Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 14, pp 20217–20237 | Cite as

A novel fusion mixture of active experts algorithm for traffic signs recognition

  • Amir Ahangi
  • Arash Fassihozzaman Langroudi
  • Fatemeh Yazdanpanah
  • Seyed Abolghasem MirroshandelEmail author
Article
  • 94 Downloads

Abstract

Traffic sign recognition is an important problem in today’s applications. In this paper, by combining ensemble and active learning methods, a novel fusion mixture of active experts algorithm is proposed for this problem. The active learning algorithm is a popular method for reducing the number of samples. The primary goal of active learning is diminishing complexity, increasing the convergence rate, speeding up training process, and decreasing the cost of samples labeling. The active learning, hence, chooses informative samples to train. In addition, ensemble methods are a combination of simple classifiers for improving accuracy. Each classifier tries to learn a region of dataset better than other regions that all opinions are considered on ensemble methods as an ultimate decision. The mixture of experts is one of the most modern hybrid methods in which the training process takes a relatively long time, and it is a problem for large datasets. Our proposed Mixture of Active Experts tries to solve this problem. It decreases the training time process and increases the speed of convergence for finding optimal weights by selecting only informative samples in active learning phase. It is also applicable for online situations, in which the model should be trained continuously. The results of different experiments on German Traffic Sign Recognition Benchmark dataset demonstrate that the proposed method shows 96.69% accuracy and achieved the 6th rank among all the state of the art algorithms using smaller number (only 60%) of training samples.

Keywords

Traffic sign recognition Feature descriptor Mixture of experts Active learning Neural networks 

Notes

Acknowledgments

The authors thank Sara Monji-Azad for her valuable scientific advises and Seethu Mariyam Christopher for proofreading.

