Adaptive Convolutional Neural Network and Its Application in Face Recognition

Convolutional neural network (CNN) has more and more applications in image recognition. However, the structure of CNN is often determined after a performance comparison among the CNNs with different structures, which impedes the further development of CNN. In this paper, an adaptive convolutional neural network (ACNN) is proposed, which can determine the structure of CNN without performance comparison. The final structure of ACNN is determined by automatic expansion according to performance requirement. First, the network is initialized by a one-branch structure. The system average error and recognition rate of the training samples are set to control the expansion of the structure of CNN. That is to say, the network is extended by global expansion until the system average error meets the requirement and when the system average error is satisfied, the local network is expanded until the recognition rate meets the requirement. Finally, the structure of CNN is determined automatically. Besides, the incremental learning for new samples can be achieved by adding new branches while keeping the original network unchanged. The experiment results of face recognition on ORL face database show that there is a better tradeoff between the consumption of training time and the recognition rate in ACNN.

[1]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[2]  Claus Nebauer,et al.  Evaluation of convolutional neural networks for visual recognition , 1998, IEEE Trans. Neural Networks.

[3]  Christophe Garcia,et al.  A neural architecture for fast and robust face detection , 2002, Object recognition supported by user interaction for service robots.

[4]  José Hiroki Saito,et al.  Using CMU PIE Human Face Database to a Convolutional Neural Network - Neocognitron , 2005, ESANN.

[5]  Gennaro Della Vecchia,et al.  Parallel, distributed and network-based processing , 2008, J. Syst. Archit..

[6]  Peng Hong-jing Incremental Convolution Neural Network and Its Application in Face Detection , 2009 .

[7]  Klaus Kofler,et al.  Performance and Scalability of GPU-Based Convolutional Neural Networks , 2010, 2010 18th Euromicro Conference on Parallel, Distributed and Network-based Processing.

[8]  Berin Martini,et al.  Hardware accelerated convolutional neural networks for synthetic vision systems , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[9]  Brian Cheung,et al.  Hybrid Evolution of Convolutional Networks , 2011, 2011 10th International Conference on Machine Learning and Applications and Workshops.

[10]  Yann LeCun,et al.  Traffic sign recognition with multi-scale Convolutional Networks , 2011, The 2011 International Joint Conference on Neural Networks.

[11]  Yuan He,et al.  Cascaded heterogeneous convolutional neural networks for handwritten digit recognition , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).

[12]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[13]  Henk Corporaal,et al.  Memory-centric accelerator design for Convolutional Neural Networks , 2013, 2013 IEEE 31st International Conference on Computer Design (ICCD).

[14]  Christian S. Jensen,et al.  GPU-Based Computing of Repeated Range Queries over Moving Objects , 2014, 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing.

[15]  Shiming Xiang,et al.  Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks , 2014, IEEE Geoscience and Remote Sensing Letters.