Intelligent detection of imperfect wheat grains based on machine vision is of great significance to correctly and rapidly evaluate wheat quality. There is little difference between the partial characteristics of imperfect and perfect wheat grains, which is a key factor limiting the classification and recognition accuracy of imperfect wheat based on a deep learning network model. In this paper, we propose a method for imperfect wheat grains recognition combined with an attention mechanism and residual network (ResNet), and verify its recognition accuracy by adding an attention mechanism module into different depths of residual network. Five residual networks with different depths (18, 34, 50, 101, and 152) were selected for the experiment, it was found that the recognition accuracy of each network model was improved with the attention mechanism, and the average recognition rate of ResNet-50 with the addition of the attention mechanism reached 96.5%. For ResNet-50 with the attention mechanism, the optimal learning rate was further screened as 0.0003. The average recognition accuracy reached 97.5%, among which the recognition rates of scab wheat grains, insect-damaged wheat grains, sprouted wheat grains, mildew wheat grains, broken wheat grains, and perfect wheat grains reached 97%, 99%, 99%, 95%, 96%, and 99% respectively. This work can provide guidance for the detection and recognition of imperfect wheat grains using machine vision.

The turbulence effect, thermal blooming effect, laser beam aberration, platform jitter, and other effects in the process of high energy laser propagation in the atmosphere will cause serious degradation of laser beam quality, which will have a negative impact on the actual application of laser propagation engineering. It is important in the engineering application of high-energy laser propagation to evaluate the far-field intensity distribution quickly. Based on the optical transfer function (OTF) theory of imaging system, the propagation process of high-energy lasers is modeled as the imaging process of point source. By using the convolution of point spread function (PSF) of jitter, turbulence, thermal blooming, and aberration of emission system, fast calculation of the far-field intensity distribution of high energy laser is realized. The calculation results are compared with those obtained by the 4D wave optics simulation program in different propagation scenarios. The results show that the calculated facula distribution and encircled energy of this method are in good agreement with the simulation results of wave optics, which can realize the fast and accurate evaluation of the far-field intensity distribution of high-energy laser propagation and provide a reference for practical engineering application.