This paper proposes a vehicle logo recognition (VLR) system centered on front-view cars, which has been largely neglected by vision community in comparison to other object recognition tasks. The study focuses on local features that describe structural characteristics by locating the logo of a car using a coarse-to-fine (CTF) strategy that first detects the bounding box of a car then the grille and at last, the logo. The detected logo is then used to recognize the make of a car in a reduced time. Our system starts to progress in detecting the bounding box of a car by means of a vocabulary voting and scale-adaptive mean-shift searching strategy. The system continues to process in locating the bounding box of an air-intake grille using a scale-adaptive sliding window searching technique. In the next level, the bounding box of a logo is located by means of cascaded classifiers and circular region detection techniques. The classification of vehicle logos is carried out on the patch-level as occurrences of similar visual words from a visual vocabulary, instead of representing the patchbased descriptors as bag-of-features and classifying them using a standard classifier. The proposed system was tested on 25 distinctive elliptical shapes of vehicle logos with 10 images per class. The system offers the advantage of accurate logo recognition of 86.3% in the presence of significant background clutter. The proposed scheme could be independently used for part recognition of grille detection and logo detection.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
W. Li and L. Li, “A novel approach for vehicle-logo location based on edge detection and morphological filter,” in Proc. 2nd IEEE Int. Symp. on Electronic Commerce and Security (Nanchang, 2009), pp. 343–345.
Y. Li and S. Li, “A vehicle-logo location approach based on edge detection and projection,” in Proc. IEEE Int. Conf. on Vehicular Electronics and Safety (Beijing, 2011), pp. 165–168.
S. Mao, M. Ye, X. Li, F. Pang, and J. Zhou, “Rapid vehicle logo region detection based on information theory,” Comput. Electr. Eng. 39 (3), 863–872 (2013).
Y. Wang, Z. Liu, and F. Xiao, “A fast coarse-to-fine vehicle logo detection and recognition method,” in Proc. IEEE Int. Conf. on Robotics and Biomimetics (Sanya, 2007), pp. 691–696.
A. Psyllos, C. Anagnostopoulos, and E. Kayafas, “Vehicle logo recognition using a SIFT-based enhanced matching scheme,” IEEE Trans. Intellig. Transport. Syst. 11 (2), 322–328 (2010).
D. Comaniciu and P. Meer, “Mean shift: a robust approach toward feature space analysis,” IEEE Trans. Pattern Anal. Mach. Intellig. 24, 603–619 (2002).
N. Dalal and M. Triggs, “Histograms of oriented gradients for human detection,” in Proc. Computer Vision and Pattern Recognition (CVPR) (San Diego, 2005), pp. 886–893.
T. Joachims, B. Scholkopf, C. Burges, and A. Smola, Making Large-Scale SVM Learning Practical (MIT Press, Cambridge, MA, 1999).
P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Proc. Conf. on Computer Vision and Pattern Recognition (CVPR) (Kauai, HI, 2001), pp. 511–518.
J. T. Atherton and D. J. Kerbyson, “Size invariant circle detection,” Image Vision Comput. 79, 795–803 (1999).
C. Csurka, R. Dance, L. Fan, J. Willamowski, and C. Bray, “Visual categorization with bags of keypoints,” in Proc. Workshop on Statistical Learning in Computer Vision (ECCV) (Prague, 2004), pp. 1–22.
A. Ramanan and M. Niranjan, “A review of codebook models in patch-based visual object recognition,” J. Signal Processing Syst. 68 (3), 333–352 (2012).
H. Pan and B. Zhang, “An integrative approach to accurate vehicle logo detection,” Comput. Vision Image Understand. 2013, 12 (2013).
J. Hsieh, L. Chen, D. Chen, and S. Cheng, “Vehicle make and model recognition using symmetrical SURF,” in Proc. 10th IEEE Int. Conf. on Advanced Video and Signal-Based Surveillance (AVSS) (Krakow, 2013), pp. 472–477.
H. Bay, A. Ess, T. Tuytelaars, and V. L. Gool, “SURF: speeded up robust features,” Comput. Vision Image Understand. 10 (3), 346–359 (2008).
K. Zhou, M. Varadarajan, M. Vincze, and F. Liu, “Hybridization of appearance and symmetry for vehicle- logo localization,” in Proc. 15th Int. IEEE Conf. in Intelligent Transportation Systems (ITSC) (Anchorage, 2012), pp. 1396–1401.
Y. Ou, H. Zheng, S. Chen, and J. A. Chen, “Vehicle logo recognition based on a weighted spatial pyramid framework,” in Proc. 17th IEEE Int. Conf. on Intelligent Transportation Systems (ITSC) (Qingdao, 2014), pp. 1238–1244.
D. Lowe, “Distinctive image features from scaleinvariant keypoints,” Int. J. Comput. Vision 60, 91–110 (2004).
S. Yu, S. Zheng, H. Yang, and L. Liang, “Vehicle logo recognition based on bag-of-words,” in Proc. 10th IEEE Int. Conf. on Advanced Video and Signal-Based Surveillance (Krakow, 2013), pp. 353–358.
D. Llorca, R. Arroyo, and M. Sotelo, “Vehicle logo recognition in traffic images using HOG features and SVM,” in Proc. 16th Int. IEEE Annu. Conf. on Intelligent Transportation Systems (ITSC) (Hague, 2013), pp. 2229–2234.
Y. Huang, R. Wu, Y. Sun, W. Wang, and X. Ding, “Vehicle logo recognition system based on convolutional neural networks with a pretraining strategy,” IEEE Trans. Intellig. Transport. Syst. 16 (4), 1951–1960 (2015).
S. Sotheeswaran and A. Ramanan, “Front-view car detection using vocabulary voting and mean-shift search,” in Proc. 15th IEEE Int. Conf. on Advances in ICT for Emerging Regions (ICTer’15) (Colombo, 2015), pp. 16–20.
N. Dalal, “Finding People in images and videos,” Thesis (Grenoble, 2006).
S. Sotheeswaran and A. Ramanan, “A classifier-free codebook-based image classification of vehicle logos,” in Proc. 9th IEEE Int. Conf. on Industrial and Information Systems (ICIIS’14) (Gwalior, 2014), pp. 87–91.
M. Everingham, L. Van-Gool, C. Williams, J. Winn, and A. Zisserman, “The PASCAL visual object classes challenge: a retrospective,” Int. J. Comput. Vision 111 (1), 98–136 (2015).
The article is published in the original.
Sittampalam Sotheeswaran is a Senior Lecturer at the Department of Mathematics at Eastern University, Sri Lanka. He received his B.Sc. Honours in Computer Science (2008) and MPhil in Computer Science (2016) from the University of Jaffna, Sri Lanka. His research interests are in the field of Image Processing and Machine Learning.
Amirthalingam Ramanan is a Senior Lecturer at the Department of Computer Science at University of Jaffna, Sri Lanka. He received his B.Sc. Honours in Computer Science (2002) from the University of Jaffna, Sri Lanka and his PhD in Computer Science (2010) from the University of Southampton, United Kingdom. His research interests are in the algorithmic and applied aspects of Machine Learning and Computer Vision.
About this article
Cite this article
Sotheeswaran, S., Ramanan, A. A Coarse-to-Fine Strategy for Vehicle Logo Recognition from Frontal-View Car Images. Pattern Recognit. Image Anal. 28, 142–154 (2018). https://doi.org/10.1134/S1054661818010170
- car detection
- coarse-to-fine strategy
- logo classification
- vehicle logo recognition