Generating emoticons based on an image of a face

• US 9,576,175 B2
• Filed: 05/16/2014
• Issued: 02/21/2017
• Est. Priority Date: 05/16/2014
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: Chembula, Ajay B.
• Primary Examiner(s): Patel, Jayesh A
• Application Number:
  US14/279,468
• Publication Number:
  US 20150332088A1
• Time in Patent Office: 1,012 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06V 40/174 Facial expression recognition

Abstract

A device is configured to receive an image of a person. The image may include an image of a face. The device may create an emoticon based on the image of the face. The emoticon may represent an emotion of the person. The device may detect a facial expression of the person at a time that a message is being generated. The device may determine the emotion of the person based on the detected facial expression. The device may identify the emoticon as corresponding to the emotion of the person. The device may add the emoticon to the message based on the emoticon corresponding to the emotion of the person. The device may output the message including the emoticon.

Claims

1. A device, comprising:

one or more processors to;

receive an image of a person,

the image including an image of a face,

the image of the face including an expression of the person;

manipulate the image of the face to generate a plurality of facial images that depict different emotions of the person;

create a plurality of emoticons based on the image of the face and based on the plurality of facial images,

the created plurality of emoticons representing the different emotions of the person, and

each of the created plurality of emoticons being different from other emoticons of the created plurality of emoticons;

monitor facial expressions of the person during a period of time that a message is being generated by the person;

determine a particular facial expression, of the facial expressions, that is detected for a longest time during the period of time and with a highest level of confidence;

determine an emotion of the person based on the particular facial expression;

identify an emoticon, from the created plurality of emoticons, as corresponding to the emotion of the person;

add the emoticon to the message based on the emoticon corresponding to the emotion of the person; and

output the message including the emoticon.

2. The device of claim 1, where the one or more processors are further to:

prompt the person to input an image with the expression of the person; and

receive the image of the person based on prompting the person to input the image with the expression of the person.

3. The device of claim 1, where the one or more processors are further to:

cause a camera to capture the image of the person; and

receive the image of the person from the camera.

4. The device of claim 1, where the one or more processors are further to:

edit the image of the person to isolate the image of the face and remove a background image included in the image of the person.

5. The device of claim 1, where the one or more processors are further to:

change a size and a shape of a facial feature of the image of the face, and

change a color of the image of the face.

6. The device of claim 1, where the one or more processors are further to:

receive a plurality of images of the person with different facial expressions,

the plurality of images of the person including the image of the person; and

create another plurality of emoticons corresponding to the plurality of images of the person,

each of the other created plurality of emoticons being associated with a different facial expression of the different facial expressions.

7. The device of claim 1, where the one or more processors are further to:

manipulate the image of the face by at least one of changing an expression on the face, changing a size of a facial feature, changing a shape of a facial feature, or changing a color of a facial feature; and

create an image, for each different manipulation of the image of the face, as one of the created plurality of emoticons.

8. A non-transitory computer-readable medium storing instructions that,

when executed by one or more processors, cause the one or more processors to:

receive an image of a user, the image including an image of a face, the image of the face including an expression of the user;

manipulate the image of the face to generate a plurality of facial images that depict different emotions of the user;

automatically edit the image of the user to isolate the image of the face;

automatically create a plurality of emoticons based on the image of the face and based on the plurality of facial images, the created plurality of emoticons representing the different emotions of the user, and each of the created plurality of emoticons being different from other emoticons of the created plurality of emoticons;

provide the created plurality of emoticons to a communication application to permit the user to insert one or more of the created plurality of emoticons into a message being generated by the user;

monitor facial expressions of the user during a period of time that the message is being generated by the user;

determine a particular facial expression, of the facial expressions, that is detected for a longest time during the period of time and with a highest level of confidence;

determine an emotion of the user based on the particular facial expression;

identify an emoticon, from the created plurality of emoticons, as corresponding to the emotion of the user;

add the emoticon to the message based on the emoticon corresponding to the emotion of the user; and

output the message including the emoticon.

9. The non-transitory computer-readable medium of claim 8, where the instructions, when executed by the one or more processors, further cause the one or more processors to:

prompt the user to input a particular image with the expression of the user; and

receive the image of the user based on prompting the user to input the particular image with the expression of the user.

10. The non-transitory computer-readable medium of claim 8, where the instructions, when executed by the one or more processors, further cause the one or more processors to:

perform different kinds of manipulation to the image of the face to create the plurality of emoticons;

generate a respective emoticon identifier, for each of the created plurality of emoticons, identifying a kind of emoticon based on a kind of manipulation performed,

the kind of manipulation being included in the different kinds of manipulation;

associate each of the created plurality of emoticons and the respective emoticon identifiers; and

provide the created plurality of emoticons and the respective emoticon identifiers to the communication application.

11. The non-transitory computer-readable medium of claim 8, where the instructions, when executed by the one or more processors, further cause the one or more processors to:

input the created plurality of emoticons to an emoticon palette associated with the communication application.

12. The non-transitory computer-readable medium of claim 8, where at least one of the created plurality of emoticons includes a photograph of the face of the user.

13. A method, comprising:

receiving, by a first device, an image of a user,

the image including an image of a face,

the image of the face including an expression of the user;

manipulating, by the first device, the image of the face to generate a plurality of facial images that depict different emotions of the user;

creating, by the first device, a plurality of emoticons based on the image of the face and based on the plurality of facial images,

the created plurality of emoticons representing the different emotions of the user, and

each of the created plurality of emoticons being different from other emoticons of the created plurality of emoticons;

receiving, by the first device, an input for generating a message to be sent to a second device;

monitoring, by the first device, facial expressions of the user during a period of time that the input is being received;

determining, by the first device, a particular facial expression, of the facial expressions, that is detected for a longest time during the period of time and with a highest level of confidence;

identifying, by the first device, an emotion of the user based on the particular facial expression;

determining, by the first device, an emoticon, of the created plurality of emoticons, to add to the message based on the emotion of the user;

adding, by the first device, the emoticon to the message; and

outputting, by the first device, the message, with the emoticon, for transmission to the second device.

14. The method of claim 13, further comprising:

changing a size and a shape of a facial feature of the image of the face; and

changing a color of the image of the face.

15. The method of claim 13, further comprising:

causing a camera to capture the image of the user; and

receiving the image of the user from the camera.

16. The method of claim 13, further comprising:

detecting a change in the particular facial expression; and

adding the emoticon to the message based on detecting the change in the particular facial expression.

17. The method of claim 13, further comprising:

detecting a sound made by the user; and

identifying the emotion of the user based on the sound and the particular facial expression.

18. The method of claim 13, further comprising:

determining another particular facial expression of the facial expressions; and

identifying the emotion of the user based on the other particular facial expression.

19. The method of claim 13, further comprising:

changing a display option of the message based on the emotion of the user.

20. The method of claim 13, where the message includes at least one of text or a background image, and the method comprises at least one of:

changing a color of the text,

changing a font of the text based on the emotion of the user,

changing a size of the text based on the emotion of the user,

changing an emphasis of the text based on the emotion of the user,

changing a color of the background image based on the emotion of the user, or

changing a pattern of the background image based on the emotion of the user.