Application of Genetic Algorithm (GA) Trained Artificial Neural Network to Identify Tomatoes with Physiological Diseases

  • Junlong Fang
  • Changli Zhang
  • Shuwen Wang
Part of the The International Federation for Information Processing book series (IFIPAICT, volume 259)

We synthetically applied computer vision, genetic algorithm and artificial neural network technology to automatically identify the tomatoes that had physiological diseases. Firstly, the tomatoes’ images were captured through a computer vision system. Then to identify cavernous tomatoes, we analyzed the roundness and detected deformed tomatoes by applying the variation of fruit’s diameter. Secondly, we used a Genetic Algorithm (GA) trained artificial neural network. Experiments show that the above methods can accurately identify tomatoes’ shapes and meet requests of classification; the accuracy rate for the identification for tomatoes with physiological diseases was up to 100%.

Keywords

tomato with physiological disease computer vision artificial neural network genetic algorithms 

References

  1. Buckley, J.J, Hayashi, Y. Fuzzy Genetic Algorithm and Applications [J]. Fuzzy Sets and Systems 1994 Vol. 61:129-136.CrossRefGoogle Scholar
  2. Chen Genshe, Zhen Xinhai. Study and Development of Genetic Algorithm [J]. Information and Control 1994; 23(4):215-21.Google Scholar
  3. Liang Min, Sun Zhongkang. Quick Learning Algorithm and Simulation Study of Multi-layer Feed-forward Neural Network [J]. Systematic E and Electronic Technology 1993 (9):47-57.Google Scholar
  4. Liu He, Wang Maohua. Research on Artificial Neural Network Expert System of Fruit Shape’s Identification [J]. Transactions of the Chinese Society of Agricultural Engineering 1996; 12(1):171-6.Google Scholar
  5. Ni, B., Paulsen, M.R., Reid, J.F. Corn Kernel Crown Shape Identification Using Image Processing [J]. Transactions of the ASAE 1997; 40(3):833-838.CrossRefGoogle Scholar
  6. Pan Wei. Study on Automatic Identification and Classification of Agricultural Products Using Computer Vision - Automatic Identification and Classification of Tomato [D]. Northeast Agricultural University, 2000.Google Scholar
  7. Sarkar, N., Wolfe, R.R. Computer Vision Based System for Quality Separation of Fresh Market Tomatoes [J]. Transactions of the ASAE 1985; 28(5):1714-8.CrossRefGoogle Scholar
  8. Sarkar, N., Wolfe, R.R. Feature Extraction Techniques for Sorting Tomatoes by Computer Vision [J]. Transactions of the ASAE 1985; 28(3):970-4.CrossRefGoogle Scholar
  9. Sun Yanfeng, Wang Zhongtuo. Parallel Genetic Algorithm [J]. Systematic Engineering 1995; 13(2):14-6.Google Scholar
  10. Ying Yibin, Jing Hansong, Ma Junfu, Zhao Jun, Jiang Yiyuan. Application of Computer Vision Technology to Test the Size of Virgin Pears and Flaws of Fruit’s Surface [J]. Transactions of the Chinese Society of Agricultural Engineering 1999; 15(2):197-200.Google Scholar
  11. Zhang Changli, Fang Junlong, Pan Wei. Research on Genetic Algorithm Trained Multi-layer Feed-forward [J]. Neural Network’s Automatic Measuring to Tomato Maturity Transactions of the Chinese Society of Agricultural Engineering 2001; 17(3):153-6.Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2008

Authors and Affiliations

  • Junlong Fang
    • 1
  • Changli Zhang
    • 1
  • Shuwen Wang
    • 1
  1. 1.Engineering College Northeast Agricultural University HarbinChina

Personalised recommendations