Research on Prediction of Egg Freshness Based on Improved GRNN

Abstract:

The purpose of this paper is to add Particle Swarm Optimization algorithm to Generalized Regression Neural Network for predicting egg Haugh value and evaluating freshness degree of eggs. Firstly process the egg images with light-transmitting were obtained by the computer vision device including denoising, threshold segmentation, conversing HSI Color model and calculating the averages of hue, saturation, and intensity in the center of the image. Secondly analyze GRNN, and then particle swarm algorithm to optimize according to the predicted formula being derived. Thirdly train Improved GRNN and predicate Haugh value by HSI parameter data as the sample. The value of residual errors of Improved GRNN model are 6.38, the correct discerning rate of grading table eggs is 91.2%. It proves better than traditional BP neural network in terms of predicted accuracy and robustness.

• Periodical: Advanced Materials Research (Volumes 846-847)
• Pages: 902-905
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.846-847.902
• Online since: November 2013
• Authors: Jian Yang*, Ying Shi, Xiu Ying Li, Xin Wang, Ying Ying Yin
• Keywords: Freshness Degree of Eggs, Generalized Regression Neural Network, Machine Vision, Nondestructive Detection, Particle Swarm Optimization Algorithm

References

[1] Q.H. Wang, Y.L. Ren, Y.X. Wen: Transactions of the Chinese Society for Agricultural Machinery Vol. 37(2006) , p.104.

[2] L.M. Zheng, X. Yang, G.Y. Xu, H.Y. Guo: Transactions of the Chinese Society of Agricultural Engineering Vol. 10(2009) , p.335.

[3] D.F. Zhang, in: MATLAB digital image processing, edited by Machine Press, Beijing (2012) in press.

[4] KENNEDY J, EBERHART R: Particle swarm optimization (Proceedings of IEEE International Conference on Neural Networks. Perth, Australia1995).

[5] J.B. Zhang, C.F. Li, Y. Hong: Computer Engineering and Applications Vol. 43(2007) , p.49.