Deception detection system and method
First Claim
1. A system for detecting an emotional state of a person of interest, the system comprising a processing unit and a storage device, the processing unit configurable to:
- receive an image sequence captured of the person of interest;
determine hemoglobin concentration (HC) changes of the person of interest from the image sequence;
determine an emotional state associated with the person of interest using a trained classification machine learning model, the trained classification machine learning model receiving the HC changes as input, the training set for the trained classification machine learning model comprising previously determined HC changes from images of subjects with known emotional states; and
output the determined emotional state.
0 Assignments
0 Petitions
Accused Products
Abstract
A system for detecting deception is provided. The system comprises a camera, an image processing unit, and a notification device. The camera is configured to capture an image sequence of a person of interest. The image processing unit is trained to determine a set of bitplanes of a plurality of images in the captured image sequence that represent the hemoglobin concentration (HC) changes of the person, and to detect the person'"'"'s invisible emotional states based on HC changes. The image processing unit is trained using a training set comprising a set of subjects for which emotional state is known. The notification device provides a notification of at least one of the person'"'"'s detected invisible emotional states.
28 Citations
18 Claims
-
1. A system for detecting an emotional state of a person of interest, the system comprising a processing unit and a storage device, the processing unit configurable to:
-
receive an image sequence captured of the person of interest; determine hemoglobin concentration (HC) changes of the person of interest from the image sequence; determine an emotional state associated with the person of interest using a trained classification machine learning model, the trained classification machine learning model receiving the HC changes as input, the training set for the trained classification machine learning model comprising previously determined HC changes from images of subjects with known emotional states; and output the determined emotional state. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A method for detecting an emotional state of a person of interest, the method executed on a processing unit, the method comprising:
-
receiving an image sequence captured of the person of interest; determining hemoglobin concentration (HC) changes of the person of interest from the image sequence; determining an emotional state associated with the person of interest using a trained classification machine learning model, the trained classification machine learning model receiving the HC changes as input, the training set for the trained classification machine learning model comprising previously determined HC changes from images of subjects with known emotional states; and outputting the determined emotional state. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
Specification