Age prediction system and method based on voiceprint and facial image feature fusion
A face image and feature fusion technology, applied in character and pattern recognition, speech analysis, instruments, etc., can solve problems such as age prediction error, and achieve the effect of increasing accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0058] This embodiment provides an age prediction method based on fusion of voiceprint and face image features;
[0059] 1. Gender classification training process:
[0060] Image / voice data: When the system performs human-computer interaction, the system obtains two kinds of data through the microphone / camera: voice data and image data. When the device is in training mode, we need to train the obtained data separately. When the device is in the recognition mode, it is necessary to classify the obtained data by gender;
[0061] (1) Preprocessing: This step is mainly to process the original signal into a signal recognizable by the system through some specific processing. (2) Face preprocessing: First, the face in the image is detected by DLIB. Secondly, the detected face is subjected to mean filtering to filter out the noise in the image. Then, histogram equalization increases image contrast and reduces lighting effects. Finally, geometric normalization eliminates the influ...
Embodiment 2
[0100] This embodiment provides an age prediction system based on fusion of voiceprint and face image features: comprising: an image acquisition module, a sound acquisition module, a control module, a storage module and a training recognition module;
[0101] The image acquisition module: collect sample face images;
[0102] The sound collection module: collect sample sounds;
[0103] The storage module: receiving and storing the collected sample face image sent by the image collection module, receiving and storing the sample sound sent by the sound collection module;
[0104] The training identification module: call the sample face image and sample sound in the storage module to carry out training and identification to obtain a gender classifier, and obtain an age prediction classifier according to the fusion training of the sample face image, sample sound and gender classifier;
[0105] The storage module: receives and stores gender classifier and age prediction classifier;...
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