High accuracy object detection by an optical neural network implementation

In recent years, AI technology using Neural Network (NN) has made remarkable progress and is used for highly accurate classification, object detection, and anomaly detection in sensing. The difficulties with high-accuracy NN are the long processing time and high-power consumption. As one solution, an optical neural network (ONN), which realizes NN by diffraction and propagation of light, has attracted attention as an implementation method with ultra-high speed and low power consumption. Although many of the prior studies on ONN are related to classification, ONN has the potential to be applied to various tasks. As one example, the use of ONN has the possibility of ultra-fast object detection. In this study, simulations and experiments were conducted to verify the possibility of detection by ONN. Metal nuts were selected as the detection targets as a representative example of mass-produced industrial parts. In the experiment, SLM was used to implement the data input layer as phase input and the trained diffraction layer. First, the case of a single detection target in the input data was demonstrated. The precision for the 551-input data was 96.4 % in the experiment. In the data that could be detected correctly, the root mean square error between the inferred and correct positions was 2.2 % of the metal nut size. Next, another experiment has confirmed that ONN can detect multiple targets accurately. In addition, we examined ONN that uses light transmitted through the sample and found that the inference process finished within 4.17 msec (the response time of the CMOS of this setup). The results show that ONN can accurately and rapidly detect objects.