Open Access
2013 Recursive Neural Networks Based on PSO for Image Parsing
Guo-Rong Cai, Shui-Li Chen
Abstr. Appl. Anal. 2013(SI55): 1-7 (2013). DOI: 10.1155/2013/617618


This paper presents an image parsing algorithm which is based on Particle Swarm Optimization (PSO) and Recursive Neural Networks (RNNs). State-of-the-art method such as traditional RNN-based parsing strategy uses L-BFGS over the complete data for learning the parameters. However, this could cause problems due to the nondifferentiable objective function. In order to solve this problem, the PSO algorithm has been employed to tune the weights of RNN for minimizing the objective. Experimental results obtained on the Stanford background dataset show that our PSO-based training algorithm outperforms traditional RNN, Pixel CRF, region-based energy, simultaneous MRF, and superpixel MRF.


Download Citation

Guo-Rong Cai. Shui-Li Chen. "Recursive Neural Networks Based on PSO for Image Parsing." Abstr. Appl. Anal. 2013 (SI55) 1 - 7, 2013.


Published: 2013
First available in Project Euclid: 26 February 2014

MathSciNet: MR3039184
Digital Object Identifier: 10.1155/2013/617618

Rights: Copyright © 2013 Hindawi

Vol.2013 • No. SI55 • 2013
Back to Top