ACM MM, pp. 581–584 (2009)Google Scholar
  18. 18.
    Kleban, J., Xie, X., Ma, W.Y.: Spatial pyramid mining for logo detection in natural scenes. In: IEEE ICME, pp. 1470–1477 (2008)Google Scholar
  19. 19.
    Klein, G., Murray, D.: Parallel tracking and mapping on a camera phone. In: Int. Symp. on mixed and augmented reality, pp. 83–86 (2009)Google Scholar
  20. 20.
    Krapac, J., Perronnin, F., Furon, T., Jegou, H.: Instance classification with prototype selection. In: ACM ICMR, pp. 431–434 (2014)Google Scholar
  21. 21.
    Kumar, S., Hebert, M.: Discriminative fields for modeling spatial dependencies in natural images. In: NIPS, pp. 1531–1538 (2004)Google Scholar
  22. 22.
    Lewis, R., Rao, J., Reiley, D.: Measuring the effects of advertising: the digital frontier. In: Economics of digitization, pp. 1–5 (2014)Google Scholar
  23. 23.
    Li, K., Chen, S., Su, S., Duh, D., Zhang, H., Li, S.: Logo detection with extendibility and discrimination. Multimed. Tools Appl. 72, 1285–1310 (2014)CrossRefGoogle Scholar
  24. 24.
    Lin, Y., Medioni, G.: Map-enhanced uav image sequence registration and synchronization of multiple image sequences. In: CVPR, pp. 1–7 (2007)Google Scholar
  25. 25.
    Lowe, D.: Object recognition from local scale-invariant features. In: ICCV, pp. 1150–1157 (1999)Google Scholar
  26. 26.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 62(2), 91–110 (2004)CrossRefGoogle Scholar
  27. 27.
    Lu, V., Endres, I., Stroila, M., Hart, J.: Accelerating arrays of linear classifiers using approximate range queries. In: IEEE WACV, pp. 255–260 (2014)Google Scholar
  28. 28.
    McLauchlan, P.F., Jaenicke, A.: Image mosaicing using sequential bundle adjustment. Image Vis. Comput., pp. 751–759 (2002)Google Scholar
  29. 29.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.V.: A comparison of affine region detectors. IJCV 62(1–2), 43–72 (2005)Google Scholar
  30. 30.
    Ng, A., Jordan, M.I.: On discriminative vs. generative classifiers: a comparison of logistic regression and naive bayes. In: NIPS, pp. 841–849 (2001)Google Scholar
  31. 31.
    Opelt, A., Fusseneger, M., Pinz, A., Auer, P.: Generic object recognition with boosting. IEEE T PAMI 28(3), 416–431 (2006)CrossRefGoogle Scholar
  32. 32.
    Psyllos, A.P., Anagnostopoulos, C.N.E., Kayafas, E.: Vehicle logo recognition using a sift-based enhanced matching scheme. IEEE Trans. Intell. Transp. Syst. 11(2), 322–328 (2010)CrossRefGoogle Scholar
  33. 33.
    Raguram, R., Frahm, J.M., Pollefeys, M.: A comparative analysis of ransac techniques leading to adaptive real-time random sample consensus. In: Proceedings of the 10th European conference on computer vision: part II, Berlin, Heidelberg, ECCV ’08, pp. 500–513 (2008)Google Scholar
  34. 34.
    Revaud, J., Douze, M., Schmid, C.: Correlation-based burstiness for logo retrieval. In: ACM MM, pp. 965–968 (2012)Google Scholar
  35. 35.
    Ries, C., Richter, F., Romberg, S., Lienhart, R.: Automatic object annotation from weakly labeled data with latent structured svm. In: CBMI, pp. 1–4 (2014)Google Scholar
  36. 36.
    Romberg, S., Lienhart, R.: Bundle min-hashing for logo recognition. In: ACM ICMR (2013)Google Scholar
  37. 37.
    Romberg, S., Garcia Pueyo, L., Lienhart, R., van Zwol, R.: Scalable logo recognition in real-world images. In: ACM ICMR, pp. 965–968 (2011)Google Scholar
  38. 38.
    Schneiderman, H., Kanade, T.: A statistical method for 3d ob-ject detection applied to faces and cars. In: CVPR, pp. 746–751 (2003)Google Scholar
  39. 39.
    Sheikh, Y., Javed, O., Kanade, T.: Background subtraction for freely moving cameras. In: ICCV, pp. 1219–1225 (2009)Google Scholar
  40. 40.
    Simon, G., Fitzgibbon, A., Zisserman, A.: Markerless tracking using planar structures in the scene. In: Augmented reality, pp. 120–128 (2000)Google Scholar
  41. 41.
    Snavely, N., Seitz, S.M., Szeliski, R.: Modeling the world from internet photo collections. Int. J. Comput. Vis. pp. 189–210 (2008)Google Scholar
  42. 42.
    Torii, A., Sivic, J., Pajdla, T., Okutomi, M.: Visual place recognition with repetitive structures. In: CVPR (2013)Google Scholar
  43. 43.
    Torralba, A., Murphy, K., Freeman, W.: Sharing visual fea-tures for multiclass and multiview object detection. In: CVPR, pp. 762–769 (2004)Google Scholar
  44. 44.
    Vedaldi, A., Fulkerson, B.: Vlfeat: an open and portable library of computer vision algorithms. In: ACM MM, pp. 1469–1472 (2010)Google Scholar
  45. 45.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. CVPR 1, 511–518 (2004)Google Scholar
  46. 46.
    Zhu, G., Doermann, D.: Automatic document logo detection. In: ICDAR, pp. 864–868 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Raluca Boia
    • 1
  • Corneliu Florea
    • 1
  • Laura Florea
    • 1
    Email author
  • Radu Dogaru
    • 2
  1. 1.Image Processing and Analysis LaboratoryUniversity Politehnica of BucharestBucharestRomania
  2. 2.Natural Computing LaboratoryUniversity Politehnica of BucharestBucharestRomania

Personalised recommendations