Machine learning enhanced facial recognition
A technique of performing machine learning enhanced facial recognition. The technique includes accessing a facial image for a facial recognition target, performing facial recognition on the facial image, making a prediction regarding facial recognition candidates for the facial recognition target, and indicating a measure of confidence regarding the facial recognition performed on the facial image, with the measure adjusted based on the prediction. The prediction may be made based at least in part on a people model that statistically predicts the facial recognition candidates who may be present at a particular location at a particular time, a period model that predicts one or more times that the facial recognition candidates may be present at a particular location, behavioral data that indicates an intention of the facial recognition candidates to be at a particular location at a particular time, and/or actions such as purchasing tickets or registering for an event.
1. A system that performs machine learning enhanced facial recognition, comprising:
an image capture device;
at least one computing device including at least tangible computing elements that perform steps comprising:
accessing a facial image for a facial recognition target;
performing facial recognition on the facial image;
making a prediction regarding facial recognition candidates for the facial recognition target; and
indicating a measure of confidence regarding the facial recognition performed on the facial image, with the measure adjusted based on the prediction;
wherein the prediction is based at least in part on actions by the facial recognition candidates that indicate an intention to be at a particular location at a particular time, the prediction is based at least in part on behavioral data that indicates an intention of the facial recognition candidates to be at a particular location at a particular time, or the facial recognition is performed using facial images provided by one or more of the facial recognition candidates at the time of purchasing a ticket or registering for an event.
2. A system as in claim 1 , wherein the prediction is based at least in part on the actions by the facial recognition candidates that indicate the intention to be at the particular location at the particular time.
3. A system as in claim 1 , wherein the prediction is based at least in part on the behavioral data that indicates the intention of the facial recognition candidates to be at the particular location at the particular time.
4. A system as in claim 1 , wherein the facial recognition is performed using the facial images provided by the one or more of the facial recognition candidates at the time of purchasing the ticket or registering for the event.
5. A method of performing machine learning enhanced facial recognition, comprising:
accessing a facial image for a facial recognition target;
performing facial recognition on the facial image;
making a prediction regarding facial recognition candidates for the facial recognition target; and
indicating a measure of confidence regarding the facial recognition performed on the facial image, with the measure adjusted based on the prediction;
wherein the prediction is based at least in part on actions by the facial recognition candidates that indicate an intention to be at a particular location at a particular time, the prediction is based at least in part on behavioral data that indicates an intention of the facial recognition candidates to be at a particular location at a particular time, or the facial recognition is performed using facial images provided by one or more of the facial recognition candidates at the time of purchasing a ticket or registering for an event.
6. A method as in claim 5 , wherein the prediction is based at least in part on actions by the facial recognition candidates that indicate the intention to be at the particular location at the particular time.
7. A method as in claim 5 , wherein the prediction is based at least in part on the behavioral data that indicates the intention of the facial recognition candidates to be at the particular location at the particular time.
8. A method as in claim 5 , wherein the facial recognition is performed using the facial images provided by the one or more of the facial recognition candidates at the time of purchasing the ticket or registering for the event.