Quality Assessment of Components of Wheat Seed Using Different Classifications Models

To use machine vision technology in visual quality control of cereal seeds, sufficient knowledge is necessary. In this work, the capability systems, equipped with industrial digital cameras for identification and classification seven-grain groups wheat seed samples, was studied. Two statistical models three support vector machines were employed study. Through image processing 21,000 single grains, shape, colour, textural features each grain determined. Ninety-one ranked through ReliefF method. The shape most prominent, followed by colour features. Among five tested, highest accuracy obtained using quadratic (QSVM) first 35 test run model independent data, sound white wheat, small broken shrunken red barley rye were, respectively, 98.7, 98, 99.3, 90.7, 99, 100, 97.3%, an overall average 97.6%. context study, system—comprising camera or non-linear discriminate analysis method—was identified as a valuable system investigation qualities seeds.