Logo Detection and Recognition Based on Classification

Online product frauds in the booming e-commerce market have become a major concern for market surveillants and commercial companies. The logo detection plays a crucial role in preventing the increasing online counterfeit trading attempts. In this paper, a novel method based on Random Forest classification with multi-type features is presented to detect the logo regions on arbitrary images and the detected logo regions are further recognized using the visual words with spatial correlated information. Extensive experiments have been conducted on realistic and noise images with different logos. The results show that the proposed method is able to detect the logo regions, and the recognition performance outperforms the well-known Viola-Jones approach for recognizing the arbitrary logos on realistic images.

[1]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[2]  Zhengyou Zhang,et al.  Boosting-Based Face Detection and Adaptation , 2010, Synthesis Lectures on Computer Vision.

[3]  Varun Grover,et al.  E-commerce: a brand name’s curse , 2010, Electron. Mark..

[4]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[5]  Zhe Li,et al.  Fast Logo Detection and Recognition in Document Images , 2010, 2010 20th International Conference on Pattern Recognition.

[6]  Hossein Pourghassem,et al.  A Fast Logo Recognition Algorithm in Noisy Document Images , 2011, 2011 International Conference on Intelligent Computation and Bio-Medical Instrumentation.

[7]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[8]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Fatih Murat Porikli,et al.  Pedestrian Detection via Classification on Riemannian Manifolds , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Yu Chen,et al.  A Noise-Tolerant Enhanced Classification Method for Logo Detection and Brand Classification , 2011, FGIT-SecTech.

[11]  William McIlhagga,et al.  The Canny Edge Detector Revisited , 2011, International Journal of Computer Vision.

[12]  Takeshi Mita,et al.  Joint Haar-like features for face detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Olivier Buisson,et al.  Logo retrieval with a contrario visual query expansion , 2009, ACM Multimedia.

[14]  Ehud Rivlin,et al.  Applying algebraic and differential invariants for logo recognition , 1996 .

[15]  Hongye Wang.  Document Logo Detection and Recognition Using Bayesian Model , 2010, 2010 20th International Conference on Pattern Recognition.

[16]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[17]  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).

[18]  Tsuhan Chen,et al.  Efficient Kernels for identifying unbounded-order spatial features , 2009, CVPR.

[19]  Oscar Déniz-Suárez,et al.  A comparison of face and facial feature detectors based on the Viola–Jones general object detection framework , 2011, Machine Vision and Applications.

[20]  Paul A. Viola,et al.  Multiple Instance Boosting for Object Detection , 2005, NIPS.

[21]  John Wang,et al.  Data Mining Software , 2008 .

[22]  Dirk Van den Poel,et al.  FACULTEIT ECONOMIE , 2007 .