Digital image analysis of grain samples for potential use in grain cleaning.

摘要

A database of high resolution digital images of individual kernels of five grain types (barley, Canada Western Amber Durum (CWAD) wheat, Canada Western Red Spring (CWRS) wheat, oats, and rye) collected from 23 growing locations across Western Canada, was formed. The constituents of dockage were also divided into five broad categories (broken wheat kernels, chaff, buckwheat, wheat-heads, and canola) and imaged. A total of 230 features (51 morphological, 123 color, and 56 textural) were extracted from these images and classification was done using a four layer back propagation network (BPN) and a statistical (non-parametric) classifier. Different feature models, namely, morphological, color, texture, and a combination of the three, were tested for their classification performances. The results of these classification processes were used to test the feasibility of a machine vision based grain cleaner.; For cereal grains, while using the BPN classifier, classification accuracies of over 98% were obtained for barley, CWRS wheat, oats, and rye. Because of its misclassification with CWRS wheat, CWAD wheat gave a lower classification accuracy of 91%. For the dockage fractions, because of the uniqueness in their size and/or color, broken wheat kernels, buckwheat, and canola could be classified with almost 100% accuracy. The classification accuracies of chaff and wheat-heads was low because they did not have well defined shapes.; Back propagation network outperformed the non-parametric classifier in almost all the instances of classification. None of the three feature sets, i.e., morphological, color, or texture, in themselves, were capable of giving high classification accuracies. Their combination improved the classification significantly. But the use of all the features together did not give the best classification results as a lot of the features were redundant and did not contribute much towards the classification process. A feature set consisting of the top 20 morphological, color, and textural features each, gave the best results.; To quantify the amount of impurity in a grain sample, a relationship between the morphology and mass of the kernel (or dockage particle) was investigated. Area of a particle in a given image gave the best estimate of its mass. This relationship was tested and validated for quantifying the amount of impurity in a sample before and after passing it through a lab scale cleaner.; To automate the cleaner, it is desirable that the cleaner should have a decision support system to adjust its parameters (such as vibration rate, grain flow rate, etc.) by calculating the amount of impurity being removed from the sample. This was done by calculating the change in the ranges of morphological features of the particles before and after the sample was passed through the cleaner. The ranges of morphological features change significantly when a sample is passed through the cleaner, and thus can be used to provide a feedback to the system.