Abstract: Natural variation of hardness of wheat kernels often results in overlapping hardness indices (HI) distributions between hard and soft classes as measured with the single kernel characterization system (SKCS). This is particularly true for the case of the hard white (HW) and soft white (SW) wheat classes. To address this problem, a color camera was incorporated into the SKCS system so that color and kernel size data could be combined with SKCS measurements for classification purposes. Samples of hard red (HR), soft red (SR), HW, and SW wheat were classified using the SKCS system with and without the camera and results compared. Using the camera system, errors for separating HW from SW classes were reduced to less than 5%, as compared to 17.1% using SKCS alone. Furthermore, improved data processing applied to the low-level data currently produced by the SKCS system led to greater than 50% reduction in classification errors between SW and HR as compared to using HI data alone. Similar improvements in classification accuracies for 300-kernel sample containing mixtures of SW and HW were also achieved. The 300 kernel sample classification is usually what inspectors and grain traders use to determine sample purity rather than individual kernel results. The techniques developed should aid grain inspectors in properly identifying mixtures of these two classes. Unfortunately, for the SR and HR classes, incorporating the camera data decreased classification accuracy while increasing the complexity of the system. However, SR and HR clwww.lw20.comasses can be adequately distinguished with the SKCS in its current form.
Author: ;Thomas C. Pearson, Daniel L. Brabec;Hulya Dogan
Author Unit: ;
Keyword: 
Year: 
Source: Sensing and Instrumentation for Food Quality and Safety
Volume-OnPage: 
Publication Date: 
 
相似文献 [1]    Madjidi, Y. Shirinzadeh, B. Banirazi, R. Yanling Tian Smith, J. Yongmin Zhong    An Improved Approach to Estimate Soft Tissue Parameters Using Genetic Algorithm for Minimally Invasive Measurement
[2]    Pagana, G. Lepore, E. Pugno, N. Attardo, E.A. Vecchi, G.    Microwave imaging: From soft towards hard tissue monitoring
[3]    Yager, R.R.    Hard and soft information fusion using measures
[4]    Shastry, M.C. Narayanan, R.M. Rangaswamy, M.    Compressive radar imaging using white stochastic waveforms
[5]    Symons, S. Juan Xing Shahin, M. Hatcher, D.    The objective measurement of alpha-amylase in wheat kernels using spectral imaging
[6]    Zainud-Deen, S.H. El-Hadad, E.S. Awadalla, K.H. Sharshar, H.A.    Landmines discrimination using scattering parameters and an artificial neural network
[7]    Pengfei Song Linstrom, K.R. John Boye, A. Kulig, K. Burnfield, J.M. Bashford, G.R.    Tendinopathy discrimination using spatial frequency parameters and Artificial Neural Networks
[8]    Yuejun Jiang Henry Kautz Bart Selman    Solving Problems with Hard and Soft Constraints Using a Stochastic Algorithm for MAX-SAT
[9]    Protiwa, F.-F. Seekamp, E.    Experimental results using MCTs in hard and soft switching modes
[10]    Liguo Wang Xiuping Jia    Integration of Soft and Hard Classifications Using Extended Support Vector Machines