Pattern RecognitionNo Access

Multi-Feature Broad Learning System for Image Classification

Ran Liu

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

Yaqiong Liu

https://orcid.org/0000-0002-4786-5808

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

Yang Zhao

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

Xi Chen

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

Shanshan Cui

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

Feifei Wang

College of Computer Science, Chongqing University, Chongqing 400044, P. R. China

Search for more papers by this author

, and

Lin Yi

Chongqing University Cancer Hospital, Chongqing 400030, P. R. China

E-mail Address: linyi_cqu@163.com

Corresponding author.

Search for more papers by this author

https://doi.org/10.1142/S0218001421500336Cited by:6 (Source: Crossref)

Abstract

A multi-feature broad learning system (MFBLS) is proposed to improve the image classification performance of broad learning system (BLS) and its variants. The model is characterized by two major characteristics: multi-feature extraction method and parallel structure. Multi-feature extraction method is utilized to improve the feature-learning ability of BLS. The method extracts four features of the input image, namely convolutional feature, K-means feature, HOG feature and color feature. Besides, a parallel architecture that is suitable for multi-feature extraction is proposed for MFBLS. There are four feature blocks and one fusion block in this structure. The extracted features are used directly as the feature nodes in the feature block. In addition, a “stacking with ridge regression” strategy is applied to the fusion block to get the final output of MFBLS. Experimental results show that MFBLS achieves the accuracies of 92.25%, 81.03%, and 54.66% on SVHN, CIFAR-10, and CIFAR-100, respectively, which outperforms BLS and its variants. Besides, it is even superior to the deep network, convolutional deep belief network, in both accuracy and training time on CIFAR-10. Code for the paper is available at https://github.com/threedteam/mfbls.

Keywords:

