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

The invention relates to a three-dimensional face recognition method for an underground coal mine, and belongs to the technical field of multi-dimensional face recognition. According to the method, the two-dimensional face image is converted into the three-dimensional points under the camera coordinate system, the rotation matrix is combined for rotation operation, the side face data of the rotating face at multiple angles are generated, and a rich data basis is provided for three-dimensional reconstruction. PointNet + + and an expansion structure thereof are combined with an auto-encoder frame to establish a three-dimensional reconstruction model, compact feature representation can be extracted from a three-dimensional point cloud, the features are utilized to reconstruct a three-dimensional face image with details and geometric structures, the three-dimensional face image is divided into a plurality of recognition areas, and feature recognition matching is performed respectively; during recognition, a face recognition result can be directly given only by screening clear areas for image reconstruction and feature matching. According to the invention, the accuracy and fidelity of reconstruction are improved.

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.

The present application relates to a kind of three-dimensional face recognition methods for coal mine underground, belong to multidimensional stereoscopic face recognition technical field.The method is converted into three-dimensional point under camera coordinate system by two-dimensional face image, and rotation matrix is combined to carry out rotation operation, generates the rotated face side face data including multiple angles, provides rich data basis for three-dimensional reconstruction.PointNet++ and its extended structure are used in conjunction with auto-encoder framework to establish three-dimensional reconstruction model, can extract compact feature representation from three-dimensional point cloud, and utilize these features to reconstruct three-dimensional facial image with details and geometric structure, three-dimensional facial image is divided into several recognition regions, and feature recognition matching is carried out respectively;Identification, only need to filter clear area to carry out image reconstruction and feature matching, can directly give face recognition result.The present application improves the accuracy and fidelity of reconstruction.

The application relates to a three-dimensional face recognition method, system, medium and equipment based on deep learning, which comprises the following steps: acquiring a first face depth image and a second face depth image; recognizing the first face depth image to obtain a first focusing area; recognizing the first face depth image to obtain a second focusing area; comparing the first focusing area with the second focusing area to determine whether the first focusing area and the second focusing area are completely coincident; and inputting the first face depth image and the second face depth image into a pre-established face recognition model to complete face recognition in the case that the first focusing area and the second focusing area are not completely coincident. The three-dimensional face recognition based on deep learning is realized by focusing on different parts of the face through twice face image collection with different focal lengths according to the depth information of the face, and by comparing the focusing areas of the two images.

A three-dimensional (3D) face recognition system includes a structured light sensor or stereo camera sensor. The 3D face recognition system also includes a time-of-flight sensor. The 3D face recognition system further includes a processor. The processor is configured to run algorithms for face recognition on data from the structured light sensor or stereo camera sensor. The processor is also configured to use distance data from the time-of-flight sensor to optimise the algorithms for face recognition.

A three-dimensional face recognition method based on deep learning includes: constructing a three-dimensional face deep learning network, calculating the high-frequency-depth map of each training sample, and then simultaneously inputting the color face two-dimensional image and the high-frequency-depth map of each training sample into the face three-dimensional deep learning network for training; using a color camera to obtain a color face two-dimensional image of a face to be tested, and then inputting the color face two-dimensional image of the face to be tested into the trained face three-dimensional deep learning network, and outputting the three-dimensional point cloud coordinates of the face to be tested; according to the color face two-dimensional image and the three-dimensional point cloud coordinates of the face to be tested, calculating a three-dimensional face feature vector, and then comparing the three-dimensional face feature vector of the face to be tested with the three-dimensional face feature vector of the registered face in the registration library, so as to identify the personnel information of the face to be tested. The present invention belongs to the field of information technology, and can make full use of the depth information of the face to effectively improve the reliability of the face recognition result.

The invention relates to three-dimensional face recognition equipment which comprises a three-dimensional face recognizer, a position adjusting mechanism and a storage mechanism. The position adjusting mechanism comprises a base, a rotating seat, a supporting part, a driving shaft, a driven shaft, a pivoting shaft and a driving part, the rotating seat can rotate on the base, and the supporting part is connected to the rotating seat and drives the three-dimensional face recognizer to rotate in the horizontal plane and the vertical plane to adjust the angle. The storage mechanism comprises a linear driver, a moving seat and an opening and closing plate, the three-dimensional face recognizer can stretch out and draw back through the linear driver and go in and out of the inlet and outlet of the containing cavity, the inlet and outlet are automatically opened and closed through the opening and closing plate, and storage and use of the three-dimensional face recognizer are achieved. Double-plane adjustment is achieved through a single power source, and the storage mechanism is matched, so that the equipment is compact in structure and convenient to use, the user experience is improved, and the manufacturing and using cost is reduced.

The present disclosure discloses a method and device for identifying a smart door lock, an electronic device and a storage medium, and relates to the technical field of electronic devices, including: obtaining a two-dimensional face image based on a camera and identifying it to obtain a first similarity; identifying a three-dimensional face image to obtain a second similarity; if the second similarity is greater than or equal to a lower limit value of the three-dimensional face image similarity and less than an upper limit value of the three-dimensional face image similarity, then judging whether the first similarity is greater than a first two-dimensional face image similarity threshold; if the first similarity is greater than the first two-dimensional face image similarity threshold, then unlocking is performed. Compared with the related art, when the second similarity is within the range of the lower limit value of the three-dimensional face image similarity and the upper limit value of the three-dimensional face image similarity, it is supplemented based on the first similarity, so that when the accuracy of the three-dimensional face image recognition is insufficient, unlocking is performed based on the first similarity, thereby improving the adaptability of the three-dimensional face recognition to the external environment.