References

  1. 1.
    Arnaiz-González A, Díez-Pastor JF, Rodríguez JJ, García-Osorio CI (2016) Instance selection for regression by discretization. Expert Syst Appl 54:340–350CrossRefGoogle Scholar
  2. 2.
    Cai Z-x, Gu M-q (2013) Traffic sign recognition algorithm based on shape signature and dual-tree complex wavelet transform. J Cent South Univ 20(2):433–439CrossRefGoogle Scholar
  3. 3.
    Cireşan D, Meier U, Masci J, Schmidhuber J (2011) Multi-column deep neural network for traffic sign classification. Neural Netw 32(Supplement C):333–338. Selected Papers from IJCNNGoogle Scholar
  4. 4.
    Cohn D, Atlas L, Ladner R (1994) Improving generalization with active learning. Mach Learn 15:201–221Google Scholar
  5. 5.
    De la Escalera A, Armingol JM, Mata M (2003) Traffic sign recognition and analysis for intelligent vehicles. Image Vis Comput 21(3):247–258CrossRefGoogle Scholar
  6. 6.
    De Vries J et al (2006) Object recognition: a shape-based approach using artificial neural networks. Department of Computer Science, University of UtrechtGoogle Scholar
  7. 7.
    Dilip Singh Solanki, D (2015) Traffic sign detection using feature based method. Int J Adv Res Comput Sci Softw Eng 5(2):7Google Scholar
  8. 8.
    Ebrahimpour R, Nikoo H, Masoudnia S, Yousefi MR, Ghaemi MS (2011) Mixture of mlp-experts for trend forecasting of time series: A case study of the tehran stock exchange, vol 27. Special Section 1: Forecasting with Artificial Neural Networks and Computational Intelligence Special Section 2: Tourism ForecastingGoogle Scholar
  9. 9.
    Fleyeh H, Davami, E (2011) Eigen-based traffic sign recognition. IET Intell Transp Syst 5:190–196CrossRefGoogle Scholar
  10. 10.
    Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F (2012) A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. Trans Sys Man Cyber Part C 42:463–484CrossRefGoogle Scholar
  11. 11.
    Gopalakrishnan S et al (2012) A public health perspective of road traffic accidents. J Fam Med Prim Care 1(2):144MathSciNetCrossRefGoogle Scholar
  12. 12.
    Gomes HM, Barddal JP, Enembreck F, Bifet A (2017) A survey on ensemble learning for data stream classification. ACM Comput Surv (CSUR) 50(2):23CrossRefGoogle Scholar
  13. 13.
    Gecer B, Azzopardi G, Petkov N (2017) Color-blob-based cosfire filters for object recognition. Image Vis Comput 57:165–174CrossRefGoogle Scholar
  14. 14.
    Haloi M (2015) Traffic sign classification using deep inception based convolutional networks. arXiv:1511.02992
  15. 15.
    Huang Z, Yu Y, Gu J (2014) A novel method for traffic sign recognition based on extreme learning machine. In: Proceeding of the 11th world congress on intelligent control and automation, pp 1451–1456Google Scholar
  16. 16.
    Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive mixtures of local experts. Neural Comput 3(1):79–87CrossRefGoogle Scholar
  17. 17.
    Kittler J, Hatef M, Duin RPW, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20:226–239CrossRefGoogle Scholar
  18. 18.
    Kuncheva L (2014) Combining pattern classifiers. HobokenGoogle Scholar
  19. 19.
    Liang R-Z, Shi L, Wang H, Meng J, Wang JJ-Y, Sun Q, Gu Y (2016) Optimizing top precision performance measure of content-based image retrieval by learning similarity function. In: 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp 2954–2958Google Scholar
  20. 20.
    Maldonado Bascón S, Acevedo J, Rodríguez S, Lafuente Arroyo A, Caballero F, López-ferreras F (2010) An optimization on pictogram identification for the road-sign recognition task using svms. Comput Vis Image Underst 114:373–383CrossRefGoogle Scholar
  21. 21.
    Masoudnia S, Ebrahimpour R (2014) Mixture of experts: a literature survey. Artif Intell Rev 42:275–293CrossRefGoogle Scholar
  22. 22.
    Marques O (2011) Practical image and video processing using MATLAB. Wiley, New YorkCrossRefGoogle Scholar
  23. 23.
    Mirroshandel SA, Nasr A (2011) Active learning for dependency parsing using partially annotated sentences. In: Proceedings of the 12th international conference on parsing technologies. Association for Computational Linguistics, pp 140–149Google Scholar
  24. 24.
    Meuter M, Müller-Schneiders S, Nunny C, Holdy S, Goermery S, Kummerty A (2010) Decision fusion and reasoning for traffic sign recognition. In: 13th international IEEE conference on intelligent transportation systems, pp 324–329Google Scholar
  25. 25.
    Polikar R (2006) Ensemble based systems in decision making. IEEE Circ Syst Mag 6(3):21–45CrossRefGoogle Scholar
  26. 26.
    Polikar R (2012) Ensemble learning. Springer, Boston, pp 1–34CrossRefGoogle Scholar
  27. 27.
    Ru H, Guo X, Xin Y, Wang Zhong J, Lu P (2011) Traffic signs recognition based on visual attention mechanism. J China Univ Posts Telecommun 18:12–16CrossRefGoogle Scholar
  28. 28.
    Settles B (2010) Active learning literature survey, p 07Google Scholar
  29. 29.
    Settles B (2012) Active learning. Synth Lect Artif Intell Mach Learn 6(1):1–114MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    Sermanet P, Lecun Y (2011) Traffic sign recognition with multi-scale convolutional networks, p 09Google Scholar
  31. 31.
    Shopa P, Sumitha N, Patra PSK (2014) Traffic sign detection and recognition using opencv. In: International conference on information communication and embedded systems (ICICES2014), pp 1–6Google Scholar
  32. 32.
    Souani C, Faiedh H, Besbes, K (2014) Efficient algorithm for automatic road sign recognition and its hardware implementation. J Real-Time Image Process 9:79–93CrossRefGoogle Scholar
  33. 33.
    Stallkamp J, Schlipsing M, Salmen J, Igel C (2011) The german traffic sign recognition benchmark: A multi-class classification competition. In: The 2011 international joint conference on neural networks, pp 1453–1460Google Scholar
  34. 34.
    Stallkamp J, Schlipsing M, Salmen J, Igel C (2011) Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Netw 32 (Supplement C):323–332. Selected Papers from IJCNNGoogle Scholar
  35. 35.
    Staravoitau A (2018) Traffic sign classification with a convolutional network. Pattern Recogn Image Analx 28:155–162CrossRefGoogle Scholar
  36. 36.
    Sun Z-L, Wang H, Lau W-S, Seet G, Wang D (2014) Application of bw-elm model on traffic sign recognition. Neurocomput 128:153–159CrossRefGoogle Scholar
  37. 37.
    Tang B, Heywood MI, Shepherd M (2002) Input partitioning to mixture of experts. In: 2002. IJCNN’02. Proceedings of the 2002 international joint conference on neural networks, vol 1. IEEE, pp 227–232Google Scholar
  38. 38.
    Varior RR, Wang G, Lu, J (2014) Learning invariant color features for person re-identification. arXiv:1410.1035
  39. 39.
    Vinay A, Gagana B, Shekhar VS, Anil B, Murthy KB, Natarajan, S (2016) A double filtered gist descriptor for face recognition. Procedia Comput Sci 79:533–542CrossRefGoogle Scholar
  40. 40.
    Wei X, Phung SL, Bouzerdoum, A (2016) Visual descriptors for scene categorization: experimental evaluation. Artif Intell Rev 45(3):333–368CrossRefGoogle Scholar
  41. 41.
    Woniak M, Graña M, Corchado E (2014) A survey of multiple classifier systems as hybrid systems. Inf Fusion 16:3–17CrossRefGoogle Scholar
  42. 42.
    Yin S, Ouyang P, Liu L, Wei S (2014) A fast and robust traffic sign recognition method using ring of ribp histograms based feature. In: 2014 IEEE international conference on robotics and biomimetics (ROBIO 2014), pp 2570–2575Google Scholar
  43. 43.
    Yuan X, Hao X, Chen H, Wei X (2014) Robust traffic sign recognition based on color global and local oriented edge magnitude patterns. IEEE Trans Intell Transp Syst 15:1466–1477CrossRefGoogle Scholar
  44. 44.
    Yuksel SE, Wilson JN, Gader PD (2012) Twenty years of mixture of experts. IEEE Trans Neural Netw Learn Syst 23(8):1177–1193CrossRefGoogle Scholar
  45. 45.
    Zaklouta F, Stanciulescu B, Hamdoun O (2011) Traffic sign classification using kd trees and random forests. In: The 2011 international joint conference on neural networks (IJCNN). IEEE, pp 2151–2155Google Scholar
  46. 46.
    Zaklouta F, Stanciulescu B (2014) Real-time traffic sign recognition in three stages. Robot Auton Syst 62:16–24CrossRefGoogle Scholar
  47. 47.
    Zhou L, Deng Z (2014) Lidar and vision-based real-time traffic sign detection and recognition algorithm for intelligent vehicle. In: 17th international IEEE conference on intelligent transportation systems (ITSC), pp 578–583Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Amir Ahangi
    • 1
  • Arash Fassihozzaman Langroudi
    • 1
  • Fatemeh Yazdanpanah
    • 1
  • Seyed Abolghasem Mirroshandel
    • 1
    Email author
  1. 1.Department of Computer EngineeringUniversity of GuilanRashtIran

Personalised recommendations