Application US20200319706

SYSTEM AND METHOD FOR DETECTING INVISIBLE HUMAN EMOTION IN A RETAIL ENVIRONMENT
[+] Show Details

US20200319706

1. A system for determining probability for a state of human emotion among a set of identifiable states of human emotion from a digital image sequence of a person in a retail environment, the system comprising: (3) (2)

a computer-readable memory comprising the digital image sequence, the digital image sequence being of light re-emitted from the skin of the person before and during viewing of a product; and

a processing unit comprising one or more processors in communication with the computer-readable memory, the image processing unit executable to: determine, using a first machine learning model trained with a hemoglobin concentration (HC) training set, HC changes of the person using bit values from each bitplane of images in the captured image sequence, the HC training set comprising bit values from each bitplane of images captured from one or more people while such people experience a known state of emotion; and

determine a measure of probability, using a second machine learning model trained with a state training set, for the emotional state of the person against each of the set of identifiable states of human emotion, the state training set obtained by receiving bit values from each bitplane of images representing HC changes determined by the first machine learning model.

2. The system of claim 1, wherein determining the measure of probability, using the second machine learning model trained with the state training set, for the emotional state of the person further comprises determining a normalized intensity measure for the emotional state. (0)

3. The system of claim 1, wherein the person views the product before and during a point of sale event comprising a price display device displaying a price. (2) (0)

8. The system of claim 1, further comprising outputting of the detected emotional state with the highest measure of probability to a display. (0)

9. A method for determining probability for a state of human emotion among a set of identifiable states of human emotion from a digital image sequence of a person in a retail environment, the digital image sequence being of light re-emitted from the skin of the person before and during viewing of a product, the method comprising: (3) (2)

determining, using a first machine learning model trained with a hemoglobin concentration (HC) training set, HC changes of the person using bit values from each bitplane of images in the captured image sequence, the HC training set comprising bit values from each bitplane of images captured from one or more people while such people experience a known state of emotion; and

determinizing a measure of probability, using a second machine learning model trained with a state training set, for the emotional state of the person against each of the set of identifiable states of human emotion, the state training set obtained by receiving bit values from each bitplane of images representing HC changes determined by the first machine learning model.

10. The method of claim 9, wherein determining the measure of probability, using the second machine learning model trained with the state training set, for the emotional state of the person further comprises determining a normalized intensity measure for the emotional state. (0)

11. The method of claim 9, wherein the person views the product before and during a point of sale event comprising a displaying a price. (3) (0)

15. The method of claim 9, further comprising outputting of the detected emotional state with the highest measure of probability. (0)

View Abstract and Specification Size

PDF with Images and Document Face >

Full Text Publication >

Application US20200319706

SYSTEM AND METHOD FOR DETECTING INVISIBLE HUMAN EMOTION IN A RETAIL ENVIRONMENT

Patent Matrix® Search