Using time in recognizing persons in images
View Patent ↗A method of identifying at least one particular person of interest in a collection of digital images taken over time, includes providing the collection of digital images with each digital image containing one or more persons; storing in a digital database an appearance model having a set of features that are distance measurements associated with facial features of the particular person of interest at an associated time; and providing an individual recognition classifier that uses the appearance model and the associated time to identify the particular person of interest in images from the collection of digital images.
1. A method of identifying a person in a digital image by using a collection of digital images taken over time, comprising:
one or more processors to implement
providing the collection of digital images with each digital image containing one or more persons;
storing in a digital database appearance models having a set of features that are distance measurements associated with facial features of persons of interest each at an associated time;
providing a new digital image of a person of interest and the associated image capture time and the age of the person of interest in the new digital image; and
providing an individual recognition classifier that modifies one or more appearance models to compensate for the difference in time between the times associated with the appearance models and the determined age of the person of interest at the digital image capture time.
2. The method of claim 1 , wherein the distance measurements are ratios or angles associated with distances between facial features.
3. The method of claim 2 , wherein the facial features include eyes, nose, eyebrows, or mouth.
4. The method of claim 1 , wherein a greater number of appearance models is used for children during their growing years.
5. The method of claim 1 , wherein the birth dates of the persons of interest for each appearance model are known, and wherein the individual recognition classifier modifies one or more appearance models to compensate for the age difference between the age of the person of interest in the digital image and the age associated with the appearance models.
6. The method of claim 1 further including at least two appearance models with different associated times.
7. The method of claim 1 , wherein the features include the birth date of the particular person of interest.
8. The method of claim 1 , wherein the associated time is either calendar date or age of the particular person of interest.
9. The method of claim 1 , further including at least two appearance models with different associated times, wherein the appearance model with the associated time closest to the image capture time is used by the individual recognition classifies to identify the particular person of interest.
10. The method of claim 1 , wherein the appearance model is modified to produce an age specific appearance model that is used by the individual recognition classifier to identify the particular person of interest.
11. The method of claim 1 , further including at least two appearance models with different associated times, wherein an age specific appearance model is produced from the at least two appearance models, and wherein the age specific appearance model is used by the individual recognition classifies to identify the particular person of interest.