References

1. V. Bolón-Canedo and B. Remeseiro , Feature selection in image analysis: A survey, J. Vis. Commun. Image Represent. 53(4) (2019) 1–27. Google Scholar
2. C. L. P. Chen and Z. Liu , Broad learning system: An effective and efficient incremental learning system without the need for deep architecture, IEEE Trans. Neural Netw. Learn. Syst. 29(1) (2018) 10–24. Crossref, Web of Science, Google Scholar
3. C. L. P. Chen, Z. Liu and S. Feng , Universal approximation capability of broad learning system and its structural variations, IEEE Trans. Neural Netw. Learn. Syst. 30(4) (2019) 1191–1204. Crossref, Web of Science, Google Scholar
4. S. Cheng and G. Zhou , Facial expression recognition method based on improved vgg convolutional neural network, Int. J. Pattern Recogn. Artif. Intell. 34(7) (2020) art. no. 2056003, https://doi.org/10.1142/S0218001420560030. Link, Web of Science, Google Scholar
5. A. Coates and A. Y. Ng , Learning feature representations with k-means, in Neural Networks: Tricks of the Trade, Lecture Notes in Computer Science, eds. G. Montavon, G. Orr and K.-R. Müller , Vol. 7700. (Springer, Berlin, Heidelberg, 2012), pp. 561–580. Crossref, Google Scholar
6. E. D. Cubuk, B. Zoph, D. Mane, V. Vasudevan and Q. V. Le , Autoaugment: Learning augmentation strategies from data, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, Long Beach, CA, USA, 2019), pp. 113–123. Crossref, Google Scholar
7. N. Dalal and B. Triggs , Histograms of oriented gradients for human detection, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, San Diego, CA, USA, 2005), pp. 886–893. Crossref, Google Scholar
8. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li and L. Fei-Fei , ImageNet: A large-scale hierarchical image database, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, Miami, FL, USA, 2009), pp. 248–255. Crossref, Google Scholar
9. T. Devries and G. W. Taylor, Improved regularization of convolutional neural networks with cutout (2017), https://arxiv.org/abs/1708.04552. Google Scholar
10. I. S. Dhillon and D. S. Modha , Concept decompositions for large sparse text data using clustering, Mach. Learn. 42(1–2) (2001) 143–175. Crossref, Web of Science, Google Scholar
11. R. O. Duda, P. E. Hart and D. G. Stork , Pattern Classification (John Wiley & Sons, 2012). Google Scholar
12. Y. Garg and K. S. Candan , RACKNet: Robust allocation of convolutional kernels in neural networks for image classification, in Proc. 2019 Int. Conf. Multimedia Retrieval (ACM, Ottawa, ON, Canada, 2019), pp. 315–323. Crossref, Google Scholar
13. I. Goodfellow, D. Wardefarley, M. Mirza, A. Courville and Y. Bengio , Maxout networks, in Int. Conf. Machine Learning (IMLS, Atlanta, GA, USA, 2013), pp. 1319–1327. Google Scholar
14. K. He, X. Zhang, S. Ren and J. Sun , Deep residual learning for image recognition, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, Las Vegas, NV, USA, 2016), pp. 770–778. Crossref, Google Scholar
15. G. E. Hinton, S. Osindero and Y.-W. Teh , A fast learning algorithm for deep belief nets, Neural Comput. 18(7) (2006) 1527–1554. Crossref, Web of Science, Google Scholar
16. A. E. Hoerl and R. W. Kennard , Ridge regression: Biased estimation for nonorthogonal problems, Technometrics 42(1) (2000) 80–86. Crossref, Web of Science, Google Scholar
17. B. Igelnik and Y.-H. Pao , Stochastic choice of basis functions in adaptive function approximation and the functional-link net, Neural Netw. 6(6) (1995) 1320–1329. Crossref, Web of Science, Google Scholar
18. J. Jin, Z. Liu and C. P. Chen , Discriminative graph regularized broad learning system for image recognition, Sci. China Inf. Sci. 61(11) (2018) 112209. Crossref, Google Scholar
19. J. Kittler, M. Hatef, R. P. W. Duin and J. Matas , On combining classifiers, IEEE Trans. Pattern Anal. Mach. Intell. 20(3) (1998) 226–239. Crossref, Web of Science, Google Scholar
20. A. Krizhevsky and G. Hinton, Convolutional deep belief networks on CIFAR-10 (2010), https://www.cs.toronto.edu/∼kriz/. Google Scholar
21. A. Krizhevsky and G. Hinton, Learning multiple layers of features from tiny images, technical report, University of Toronto, Toronto, 2009. Google Scholar
22. A. Krizhevsky, I. Sutskever and G. E. Hinton , ImageNet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (ACM, Lake Tahoe, NV, USA, 2012), pp. 1097–1105. Google Scholar
23. Y. LeCun, L. Bottou, Y. Bengio and P. Haffner , Gradient-based learning applied to document recognition, Proc. IEEE 86(11) (1998) 2278–2324. Crossref, Web of Science, Google Scholar
24. Y. LeCun, F. J. Huang and L. Bottou , Learning methods for generic object recognition with invariance to pose and lighting, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, Washington, DC, USA, 2004), pp. 97–104. Crossref, Google Scholar
25. S. Li, W. Song, L. Fang, Y. Chen, P. Ghamisi and J. A. Benediktsson , Deep learning for hyperspectral image classification: An overview, IEEE Trans. Geosci. Remote Sensing 57(9) (2019) 6690–6709. Crossref, Web of Science, Google Scholar
26. S. Liang, Y. Khoo and H. Yang, Drop-activation: Implicit parameter reduction and harmonic regularization (2020), https://arxiv.org/abs/1811.05850. Google Scholar
