Figure | The metasurface-based optical learning machine (MOLM) for highly scalable machine vision (IMAGE)
Caption
Figure | The metasurface-based optical learning machine (MOLM) for highly scalable machine vision. a, Schematic of the MOLM. The optical image generated by a spatial light modulator (SLM) is projected onto a single-layer metasurface consisting of massive cylindrical silicon meta-atoms. An optical lens then collects the reflected optical image by the metasurface. Following that, the optical field at the focusing plane is captured by an image sensor array. Lastly, the captured image is fed into a digital neural network to produce the prediction result. b, Image of the metasurface chip compared with a Hong Kong dollar coin. c, The heat map of the prediction probabilities of the MOLM and the state-of-the-art segmentation model (SAM). The inset graphs a, b, and c represent three different zoom-in regions of the WSI, respectively.
Credit
Prof. Chaoran Huang et al.
Usage Restrictions
Credit must be given to the creator.
License
CC BY