Method for making montage based on dialogue and apparatus using the same

1. A method for making a montage based on a dialogue, comprising:

extracting a feature for making a montage based on a dialogue between at least one inquirer and at least one respondent;

generating a facial feature image based on the feature; and

making a montage based on the facial feature image;

wherein generating the facial feature image comprises:

retrieving the facial feature image from a facial feature image database in consideration of metadata corresponding to the feature;

generating a new facial feature image corresponding to the feature when a facial feature image tagged with the metadata is not present in the facial feature image database; and

displaying the montage on a display shared between the at least one inquirer and the at least one respondent; and

wherein generating the new facial feature image comprises generating the new facial feature image by applying a Generative Adversarial Network (GAN) to the facial feature image database.

2. The method of claim 1 , further comprising:

determining whether there are missing features based on the dialogue; and

generating an additional question for getting an additional feature when it is determined that there are missing features.

3. The method of claim 2 , wherein the montage is made by combining multiple facial feature images generated based on multiple features.

4. The method of claim 1 , wherein extracting the feature comprises extracting a keyword corresponding to the feature by analyzing an answer provided by the at least one respondent, corresponding to a purport of a question asked by the at least one inquirer, and taking the keyword as metadata.

5. The method of claim 1 , wherein generating the new facial feature image comprises tagging the new facial feature image with the metadata and storing the new facial feature image tagged with the metadata in the facial feature image database.

6. The method of claim 1 , further comprising:

creating metadata by analyzing characteristics of each of multiple 2D or 3D facial feature images; and

configuring the facial feature image database by tagging each of the multiple facial feature images with metadata corresponding thereto.

7. The method of claim 1 , wherein the feature corresponds to characteristic information of each of facial components constituting the montage.

8. The method of claim 1 , wherein displaying the montage comprises displaying at least one recommended montage as well as the montage.

9. An apparatus for making a montage based on a dialogue, comprising:

a processor for extracting a feature for making a montage based on a dialogue between at least one inquirer and at least one respondent, generating a facial feature image based on the feature, and making a montage based on the facial feature image; and

a facial feature image database for managing the facial feature image;

wherein

the processor retrieves the facial feature image from the facial feature image database in consideration of metadata corresponding to the feature, and when a facial feature image tagged with the metadata is not present in the facial feature image database, the processor generates a new facial feature image corresponding to the feature;

the processor displays the montage on a display shared between the at least one inquirer and the at least one respondent; and

the processor generates the new facial feature image by applying a Generative Adversarial Network (GAN) to the facial feature image database.

10. The apparatus of claim 9 , wherein the processor determines whether there are missing features based on the dialogue, and generates an additional question for getting an additional feature when it is determined that there are missing features.

11. The apparatus of claim 9 , wherein the montage is made by combining multiple facial feature images generated based on multiple features.

12. The apparatus of claim 9 , wherein the processor extracts a keyword corresponding to the feature by analyzing an answer provided by the at least one respondent, corresponding to a purport of a question asked by the at least one inquirer, and takes the keyword as metadata.

13. The apparatus of claim 9 , wherein the processor tags the new facial feature image with the metadata and stores the new facial feature image tagged with the metadata in the facial feature image database.

14. The apparatus of claim 9 , wherein the facial feature image database is configured by tagging each of multiple 2D or 3D facial feature images with metadata created by analyzing characteristics of the facial feature image.