A computer vision method for mental states
A computer vision and mental state technology, applied in the field of computer vision, can solve the problems of lack of objective evaluation and single evaluation method of patient mental state, and achieve the effect of improving calculation accuracy, high flexibility, and improving diagnostic accuracy and efficiency.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0031] Such as figure 1 As shown, a computer vision method for auxiliary diagnosis of mental state, the process is as follows:
[0032] (1), select 343 facial expression video sequences of 12 objects as the training database. These include deadpan videos and micro-expressive videos.
[0033] (2) Take out each frame of the video and convert it to gray scale, and cut out each frame of the image into a face image of equal size, which is used as a training sample first.
[0034] (3) Use a convolutional neural network for network training. This convolutional neural network includes a total of 4 convolutional layers and 4 pooling layers. The operations of convolution and pooling are performed alternately. First, the image is input to the first layer. In the convolution layer, it is known that there are multiple convolution kernels. After the convolution kernels are discretely convolved with the original image and a bias item is added, the extracted image features are obtained thro...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


