Performance evaluation of a model for the classification of contaminants from wheat using near-infrared hyperspectral imaging

Citation

Ravikanth, L., Singh, C.B., Jayas, D.S., White, N.D.G. (2016). Performance evaluation of a model for the classification of contaminants from wheat using near-infrared hyperspectral imaging. Biosystems Engineering, [online] 147 248-258. http://dx.doi.org/10.1016/j.biosystemseng.2016.04.001

Plain language summary

The presence of contaminants in wheat reduces its quality and thereby its grade. The identification of these contaminants in wheat is difficult when they are physically and sometimes visually similar. Moreover, manual contaminant identification methods are time-consuming and labour intensive. Near-infrared (NIR) hyperspectral imaging is an advanced image processing technique used effectively for quality evaluation of various food and agricultural products. This technique can be an effective alternative to the traditionally used manual contaminant identification methods. This study reports the performance evaluation of the previously developed classification model to differentiate seven foreign material types (barley, canola, maize, flaxseed, oats, rye, and soybean); six dockage types (broken wheat kernels, buckwheat, chaff, wheat spikelets, stones, and wild oats); and two animal excreta types (deer and rabbit droppings) from Canada Western Red Spring (CWRS) wheat using NIR hyperspectral imaging. We were able to detect the various contaminants in wheat.

Abstract

The presence of contaminants in wheat reduces its quality and thereby its grade. The identification of these contaminants in wheat is difficult when they are physically and sometimes visually similar. Moreover, manual contaminant identification methods are time-consuming and labour intensive. Near-infrared (NIR) hyperspectral imaging is an advanced image processing technique used effectively for quality evaluation of various food and agricultural products. This technique can be an effective alternative to the traditionally used manual contaminant identification methods. This study reports the performance evaluation of the previously developed classification model to differentiate seven foreign material types (barley, canola, maize, flaxseed, oats, rye, and soybean); six dockage types (broken wheat kernels, buckwheat, chaff, wheat spikelets, stones, and wild oats); and two animal excreta types (deer and rabbit droppings) from Canada Western Red Spring (CWRS) wheat using NIR hyperspectral imaging. The classification model tested in this study was developed using standard normal variate (SNV) spectral pre-processing technique and k-nearest neighbours (k-NN) classifier. Two separate experiments were conducted to identify and quantify (by number) the amount of contaminant type present along with wheat. The performance of the classification model was compared with the model validation results. The results of the developed classification model were very close to the model validation results and thus this model can be used for the classification of various contaminants in wheat.

Publication date

2016-07-01