27. B. Liu, X. Zeng, F. Tian, S. Zhang and L. Zhao , Domain transfer broad learning system for long-term drift compensation in electronic nose systems, IEEE Access 7 (2019) 143947–143959. Crossref, Web of Science, Google Scholar
28. Z. Liu, J. Zhou and C. P. Chen , Broad learning system: Feature extraction based on k-means clustering algorithm, in 2017 4th Int. Conf. Information, Cybernetics and Computational Social Systems (ICCSS) (IEEE, Dalian, China, 2017), pp. 683–687. Crossref, Google Scholar
29. B. S. Manjunath, J.-R. Ohm, V. V. Vasudevan and A. Yamada , Color and texture descriptors, IEEE Trans. Circuits Syst. Video Technol. 11(6) (2001) 703–715. Crossref, Web of Science, Google Scholar
30. Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu and A. Y. Ng, Reading digits in natural images with unsupervised feature learning, in NIPS Workshop on Deep Learning and Unsupervised Feature Learning (Granada, Spain, 2011), pp. 1–9. Google Scholar
31. Y.-H. Pao, G.-H. Park and D. J. Sobajic , Learning and generalization characteristics of the random vector functional-link net, Neurocomputing 6(2) (1994) 163–180. Crossref, Web of Science, Google Scholar
32. Y.-H. Pao and Y. Takefuji , Functional-link net computing: Theory, system architecture, and functionalities, Computer 25(5) (1992) 76–79. Crossref, Web of Science, Google Scholar
33. J. K. Patil and R. Kumar , Color feature extraction of tomato leaf diseases, Int. J. Eng. Trends Technol. 2(2) (2011) 72–74. Google Scholar
34. R. Salakhutdinov and G. Hinton , Deep Boltzmann machines, in Proceedings of the International Conference on Artificial Intelligence and Statistics (PMLR, Clearwater Beach, FA, USA, 2009), pp. 448–455. Google Scholar
35. K. Simonyan and A. Zisserman , Very deep convolutional networks for large-scale image recognition, in Int. Conf. Learning Representations (ICLR, San Diego, CA, USA, 2015), arXiv:1409.1556. Google Scholar
36. K. E. Smith and P. Williams , A shallow learning-reduced data approach for image classification, in Canadian Conf. Artificial Intelligence (Springer, Kingston, ON, CAN, 2019), pp. 345–351. Crossref, Google Scholar
37. C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke and A. Rabinovich , Going deeper with convolutions, in Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, Boston, MA, USA, 2015), pp. 1–9. Crossref, Google Scholar
38. M. Szummer and R. W. Picard , Indoor-outdoor image classification, in Proc. 1998 IEEE Int. Workshop on Content-Based Access of Image and Video Database (IEEE, Bombay, IND, 1998), pp. 42–51. Crossref, Google Scholar
39. M. Tan and Q. V. Le , Efficientnet: Rethinking model scaling for convolutional neural networks, in Int. Conf. Machine Learning (IMLS, Long Beach, CA, USA, 2019), pp. 6105–6114. Google Scholar
40. W. Wang, Y. Yang, X. Wang, W. Wang and J. Li , Development of convolutional neural network and its application in image classification: A survey, Opt. Eng. 58(4) (2019) 040901. Crossref, Web of Science, Google Scholar
41. Y. Wang and Z. Wang , A survey of recent work on fine-grained image classification techniques, J. Vis. Commun. Image Represent. 59 (2019) 210–214. Crossref, Web of Science, Google Scholar
42. J. S. Wei, J. C. Lv and Z. Yi , A new sparse restricted Boltzmann machine, Int. J. Pattern Recogn. Artif. Intell. 33(10) (2019), art. no. 1951004, https://doi.org/10.1142/S0218001419510042. Link, Web of Science, Google Scholar
43. C. Wu, Y. Li, Z. Zhao and B. Liu , Extreme learning machine with autoencoding receptive fields for image classification, Neural Comput. Appl. 32(12) (2020) 8157–8173. Crossref, Web of Science, Google Scholar
44. M. Xu, J. Cheng, D. W. K. Wong, A. Taruya, A. Tanaka and J. Liu , Automatic atherosclerotic heart disease detection in intracoronary optical coherence tomography images, in Int. Conf. IEEE Engineering in Medicine and Biology Society (IEEE, Chicago, IL, USA, 2014), pp. 174–177. Google Scholar
45. L. Xu, A. Krzyzak and C. Y. Suen , Methods of combining multiple classifiers and their applications to handwriting recognition, IEEE Transactions on Systems, Man, and Cybernetics 22(3) (1992) 418–435. Crossref, Google Scholar
46. F. Yang , A CNN-based broad learning system, in IEEE Int. Conf. Computer and Communications (IEEE, Chengdu, China, 2018), pp. 2105–2109. Crossref, Google Scholar
47. F. W. Yang, H. J. Lin, S.-H. Yen and C.-H. Wang , A study on the convolutional neural algorithm of image style transfer, Int. J. Pattern Recogn. Artif. Intell. 33(5) (2019), art. no. 1954020, https://doi.org/10.1142/S021800141954020X. Link, Web of Science, Google Scholar
48. C. Zetzsche, G. Krieger and B. Wegmann , The atoms of vision: Cartesian or polar?, J. Opt. Soc. Am. A-Opt. Image Sci. Vis. 16(7) (1999) 1554–1565. Crossref, Web of Science, Google Scholar
49. J. Zhao and L. Jiao , Sparse deep tensor extreme learning machine for pattern classification, IEEE Access 7 (2019) 119181–119191. Crossref, Web of Science, Google Scholar
50. Q. Zhou and X. He , Broad learning model based on enhanced features learning, IEEE Access 7 (2019) 42536–42550. Crossref, Web of Science, Google Scholar