Abstract: An optical path folding element includes a main body, a light absorption film layer and a matte structure. The main body has optical surface including an incident surface, a reflective surface and an emitting surface. A light enters into the optical folding element through the incident surface. The reflective surface reflects the light so as to change a traveling direction thereof. The light exits the optical folding element through the emitting surface. The light absorbing film layer is configured to reduce reflectance and provided adjacent to at least part of the optical surface, and the light absorbing film layer is in physical contact with the main body. The matte structure is disposed adjacent to at least part of the optical surface. The matte structure provides an undulating profile on a surface of the optical path folding element, and the matte structure is formed in one-piece with the main body.

Abstract: An imaging lens module includes a plastic lens barrel, a first optical element assembly and a second optical element assembly, wherein both of the first optical element assembly and the second optical element assembly are disposed in the plastic lens barrel. The plastic lens barrel includes a first inner annular surface and a second inner annular surface. The first inner annular surface forms a first receiving space. The second inner annular surface forms a second receiving space. The first optical element assembly is disposed in the first receiving space and includes a plurality of optical lens elements and a first retainer. The second optical element assembly is disposed in the second receiving space and includes a first light blocking sheet and a second retainer.

Abstract: A verification system and a verification method for a neural network accelerator hardware are provided. The verification system for a neural network accelerator hardware includes a neural network graph compiler and an execution performance estimator. The neural network graph compiler is configured to receive an assumed neural network graph and convert the assumed neural network graph into a suggested inference neural network graph according to a hardware information and an operation mode. The execution performance estimator is configured to receive the suggested inference neural network graph and calculate an estimated performance of the neural network accelerator hardware according to a hardware calculation abstract information of the suggested inference neural network graph.

Abstract: A chip-scale integrated multi-wavelength biological sensing device employing a plurality of filter-sensor assemblies is provided. The plurality of filter-sensor assemblies can include sufficient number of optical channels enabled by plasmonic filters having different nanoscale patterns and provided directly on an array of photodetectors. Combined with simultaneous illumination of light including multiple peak wavelengths with small full width at half maximum values, the independent optical channels of the plurality of filter-sensor assemblies enable correlation of detected optical signals with biological parameters. Signal processing methods for robustly extracting The PPG signals can be extracted by a robust signal processing method. Successful measurement of peripheral blood oxygen (SpO2) and blood pressure has been demonstrated.