15 - Quality Evaluation of Wheat

Abstract

The quality of wheat varies significantly due to differences in physiology, growing conditions, crop management practices, and grain handling and storage techniques. This chapter focuses on quality evaluation of wheat using machine vision systems. The major tasks performed by a machine vision system can be grouped into three processes: image acquisition, processing or analysis, and recognition. Various characteristics of the objects are extracted and final decisions are made using different image-processing algorithms and pattern-recognition techniques, respectively. Machine-vision-based inspection is already in commercial use in automotive, electronics, and other industries. Many of the industrial objects being inspected are of defined size, shape, color, and texture. Agricultural or biological objects, including grain kernels, on the other hand, are of variable size, shape, color, and texture. In addition, these features may vary from year to year, by growing region within a year, and even over a single growing season. The development of a near-infrared (NIR) spectroscopy system for measuring the moisture and protein content in wheat, the kernel vitreousness or hardness, fungal contamination, scab or mold damage, and insect infestation has made the measurement of these quality factors objective, and the system has been adopted by the industry. NIR spectroscopy has replaced the chemically intensive Kjeldahl method for protein content measurement in many countries. For proper functioning of the NIR system, large amounts of reference data from different growing regions should be used for calibration. Once properly calibrated, it is a rapid technique requiring small sample sizes. NIR spectroscopy has the potential to be used for measuring the hardness and vitreousness of kernels, for color classification, the identification of damaged kernels, the detection of insect and mite infestation, and the detection of mycotoxins.