User identification system and method for identifying user

• US 20130243242A1
• Filed: 08/15/2012
• Published: 09/19/2013
• Est. Priority Date: 03/16/2012
• Status: Active Grant

• Current Assignee: PixArt Imaging Incorporated
• Original Assignee: PixArt Imaging Incorporated
• Inventors: Gu, Ren-Hau, Wu, Chih-Yen
• Granted Patent: US 9,280,714 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

The present invention discloses an identification system which includes an image sensor, a storage unit and a comparing unit. The image sensor captures a plurality of images of the motion trajectory generated by a user at different timings. The storage unit has stored motion vector information of a group of users including or not including the user generating the motion trajectory. The comparing unit compares the plurality of images with the motion vector information to identify the user. The present invention also provides an identification method.

Claims

1. An identification system for identifying a user by receiving a motion trajectory generated by the user, the identification system comprising:

an image sensor for capturing a plurality of images of the motion trajectory generated by the user at different timings;

a storage unit for storing motion vector information of a group of users including or not including the user generating the motion trajectory; and

a comparing unit for comparing the plurality of images with the motion vector information to identify the user.

2. The identification system of claim 1, wherein the motion trajectory includes a plurality of motion vectors indicating sequential movements.

3. The identification system of claim 2, wherein each of the motion vectors includes distance information and angle information.

4. The identification system of claim 1, further comprising:

a processing unit for generating the motion vector information of the group of users according to the motion trajectories which are generated in advance by the group of users.

5. The identification system of claim 4, wherein each of the motion trajectories generated by the group of users comprises a plurality of motion vectors indicating sequential movements.

6. The identification system of claim 5, wherein each of the motion vectors generated by the group of users includes distance information and angle information.

7. The identification system of claim 6, wherein the processing unit statistically classifies the distance information and the angle information so as to obtain the individual motion vector information for each user in the group of users.

8. The identification system of claim 4, wherein the processing unit includes a Support Vector Machine (SVM) classifier, a Principal Component Analysis (PCA) classifier or a Neural Networks (NN) classifier.

9. The identification system of claim 1, wherein the motion trajectory is a motion trajectory of a part of a hand of the user.

10. The identification system of claim 1, further comprising a light transmissive element disposed within a sensible area of the image sensor, wherein the user contacts the light transmissive element to generate the motion trajectory.

11. The identification system of claim 10, further comprising:

a light emitting element for providing a light beam, which is disposed at the same side as the image sensor with respect to the light transmissive element, wherein when the user contacts the light transmissive element, the image sensor receives the light beam reflected by the user to capture the plurality of images of the motion trajectory generated by the user at different timings.

12. An identification method, comprising:

capturing a plurality of images of a motion trajectory generated by a user; and

comparing the plurality of images with pre-stored motion vector information to identify the user.

13. The identification method of claim 12, wherein before capturing the plurality of images of the motion trajectory generated by the user, the identification method further comprising:

receiving a plurality of images of the motion trajectories generated by a group of users including or not including the user generating the motion trajectory; and

generating the motion vector information including individual motion vector information corresponding to each user in the group of users.

14. The identification method of claim 13, wherein each of the motion trajectories generated by the group of users comprises a plurality of motion vectors indicating sequential movements.

15. The identification method of claim 14, wherein each of the motion vectors generated by the group of users includes distance information and angle information.

16. The identification method of claim 15, further comprising:

statistically classifying the distance information and the angle information so as to obtain the individual motion vector information for each user in the group of users.

17. The identification method of claim 12, wherein before capturing the plurality of images of the motion trajectory generated by the user, the identification method further comprising:

judging whether the user contacts an identification system according to a light intensity variation.

18. An identification system for identifying a user by receiving a motion trajectory generated by the user, the identification system comprising:

a trajectory detection unit for detecting a motion trajectory generated by the user;

a storage unit for storing motion vector information of a group of users including or not including the user generating the motion trajectory; and

a comparing unit for comparing the motion trajectory with the motion vector information to identify the user.

19. The identification system of claim 18, wherein the motion trajectory includes a plurality of motion vectors indicating sequential movements.

20. The identification system of claim 19, wherein each of the motion vectors includes distance information and angle information.

21. The identification system of claim 18, further comprising:

a processing unit for generating motion vector information of the group of users according to the motion trajectories which are generated in advance by the group of users.

22. The identification system of claim 21, wherein each of the motion trajectories generated by the group of users comprises a plurality of motion vectors indicating sequential movements.

23. The identification system of claim 22, wherein each of the motion vectors generated by the group of users includes distance information and angle information.

24. The identification system of claim 23, wherein the processing unit statistically classifies the distance information and the angle information so as to obtain the individual motion vector information for each user in the group of users.

25. The identification system of claim 21, wherein the processing unit includes a Support Vector Machine (SVM) classifier, a Principal Component Analysis (PCA) classifier or a Neural Networks (NN) classifier.

26. The identification system of claim 18, wherein the motion trajectory is a motion trajectory of a part of a hand of the user.

27. The identification system of claim 18, wherein the trajectory detection unit includes a touch panel.