User interface for face recognition
View Patent ↗A method of organizing an image collection includes detecting faces in the image collection, extracting features from the detected faces, determining a set of unique faces by analyzing the extracted features, wherein each face in the set of unique faces is believed to be from a different person than the other faces in the set; and displaying the unique faces to a user.
1. A method of organizing an image collection comprising:
a) detecting images in the image collection that contain one or more faces;
b) using a feature extractor to extract local features relating to the appearance of a person from each detected face in the image collection and global features related to camera and capture conditions from each corresponding image, wherein global features include at least one of image capture time, geographic information, flash fire information, and camera model;
c) determining a set of unique faces by analyzing the local and global extracted features, wherein each face in the set of unique faces is believed to be from a different person than the other faces in the set; and
d) displaying the unique faces to a user.
2. The method of claim 1 , further including:
e) the user selecting one of the unique faces using a touch screen, a mouse, audio input, text input, or keyboard input.
3. The method of claim 2 , wherein the user provides a label that is associated with the selected unique face.
4. The method of claim 3 , wherein an image that contains a face similar to the selected unique face is annotated by a provided name.
5. The method of claim 2 , further including selecting one or more unique faces and creating icon corresponding to such selected faces that are useable for future searching.
6. The method of claim 2 wherein there are two or more icons of the same face and such icons are combined into a single icon.