Paper Infomation
Profiled Fiber Image Recognition Based on Deep Convolutional Neural Network
Full Text(PDF, 1356KB)
Author: Shuolei Sun, Huan Wu, Zheng Tie
Abstract: In recent years, deep convolutional neural network (DCNN), a deep learning method, has been widely used in the field of image recognition. It not only significantly improves the recognition accuracy, but also can automatically learn and extract features layer by layer to avoid complex feature extraction process of the traditional recognition algorithm. This paper firstly introduces the DCNN for the profiled image recognition, and designs a fiber image recognition method based on a proposed DCNN. The classification results of five types of profiled fibers show that the average recognition rate is 94.4% and significant improvements are achieved in recognition accuracy as compared with SVM classifier.
Keywords: Deep Learning; Deep Convolutional Neural Network; SVM; Profiled Fiber; Fiber Recognition
References:
[1]Sumin Li, Yan Wan, Peifeng Zeng. Effect of n Chain Code on Feature Parameters of Profiled Fibers [J]. Journal of Donghua University(Natural Science),208,34(5):608-613.
[2]Rumelhart D, Hinton G, Wiliams R. Learning representations by back-propagating errors[J].Nature,1986,323(6088):533- 536.
[3]X T Xu, L Yao, Y Wan. A new shaped fiber classification algorithm based on SVM[C]//The 2nd International Workshop on Intelligent System and Applications. China, Wuhan,2010: 3-5.
[4]LeCun Y, Botou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of IEEE,1988,86 (11):2278-2324.
[5]LeCun Y, Boser B, Denker J S, et al. Backpropagation Applied to Handwriten Zip Code Recognition[J]. Neural Computation, 1989,1(4):541-551.
[6]Lawrence, S.Giles, C.L.,Tsoi,A.C.,Back,A.D. Face recognition:A convolutional neural-network approach. IEEE Transactions on Neural Networks 8(1997) 98-113.
[7]Sermanet, P., Kavukcuoglu, Chintala,S., et al. Pedestrian detection with unsupervised multi-stage feature learning. 2013 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), IEEE(2013)3626-3633.
[8]Hinton, G., Deng, L., et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29(2012)82-97.
[9] Hubel D H, Wiesel T N. Receptive Fields, Binocular Interaction and Functional Architecture in the Cat’s Visual Cortex [J]. Journal of Physiology,1962,160:106-154.
[10]Fukushima K, Miyake S.Neocognitron. A new algorithm for pattern recognition tolerant of deformations and shifts in position[J]. Pattern Recognition,1982,15(6):455-469.
[11]Hongtao Lu, Qinchuan Zhang. Applications of Deep Convolutional Neural Network in Computer Vision[J]. Journal of Data Acquisition and Processing.2016,1(31):1-17.
[12]Zhiyuan Sun, Chengxiang Lu,Zhongzhi Shi, et al. Research and Advances on Deep Learning [J].Computer Science.2016,2(43).