Using line segments to train multi-stream stacked autoencoders for image classification

Pattern Recognition Letters

Volumn 94, Issue , 2017, Pages 55-61

  Tang, Xue song ^a   Hao, Kuangrong ^a   Wei, Hui ^b   Ding, Yongsheng ^a  

^a DONGHUA UNIVERSITY   (China)

^b FUDAN UNIVERSITY   (China)

Author keywords

Deep geometric representation; Image classification; Line segments; Multi stream deep learning; Representation learning

Indexed keywords

CLASSIFICATION (OF INFORMATION); DEEP LEARNING; GEOMETRY; IMAGE SEGMENTATION; LEARNING SYSTEMS; OBJECT RECOGNITION;

AUTOENCODERS; GEOMETRIC FEATURE; GEOMETRIC INFORMATION; GEOMETRIC REPRESENTATION; LEARNING PARADIGMS; LINE SEGMENT; MULTI-STREAM; REPRESENTATION LEARNING;

IMAGE CLASSIFICATION;

EID: 85019835456     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patrec.2017.05.025     Document Type: Article

References (22)

1. Krizhevsky, A., Sutskever, I., Hinton, G.E., Imagenet classification with deep convolutional neural networks. International Conference on Neural Information Processing Systems, 2012, 1097–1105.
2. Taigman, Y., Yang, M., Ranzato, M., Wolf, L., Deepface: closing the gap to human-level performance in face verification. 2014, 1701–1708.
3. Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L., Panda: pose aligned networks for deep attribute modeling. 2014, 1637–1644.
4. Farabet, C., Couprie, C., Najman, L., LeCun, Y., Learning hierarchical features for scene labeling. IEEE Trans. Pattern Anal. Mach. Intell. 35:8 (2013), 1915–1929.
5. Wu, D., Shao, L., Leveraging hierarchical parametric networks for skeletal joints based action segmentation and recognition. 2014, 724–731.
6. Eslami, S.M.A., Heess, N., Williams, C.K.I., Winn, J., The shape Boltzmann machine: a strong model of object shape. 2012, 406–413.
7. Wei, H., Li, Q., Dong, Z., Learning and representing object shape through an array of orientation columns. IEEE Trans. Neural Netw. Learn. Syst. 25:7 (2014), 1346–1358.
8. Liu, X., Cao, Z., Gu, N., Nahavandi, S., Zhou, C., Tan, M., Intelligent line segment perception with cortex-like mechanisms. IEEE Trans. Syst. Man Cybern. 45:12 (2015), 1522–1534.
9. Fernandes, L.A.F., Oliveira, M.M., Real-time line detection through an improved hough transform voting scheme. Pattern Recognit. 41:1 (2008), 299–314.
10. Bonci, A., Leo, T., Longhi, S., A bayesian approach to the hough transform for line detection. IEEE Trans. Syst. Man Cybern. Part A 35:6 (2005), 945–955.
11. Grompone, Jakubowicz, J., Morel, J.M., Randall, G., Lsd: a fast line segment detector with a false detection control. IEEE Trans. Pattern Anal. Mach. Intell 32:4 (2010), 722–732.
12. Lecun, Y., Bengio, Y., Convolutional networks for images, speech, and time series. 1995.
13. Bengio, Y., Courville, A., Vincent, P., Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35:8 (2013), 1798–1828.
14. Simonyan, K., Zisserman, A., Two-stream convolutional networks for action recognition in videos. Adv. Neural. Inf. Process Syst. 1:4 (2014), 568–576.
15. Latecki, L.J., Lakamper, R., Shape similarity measure based on correspondence of visual parts. IEEE Trans. Pattern Anal. Mach. Intell. 22:10 (2000), 1185–1190.
16. Wei, H., Tang, X.S., A genetic-algorithm-based explicit description of object contour and its ability to facilitate recognition. Cybern. IEEE Trans. 45:11 (2014), 2558–2571.
17. Ferrari, V., Tuytelaars, T., Gool, L.V., Object detection by contour segment networks. Computer Vision - ECCV 2006, European Conference on Computer Vision, Graz, Austria, May 7–13, 2006, Proceedings, 2006, 14–28.
18. Borenstein, E., Ullman, S., Class-specific, top-down segmentation. Computer Vision - ECCV 2002, European Conference on Computer Vision, Copenhagen, Denmark, May 28–31, 2002, Proceedings, 2002, 109–124.
19. Marlin, B.M., Swersky, K., Chen, B., Freitas, N.D., Inductive principles for restricted Boltzmann machine learning. J. Mach. Learn. Res.-Proc. Track Artif. Intell. Stat. 9:9 (2010), 509–516.
20. Tomczak, J.M., Learning informative features from restricted Boltzmann machines. Neural Process. Lett., 2015, 1–16.
21. Mocanu, D.C., Mocanu, E., Nguyen, P.H., Gibescu, M., Liotta, A., A topological insight into restricted Boltzmann machines. Mach. Learn., 2016, 1–28.
22. Sanchez, J., Perronnin, F., High-dimensional signature compression for large-scale image classification., 42(7), 2011, 1665–1672.