Abstract
In the field of deep learning and image recognition, to improve the accuracy of recognition, the neural model with a complex structure is usually selected as the training model. However, the model with a complex structure has the disadvantages of a large amount of calculation and time-consuming, which limits the ability of deep CNN to deploy on resource-limited devices like mobile phones. This paper presented a new logo recognition approach that is based on knowledge distillation, improving the recognition accuracy of a small model by knowledge transfer. At the same time, a bias neural network is introduced to increase the recognition accuracy of the target class. In this paper, we select ResNet-50 as the cumbersome network, ResNet-18 and VGG16 as small networks respectively. With only knowledge distillation, the average recognition accuracy of ResNet-18 and VGG16 have increased by 8% and 11% respectively. With the proposed bias neural network, the recognition accuracy of ResNet-18 and VGG16 further increased by 2%–10%. The recognition accuracy of the target class is within 5% of that of ResNet-50, which means the bias neural network with fewer layers and parameters is able to reach nearly the same recognition performance as the cumbersome network on target logo classes. And the experiments validate that the bias neural network can improve the accuracy of bias classes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lipikorn, R., Cooharojananone, N., Kijsupapaisan, S., et al.: Vehicle logo recognition based on interior structure using SIFT descriptor and neural network. In: International Conference on Information Science, Electronics and Electrical Engineering, pp. 1595–1599. IEEE (2014)
Da, P., Ping, S.: A method of TV logo recognition based on SIFT. In: 3rd International Conference on Multimedia Technology (ICMT-13), pp. 1571–1579. Atlantis Press (2013)
Llorca, D.F., Arroyo, R., Sotelo, M.A.: Vehicle logo recognition in traffic images using HOG features and SVM. In: International Conference on Intelligent Transportation Systems, pp. 2229–2234. IEEE (2014)
Lu, F., Liu, Y., Zhang, R.: An improved HOG-based vehicle logo location and recognition method. Study Opt. Commun. 5, 26–29 (2012)
Biswas, C., Mukherjee, J.: Logo recognition technique using sift descriptor, Surf descriptor and Hog descriptor. Int. J. Comput. Appl. 117(22), 34–37 (2014)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. Comput. Sci. 14(7), 38–39 (2015)
Bianco, S., Buzzelli, M., Mazzini, D., et al.: Deep learning for logo recognition. Neurocomputing 245, 23–30 (2017)
Shu-Kuo, S., Zen, C.: Robust logo recognition for mobile phone applications. J. Inf. Sci. Eng. 27(2), 545–559 (2014)
Hichem, S., Lamberto, B., Giuseppe, S., Alberto, D.: Context-dependent logo matching and recognition. IEEE Trans. Image Process. 22(3), 1018–1031 (2013)
Wang, Y., Yang, W., Zhang, H.: Deep learning single logo recognition with data enhancement by shape context. In: The 2018 International Joint Conference on Neural Networks (IJCNN). IEEE (2018)
FlickrLogos-32: http://www.multimedia-computing.de/flickrlogos/. Accessed 22 July 2018
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)
Liu, X., Zhang, B.: Automatic collecting representative logo images from the internet. Tsinghua Sci. Technol. 18(6), 606–617 (2013)
Leonid, K., Joseph, S., Yochay, T., Asaf, T.: Fine-grained recognition of thousands of object categories with single-example training. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 965–974. IEEE (2017)
Ning, X., Zhu, W., Chen, S.: Recognition, object detection and segmentation of white background photos based on deep learning. In: 32nd Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 182–187. IEEE (2017)
Chen, R., Matthew, H., Lyudmila, M., Xiao, J., Liu, W.: Vehicle logo recognition by spatial-SIFT combined with logistic regression. In: 19th International Conference on Information Fusion (FUSION), pp. 1228–1235. IEEE (2016)
Rajalida, L., Nagul, C., Suppassara, K., Tavinee, I.: Vehicle logo recognition based on interior structure using SIFT descriptor and neural network. In: 2014 International Conference on Information Science, Electronics and Electrical Engineering, pp. 1595–1599. IEEE (2014)
Apostolos, P., Christos-Nikolaos, A., Eleftherios, K.M.: A new method for Vehicle Logo Recognition. In: 2012 International Conference on Vehicular Electronics and Safety (ICVES 2012), pp. 261–266. IEEE (2012)
Apostolos, P., Psyllos, C.N., Anagnostopoulos, E.K.: Vehicle logo recognition using a SIFT-based enhanced matching scheme. IEEE Trans. Intell. Transp. Syst. 11(2), 322–328 (2010)
Xia, L., Qi, F., Zhou, Q.: A learning-based logo recognition algorithm using SIFT and efficient correspondence matching. In: 2008 International Conference on Information and Automation, pp. 1767–1772. IEEE (2008)
Sonawane, D.R., Apte, S.D.: Improved Context Dependent logo matching framework using FREAK method. In: 2016 IEEE International Conference on Advances in Electronics, Communication and Computer Technology (ICAECCT), pp. 362–366. IEEE (2016)
Tang, S., Zhang, Y.D., Chen, H.: Scalable logo recognition based on compact sparse dictionary for mobile devices. In: 17th International Workshop on Multimedia Signal Processing (MMSP), pp. 1–6. IEEE (2015)
Leonardo, B., Guillermo, C.C., Pedro, S.: Real-time single-shot brand logo recognition. In: 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 134–140. IEEE (2017)
Afsoon, A.S., Alireza, D., Hasan, F., Mehran, Y.: Persian logo recognition using local binary patterns. In: 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA), pp. 258–261. IEEE (2017)
Matheel, E., Abdulmunim, H.K.: Logo matching in Arabic documents using region based features and SURF descriptor. In: 2017 Annual Conference on New Trends in Information & Communications Technology Applications (NTICT), pp. 75–79. IEEE (2017)
Bucilua, C., Caruana, R., Niculescu-Mizil, A.: Model compression. In: Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD 2006, pp. 535–541. ACM, New York (2006)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778. IEEE (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Acknowledgement
The work was supported in part by the National High-tech R&D Program of China (863Program) (2015AA017201) and National Key Research and Development Program of China (2016QY01W0200). The authors are very grateful to the anonymous viewers of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, Y., Wu, Z., Huang, Y. (2018). A Bias Neural Network Based on Knowledge Distillation. In: Qiao, J., et al. Bio-inspired Computing: Theories and Applications. BIC-TA 2018. Communications in Computer and Information Science, vol 952. Springer, Singapore. https://doi.org/10.1007/978-981-13-2829-9_34
Download citation
DOI: https://doi.org/10.1007/978-981-13-2829-9_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2828-2
Online ISBN: 978-981-13-2829-9
eBook Packages: Computer ScienceComputer Science (R0)