US Patent Application 18337806. Emotion Detection simplified abstract
Contents
Emotion Detection
Organization Name
Inventor(s)
Olivier Soares of San Jose CA (US)
Emotion Detection - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18337806 Titled 'Emotion Detection'
Simplified Explanation
The abstract describes a method for estimating emotions from facial images. It involves using a convolutional neural network (CNN) to analyze the image and generate a numerical representation called a latent vector. This CNN is trained using pairs of facial images and their corresponding 3D mesh representations. The method also involves comparing the latent vector of the image to a database of previously processed latent vectors associated with known emotion types to determine the emotion type of the image.
Original Abstract Submitted
Estimating emotion may include obtaining an image of at least part of a face, and applying, to the image, an expression convolutional neural network (“CNN”) to obtain a latent vector for the image, where the expression CNN is trained from a plurality of pairs each comprising a facial image and a 3D mesh representation corresponding to the facial image. Estimating emotion may further include comparing the latent vector for the image to a plurality of previously processed latent vectors associated with known emotion types to estimate an emotion type for the image.
