Neonatal pain expression recognition method based on double-flow convolutional neural network
A convolutional neural network and expression recognition technology, applied in the field of newborn pain expression recognition, can solve the problems of only considering the video space information and ignoring the video time information, so as to reduce the complexity, improve the recognition rate and high recognition rate Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0038] Such as figure 1 As shown, the specific steps of a newborn pain expression recognition method based on shared Attention two-stream convolutional neural network are as follows:
[0039] Step 1: Obtain the neonatal pain expression database. There are a total of 1897 videos in this database, including 4 emotions in total. These 4 emotions are: calm, crying, mild pain and severe pain. The ratio is divided into training set and test set. Part of the video capture images in the database are as follows image 3 shown.
[0040] Step 2: Framing the videos in the training set and testing set in the database to obtain a series of frame pictures, then select the frame with the largest expression change in each video frame, and add optical flow between multiple consecutive frames The corresponding optical flow diagram is obtained by the displacement field, and the specific operation is as follows:
[0041] (1) Capture frames from the video
[0042] Use the ffmpeg code in OpenCV ...
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