Shape recognition based on neural networks trained by differential evolution algorithm

In this paper a new method for recognition of 2D occluded shapes based on neural networks using generalized differential evolution training algorithm is proposed. Firstly, a generalization strategy of differential evolution algorithm is introduced. And this global optimization algorithm is applied to train the multilayer perceptron neural networks. The proposed algorithms are evaluated through a plant species identification task involving 25 plant species. For this practical problem, a multiscale Fourier descriptors (MFDs) method is applied to the plant images to extract shape features. Finally, the experimental results show that our proposed GDE training method is feasible and efficient for large-scale shape recognition problem. Moreover, the experimental results illustrated that the GDE training algorithm combined with gradient-based training algorithms will achieve better convergence performance.

[1]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[2]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[3]  Riccardo Poli,et al.  New ideas in optimization , 1999 .

[4]  George Papadourakis,et al.  Curvature scale-space-driven object recognition with an indexing scheme based on artificial neural networks , 1999, Pattern Recognit..

[5]  Steven Doyle,et al.  Automated mirror design using an evolution strategy , 1999 .

[6]  C. Charalambous,et al.  Conjugate gradient algorithm for efficient training of artifi-cial neural networks , 1990 .

[7]  Thomas S. Huang,et al.  Modified Fourier Descriptors for Shape Representation - A Practical Approach , 1996 .

[8]  Min Liang,et al.  Fast learning algorithms for multi-layered feedforward neural network , 1994, Proceedings of National Aerospace and Electronics Conference (NAECON'94).

[9]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[10]  Mandyam D. Srinath,et al.  Contour sequence moments for the classification of closed planar shapes , 1987, Pattern Recognit..

[11]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[12]  Chris Aldrich,et al.  Combinatorial evolution of regression nodes in feedforward neural networks , 1999, Neural Networks.

[13]  R. Storn,et al.  Differential evolution a simple and efficient adaptive scheme for global optimization over continu , 1997 .

[14]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[15]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[16]  S. P. Day,et al.  A stochastic training technique for feed-forward neural networks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[17]  Stefan Janaqi,et al.  Generalization of the strategies in differential evolution , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[18]  Joni-Kristian Kämäräinen,et al.  Differential Evolution Training Algorithm for Feed-Forward Neural Networks , 2003, Neural Processing Letters.

[19]  Sven Loncaric,et al.  A survey of shape analysis techniques , 1998, Pattern Recognit..