Efficient detection of internal infestation in wheat based on biophotonics.

In the process of grain storage, there are many losses of grain quantity and quality for the sake of insects. As a result, it is necessary to find a rapid and economical method for detecting insects in the grain. The paper innovatively proposes a model of detecting internal infestation in wheat by combining pattern recognition and BioPhoton Analytical Technology (BPAT). In this model, the spontaneous ultraweak photons emitted from normal and insect-contaminated wheat are firstly measured respectively. Then, position, distribution and morphological characteristics can be extracted from the measuring data to construct wheat feature vector. Backpropagation (BP) neural network based on genetic algorithm is employed to take decision on whether wheat kernel has contaminated by insects. The experimental results show that the proposed model can differentiate the normal wheat from the insect-contaminated one at an average accuracy of 95%. The model can also offer a novel thought for detecting internal infestation in the wheat.