2 results about "Three-dimensional face recognition" patented technology

The invention discloses a 3D face cluster classification system based on a twin point cloud network, and relates to the field of three-dimensional face recognition, and the system comprises a point cloud obtaining and preprocessing module which is used for obtaining original three-dimensional face point cloud data, and carrying out the spatial normalization and enhancement processing of the data; the twin feature extraction module is used for hierarchically extracting multi-scale local features from the preprocessed point cloud and aggregating the multi-scale local features into global feature representation; the geometric consistency constraint module is used for generating a geometric constraint signal based on the similarity measurement between the input point cloud pairs in the original geometric space in the feature learning process; and the collaborative optimization judgment module is used for fusing the geometric constraint signal and classification loss based on depth features, jointly guiding parameter updating, and finally outputting a human face group classification result. According to the scheme of the invention, the instability of feature characterization under a complex acquisition condition can be reduced, and the discrimination capability of fine geometric differences of different ethnic groups is enhanced.

The present application relates to the technical field of optical dot array projector, and especially relates to a regular dot array pattern projector device based on VCSEL, which receives configuration instructions through a parameter configuration module and outputs parameters such as lateral period, longitudinal period and offset; a light source generation module integrates a vertical cavity surface emitting laser chip, and generates laser beams with corresponding divergence angles according to arrangement parameters; an optical processing module includes a microlens array, a diffractive optical element or a mask element, the unit arrangement parameters of which are consistent with the configuration parameters, and the optical processing module performs beam splitting, diffraction or screening processing on the light beams; a distance control module calculates and maintains the working distance between the chip and the optical element based on the generalized Talbot principle; and a pattern generation module converts the processed light beams into regular dot array patterns and projects the regular dot array patterns to a target area. The present application does not need physical cutting and splicing of the microlens array, reduces the customization cost and detection complexity, improves the production yield and pattern accuracy, and is suitable for three-dimensional face recognition and industrial vision scenes.