Generating content data for a video file

摘要

A method for generating content data for a video file (200) is provided. The video file (200) comprises a video sequence and the content data (201) for characterizing the video sequence. According to the method, at least one face containing image (204, 205, 207, 209, 212) is determined by scanning at least a part of the video sequence for face containing images. Each face containing image contains at least one representation of a face. Based on the determined face containing image a picture containing the face is generated and assigned to the content data (201) of the video file (200).

主权项

1. A method for generating content data for a video file, the video file comprising a video sequence and the content data for characterizing the video sequence, wherein the method comprises the steps:
determining at least one face containing image by scanning at least a part of the video sequence for face containing images, each face containing image containing at least one representation of a face; generating at least one picture containing the face based on the determined at least one face containing image; cropping the at least one picture by removing an area of the picture which does not contain the representation of the face; and assigning the at least one picture to the content data of the video file, wherein the step of generating at least one picture comprises: determining for each face containing image a percentage area covered by the representation of the face, the percentage area indicating a relative amount of area of the image covered by the representation of the face as compared to an entire area of the image; and generating the at least one picture based on the determined at least one face containing image and on the corresponding percentage area.