Study of the Vibration Screening for Image Recognition of the Stored-Grain Insects

Abstract:

The automatic vibration screening of the insects is the important part in the image recognition of the stored-grain insects. A screening detection device of the stored-grain insects was developed to analyze the vibration screening properties of Coleopteran insects. The main structure of the device included a vibration screening unit, a dust removal unit of the grain insects, a binocular machine vision unit and an automatic transporting unit. The adults of Sitophilus Oryzae were taken as the screening objects. Full factorial design was used in order to find out the better vibration screening parameters. Then orthogonal experiment was designed to optimize the screening parameters further, and distinguish between the primary factors and the secondary factors. The optimal vibration screening parameters of the detection device for the stored-grain insects were determined by a series of experiments. The best parameters were that the amplitude of the vibration sieve was 3.5 mm, the vibrating direction angle was 30oand the crank plate speed was 600r/min.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3302-3306
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3302
• Online since: August 2013
• Authors: Hong Tao Zhang, Heng Yuan Zhang, Yu Xia Hu
• Keywords: Full Factorial Design (FFD), Image Recognition, Parameter Optimization, Stored-Grain Insects, Vibration Screening

References

[1] S. Neethirajan, C. Karunakaran, D. S. Jayas, and N. D. G. White. Detection techniques for stored-product insects in grain [J]. Food Control. vol. 18(2007) No. 2, pp.157-162.

DOI: 10.1016/j.foodcont.2005.09.008

[2] A. V. Braker, W. E. Burkholder, and D. L. Faustini. Factors affecting the design of traps for stored-product insects[J]. Journal of the Kansas Entomological Society，Vol. 63(1990) No. 4, pp.466-485.

[3] F. E. Dowell, J. E. Throne, and D. Wang. Identifying stored-grain insects using near-infrared spectroscopy[J]. Journal of Economic Entomology, Vol. 92(1999) No. 1, pp.165-169.

DOI: 10.1093/jee/92.1.165

[4] C. Ridgway, E. R. Davies, and J. Chambers. Rapid machine vision method for the detection of insects and other particulate bio-contaminants of bulk grain in transit[J]. Biosystem Engineering. vol. 83(2002) No. 1, pp.21-30.

[5] H. P. Mao and H. T. Zhang. Stored-grain pests image recognition progress and prospects of research[J]. Journal of Agricultural Machinery, vol. 39(2008) No. 4, pp.175-179. (in Chinese).

[6] M. A. Shahin and S. J. Symons. Detection of Fusarium damaged kernels in Canada Western Red Spring wheat using visible near_infrared hyperspectral imaging and principal component analysis [J]. Computers and Electronics in Agriculture, vol. 75(2011).

DOI: 10.1016/j.compag.2010.10.004

[7] C. B. Singh, D. S. Jayas, J. Paliwal, and N. D.G. White. Identification of insect-damaged wheat kernels using short-wave near-infrared hyperspectral and digital color[J]. Computers and Electronics in Agriculture, vol. 73(2010) No. 2, pp.118-125.

DOI: 10.1016/j.compag.2010.06.001

[8] D. Y. Qiu, H. T. Zhang, T. J. Chen, W. B. Tang, Y. Z. Zhang, and C. H. Zhang. Hardware design of an intelligent detection system for stored-grain pests based on machine vision[J]. Journal of Agricultural Machinery, vol. 34(2003) No. 1, pp.86-87.