Evaluation method and device for face image similarity
A face image and evaluation method technology, which is applied in the field of face image similarity evaluation methods and devices, can solve problems such as reduced efficiency, increased distance, and failure of Euclidean distance similarity measurement, so as to reduce computational complexity and storage space, improving efficiency and applicability, and reducing computational complexity
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0064] Such as figure 1 As shown, the method for evaluating the similarity of human face images provided by the embodiment of the present application, an implementation thereof, includes the following steps:
[0065] Step 102: Collect face image information, obtain face multi-dimensional feature vectors, and perform Int quantization on the face multi-dimensional feature vectors.
[0066] Use face photo collection equipment (such as cameras, monitors, etc.) to collect face image information and transmit it to the face recognition server, use face recognition algorithms (such as SenseTime face recognition algorithms, etc.) to calculate the feature vector of the face image to be recognized, and calculate Obtain 512-dimensional eigenvalues, and the dimension of eigenvectors is related to the algorithm, generally greater than 500 dimensions.
[0067] Perform Int quantization on the obtained float-type 512-dimensional eigenvalues. For example, Int6 quantization or Int8 quantization...
Embodiment 2
[0099] like image 3 As shown, an embodiment of the apparatus for evaluating the similarity of human face images provided by the embodiment of the present application includes a quantization module 310 , a dimensionality reduction module 320 , a training module 330 and an evaluation module 340 .
[0100] The quantization module 310 is configured to collect face image information, obtain multi-dimensional feature vectors of faces, and perform Int quantization on the multi-dimensional feature vectors of faces, so as to reduce computational complexity and storage space.
[0101] Use face photo collection equipment (such as cameras, monitors, etc.) to collect face image information and transmit it to the face recognition server, use face recognition algorithms (such as SenseTime face recognition algorithms, etc.) to calculate the feature vector of the face image to be recognized, and calculate Obtain 512-dimensional eigenvalues, and the dimension of eigenvectors is related to the ...
Embodiment 3
[0138] An embodiment of the device for evaluating the similarity of human face images provided by the present application includes a memory and a processor.
[0139] memory for storing programs;
[0140] The processor is configured to implement the method in Embodiment 1 by executing the program stored in the memory.
[0141]Those skilled in the art can understand that all or part of the steps of the various methods in the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: read-only memory, Random access memory, disk or CD, etc.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com