Yu Bao
ABSTRACT
Logo detection has been extensively studied because of its applications in many fields. Most existing studies for logo detection are based on hand-designed local features which have certain limitations. Recently, Convolutional Neural Networks (CNN), especially the series of region-based CNN (R-CNN) have achieved great success in general object detection due to its power of feature learning and representation. There are also few work on logo detection based on R-CNN, showing its superiority. However, logo detection presents its own challenges compared to general object detection. In this paper, we aim to experimentally investigate the appropriate architecture and settings of R-CNN for logo detection, by comparing several popular frameworks of R-CNN and considering the characteristics of logo objects in images. We expect our results will be helpful for designing a state-of-the-art logo detection system using handy machine learning techniques.
- S. Bianco, M. Buzzelli, D. Mazzini, and R. Schettini. Logo recognition using cnn features. In ICIAP. 2015.Google Scholar
- W.-T. Chu and T.-C. Lin. Logo recognition and localization in real-world images by using visual patterns. In ICASSP, 2012.Google ScholarCross Ref
- D. Erhan, C. Szegedy, A. Toshev, and D. Anguelov. Scalable object detection using deep neural networks. In CVPR, 2014. Google ScholarDigital Library
- M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. IJCV, 2010. Google ScholarDigital Library
- R. Girshick. Fast r-cnn. In ICCV, 2015. Google ScholarDigital Library
- R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR, 2014. Google ScholarDigital Library
- S. C. Hoi, X. Wu, H. Liu, Y. Wu, H. Wang, H. Xue, and Q. Wu. Logo-net: Large-scale deep logo detection and brand recognition with deep region-based convolutional networks. arXiv preprint arXiv:1511.02462, 2015.Google Scholar
- F. N. Iandola, A. Shen, P. Gao, and K. Keutzer. Deeplogo: Hitting logo recognition with the deep neural network hammer. arXiv preprint arXiv:1510.02131, 2015.Google Scholar
- Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. In ACM MM, 2014. Google ScholarDigital Library
- Y. Kalantidis, L. G. Pueyo, M. Trevisiol, R. van Zwol, and Y. Avrithis. Scalable triangulation-based logo recognition. In ICMR, 2011. Google ScholarDigital Library
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, 2012. Google ScholarDigital Library
- A. P. Psyllos, C.-N. E. Anagnostopoulos, and E. Kayafas. Vehicle logo recognition using a sift-based enhanced matching scheme. IEEE Trans Intell Transp Syst, 2010. Google ScholarDigital Library
- S. Ren, K. He, R. Girshick, and J. Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS, 2015. Google ScholarDigital Library
- J. Revaud, M. Douze, and C. Schmid. Correlation-based burstiness for logo retrieval. In ACM MM, 2012. Google ScholarDigital Library
- S. Romberg, L. G. Pueyo, R. Lienhart, and R. Van Zwol. Scalable logo recognition in real-world images. In ICMR, 2011. Google ScholarDigital Library
- J. R. Uijlings, K. E. van de Sande, T. Gevers, and A. W. Smeulders. Selective search for object recognition. IJCV, 2013. Google ScholarDigital Library
- M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional networks. In ECCV. 2014.Google Scholar
Recommendations
Deep Learning for Logo Detection: A Survey
Logo detection has gradually become a research hotspot in the field of computer vision and multimedia for its various applications, such as social media monitoring, intelligent transportation, and video advertising recommendation. Recent advances in this ...
Logo detection using weakly supervised saliency map
AbstractBox level annotation of a large number of logo images for training purpose of typical deep learning architecture is highly challenging. Thus, a method that can detect the logo with the help of training to remove box-level annotations can be ...
Patch-CNN: Deep learning for logo detection and brand recognition
Automatic logo detection and recognition is significantly growing due to the increasing requirements of intelligent documents analysis and retrieval. The main problem to logo detection is intra-class variation, which is generated by the variation in image ...
Comments