Method and system for image processing
Provided is an image processing method and system. More particularly, provided are an image processing method and system that may map a facial expression of a user, a specific event, etc., to a character in real time by mapping an object such as a face of a user included in an input image to a virtual object such as a face of a specific character, and by applying an event corresponding to a combination of components defined for the object to the virtual object, and a non-transitory computer-readable recording medium that, when executed by a processor, cause the processor to implement the image processing method in conjunction with a computer device.
1. A non-transitory computer-readable recording medium storing instructions that, when executed by a processor, cause the processor to implement an image processing method in conjunction with a computer, the image processing method comprising:
extracting landmark information of an object included in an input image;
mapping the object included in the input image to a virtual object based on the landmark information, the virtual object being an avatar or a character;
determining values of a plurality of components with respect to the object based on the landmark information;
determining an event corresponding to a combination of the determined values of the plurality of components; and
applying the determined event to the virtual object.
2. The non-transitory computer-readable recording medium of claim 1 , wherein the plurality of components comprises a plurality of landmark components included in the object and a plurality of angular components representing a rotation of the object.
3. The non-transitory computer-readable recording medium of claim 2 , wherein:
the image processing method further comprises setting and managing a plurality of shape values representing two or more different shapes for one or more of the plurality of landmark components; and
the determining a values of the plurality of components comprises determining a shape value corresponding to a shape of a first landmark component as a value of the first landmark component, the first landmark component being one from among the plurality of landmark components, the shape of the first landmark component determined based on the landmark information, the landmark information including a first set of shape values for the first landmark component.
4. The non-transitory computer-readable recording medium of claim 2 , wherein:
the plurality of angular components corresponds to a plurality of rotational axes associated with the object;
the image processing method further comprises setting and managing a plurality of angular values representing two or more different angles for one or more of the plurality of rotational axes; and
the determining a values of the plurality of components comprises,
determining an angle of the object for a first rotational axis among the plurality of rotational axes based on the landmark information, and
determining an angular value corresponding to the determined angle of the object from among the plurality of angular values managed for the first rotational axis as a value of an angular component corresponding to the first rotational axis.
5. The non-transitory computer-readable recording medium of claim 1 , wherein:
the image processing method further comprises managing a plurality of events associated with a plurality of combinations by setting an event for each combination of values associated with the plurality of components; and
the determining an event comprises extracting an event corresponding to the combination of the determined values from among the plurality of events.
6. The non-transitory computer-readable recording medium of claim 1 , wherein the applying the determined event comprises:
loading a motion file corresponding to the determined event; and
sequentially applying motion frames of an animation included in the loaded motion file to frames for displaying the virtual object based on a frame unit.
7. The non-transitory computer-readable recording medium of claim 1 , wherein the image processing method further comprises:
normalizing at least one of a size, a location, or an angle of the object based on the extracted landmark information.
8. The non-transitory computer-readable recording medium of claim 2 , wherein the image processing method further comprises:
correcting coordinates of the landmark components of the object recognized through the landmark information extracted from a current frame of the input image based on the landmark information extracted from a previous frame of the input image.
9. The non-transitory computer-readable recording medium of claim 8 , wherein the correcting comprises correcting the coordinates of the landmark components of the object extracted from the current frame of the input image using a credibility value that is calculated based on a variation between an angle for each rotational axis of the object recognized from the current frame and an angle for each rotational axis of the object recognized from the previous frame.
10. The non-transitory computer-readable recording medium of claim 1 , wherein:
the object comprises a face of a user included in the image input through a camera; and
the virtual object comprises a face of the character to be mapped to the face of the user in real time.
11. The non-transitory computer-readable recording medium of claim 10 , wherein the image processing method further comprises:
measuring a relative value indicating a level at which each eye included in the face of the user is open or closed with respect to a number of consecutive frames of the image, and storing the measured relative value in a buffer;
analyzing the relative value of the number of frames stored in the buffer; and
applying an one-eye motion operation to the face of the character based on results of the analyzing indicating that each eye is open or closed.
12. An image processing method comprising:
extracting landmark information of an object included in an input image;
mapping the object included in the input image to a virtual object based on the landmark information, the virtual object being an avatar or a character;
determining values of a plurality of components with respect to the object based on the landmark information;
determining an event corresponding to a combination of the determined values of the plurality of components; and
applying the determined event to the virtual object.
13. The image processing method of claim 12 , wherein the plurality of components comprises a plurality of landmark components included in the object and a plurality of angular components representing a rotation of the object.
14. The image processing method of claim 13 , further comprises:
setting and managing a plurality of shape values representing two or more different shapes for one or more of the plurality of landmark components, and
the determining values of the plurality of components comprises determining a shape value corresponding to a shape of a first landmark component as a value of the first landmark component, the first landmark component being one from among the plurality of landmark components, the shape of the first landmark component determined based on the landmark information, the landmark information including a first set of shape values for the first landmark component.
15. The image processing method of claim 13 , wherein:
the plurality of angular components corresponds to a plurality of rotational axes associated with the object;
the image processing method further comprises setting and managing a plurality of angular values representing two or more different angles for each of the plurality of rotational axes; and
the determining values of the plurality of components comprises,
determining an angle of the object for a first rotational axis among the plurality of rotational axes based on the landmark information, and
determining an angular value corresponding to the determined angle of the object from among the plurality of angular values managed for the first rotational axis as a value of an angular component corresponding to the first rotational axis.
16. The image processing method of claim 12 , further comprising:
managing a plurality of events associated with a plurality of combinations by setting an event for each combination of values associated with the plurality of components,
wherein the determining an event comprises extracting an event corresponding to the combination of the determined values from among the plurality of events.
17. The image processing method of claim 12 , wherein the applying the determined event comprises:
loading a motion file corresponding to the determined event; and
sequentially applying motion frames of an animation included in the loaded motion file to frames for displaying the virtual object based on a frame unit.
18. The image processing method of claim 13 , further comprising:
correcting coordinates of the landmark components of the object recognized through the landmark information extracted from a current frame of the input image based on the landmark information extracted from a previous frame of the input image.
19. The image processing method of claim 18 , wherein the correcting comprises correcting the coordinates of the landmark components of the object extracted from the current frame of the input image using a credibility value that is calculated based on a variation between an angle for each rotational axis of the object recognized from the current frame and an angle for each rotational axis of the object recognized from the previous frame.