Device for comparing a plurality of photos of the same user
A photo and face feature technology, applied in the field of photo comparison devices, can solve the problems of inaccurate comparison results, etc., and achieve the effects of overcoming one-sidedness, ease of use, and improving the comparison rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0019] Example one
[0020] Such as figure 1 As shown in the photo comparison device for one person with multiple photos, the photo reading module 1 is connected to the middle module 2, and the photo reading module 1 reads multiple photos of the person who needs to be identified, and can include a scanner to scan the photos if necessary . The read photo data is transmitted to the middle module 2 to extract facial features and construct a template.
[0021] The photo comparison device has a built-in photo module 3 in which a face database stores many face photos. The photo module 3 extracts facial features from these face photos and constructs templates respectively.
[0022] The data of the middle module 2 and the photo module 3 are transmitted to the identification module 4 for comparison and identification, and then the result module 5 sorts and extracts candidate results for display on the display module 6.
[0023] The comparison of the recognition module 4 may adopt a method of...
Example Embodiment
[0029] Example two
[0030] Such as figure 1 In the photo comparison device with multiple photos of one person shown, the comparison of the recognition module 4 can adopt a method of finding the maximum similarity, including a maximum similarity calculation unit.
[0031] The rest is the same as the first embodiment
[0032] The working process of the device is as follows:
[0033] 1) The photo module contains existing M face photos, extract facial features from these photos, and construct templates. Each template in this module is marked as B i (0≤i≤M).
[0034] 2) The intermediate module extracts facial features for N photos of the same person to be recognized, and each feature template is denoted as A j (0
[0035] 3) The recognition module compares the template in the intermediate module with the template in the photo module, and finds the maximum similarity with each template in the photo module, namely: S i =MAX(F(A j , B i )), where F is the comparison function of the two te...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap