Systems and Methods for Image Editing

摘要

Various embodiments are disclosed for image editing. A frame is obtained from a frame sequence depicting at least one individual, and facial characteristics in the frame are analyzed. A utilization score is assigned to the frame based on the detected facial characteristics, and a determination of whether to utilize the frame is made based on the utilization score. A completeness value is assigned, and a determination is made based on the completeness value of whether to repeat the steps above for an additional frame in the frame sequence based on the completeness value. Regions from the frames are combined to generate a composite image.

主权项

1. A method for editing images in a frame sequence, comprising:
(a) obtaining, by an image editing system, a frame from the frame sequence depicting at least one individual; (b) detecting, by the image editing system, a presence of at least one face region in the frame; (c) detecting, by the image editing system, a presence of at least one smile in the frame; (d) detecting, by the image editing system, a presence of at least one set of blinking eyes in the frame; (e) assigning a utilization score based on detection of smiles and detection of blinking eyes; (f) determining whether to utilize the frame based on the utilization score; (g) assigning a completeness value; determining whether to repeat steps (a)-(g) for an additional frame in the frame sequence based on the completeness value; and combining the face regions from the utilized frames to generate a composite image.