System and method for providing an on-chip context aware contact list

Patent metadata

Field	Value
Publication number	US-2017193315-A1
Application number	US-201615061206-A
Country	US
Kind code	A1
Filing date	Mar 4, 2016
Priority date	Dec 30, 2015
Publication date	Jul 6, 2017
Grant date	—

Abstract

A system, method and device for object identification is provided. The method of identifying objects includes, but is not limited to, calculating feature vectors of the object, calculating feature vectors of the object's context and surroundings, combining feature vectors of the object, calculating likelihood metrics of combined feature vectors, calculating verification likelihood metrics against contact list entries, calculating a joint verification likelihood metric using the verification likelihood metrics, and identifying the object based on the joint verification likelihood metric.

First claim

What is claimed is:

1 . A method, comprising:
calculating feature vectors of an object; combining the feature vectors of the object; calculating likelihood metrics of the combined feature vectors; calculating verification likelihood metrics against contact list entries; calculating a joint verification likelihood metric using the verification likelihood metrics; and identifying the object based on the joint verification likelihood metric.

2 . The method of claim 1 , further comprising:
transmitting, using a communications module, at least one of the combined feature vectors, the verification likelihood metrics, the contact list entries, and the joint verification likelihood metric to a server.

3 . The method of claim 1 , wherein when the joint verification likelihood metric satisfies a specified criteria, a user is notified of a corresponding contact list entry.

4 . The method of claim 3 , further comprising updating contact list feature vectors when the user confirms correct identification of the object.

5 . The method of claim 1 , wherein the feature vectors are associated with at least one of an image, a facial image, an image background, a physical sensor, a voice recording, and a biometric sensor.

6 . The method of claim 1 , wherein calculating the joint verification likelihood metric comprises sharing computing parameters including at least one of weights, biases, and non-linear functions.

7 . The method of claim 1 , wherein identification of the object triggers execution of predefined automated actions.

8 . The method of claim 7 , wherein the predefined automated actions includes at least one of setting an alarm, alerting an authority, locking a door, controlling access to a security system, and navigating a vehicle.

9 . The method of claim 1 , wherein combining the feature vectors of the object comprises reducing dimensions of the combined feature vectors.

10 . An electronic device for object identification comprising:
a memory that stores a context aware contact list; an intelligent machine; and a sensor block that acquires sensor data of a surrounding environment, wherein the intelligent machine calculates and combines feature vectors of the sensor data, calculates likelihood metrics of the combined feature vectors, calculates verification likelihood metrics against contact list entries in the context aware contact list, and calculates a joint verification likelihood metric using the verification likelihood metrics.

11 . The electronic device of claim 10 , further comprising a communication module.

12 . The electronic device of claim 11 , wherein the electronic device transmits at least one of the combined feature vectors, the verification likelihood metrics, the contact list entries, and the joint verification likelihood metric to a server.

13 . The electronic device of claim 10 , wherein when the joint verification likelihood metric satisfies a specified criteria, a user is notified of a corresponding contact list entry.

14 . The electronic device of claim 13 , further comprising updating contact list feature vectors when the user confirms correct identification of the object.

15 . The electronic device of claim 10 , wherein the feature vectors are associated with at least one of an image, a facial image, an image background, a physical sensor, a voice recording, and a biometric sensor.

16 . The electronic device of claim 10 , wherein the intelligent machine comprises shared computing parameters including at least one of weights, biases, and non-linear functions.

17 . The electronic device of claim 10 , wherein identification of the object triggers execution of predefined automated actions.

18 . The electronic device of claim 17 , wherein the predefined automated actions includes at least one of setting an alarm, alerting an authority, locking a door, controlling access to a security system, and navigating a vehicle.

19 . The electronic device of claim 10 , wherein combining the feature vectors of the sensor data comprises reducing dimensions of the combined feature vectors.

20 . The electronic device of claim 10 , wherein the contact list entries in the context aware contact list include at least one of a person, a weapon, a vehicle, a vehicle license plate, and an animal.

Assignees

• Samsung Electronics Co Ltd

Inventors

• El-Khamy Mostafa
• Kang Inyup
• Lee Jungwon

Classifications

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title

• G07C9/37

  using biometric data, e.g. fingerprints, iris scans or voice recognition · CPC title

• G08G1/0175

  by photographing vehicles, e.g. when violating traffic rules · CPC title

• G08G1/054

  photographing overspeeding vehicles · CPC title