Imaging workflow using facial and non-facial features
A method for determining an impact score for a digital image includes providing the digital image wherein the digital image includes faces; using a processor to determine an image feature for the faces; using the processor to compute an object impact score for the faces, wherein the object impact score is based at least upon one of the determined image features; weighting the object impact score for the faces based on one of the determined image features for a face; using the processor to compute an impact score for the digital image by combining the weighted object impact scores for the faces in the image; and storing the computed impact score in a processor accessible memory.
1. A method of capturing digital images, comprising:
a camera defining an image view of a scene;
detecting, in the image view of the scene, a human face;
computing a facial quality parameters score for the human face based on an evaluation of facial quality parameters;
detecting, in the image view of the scene, a human body;
computing a body quality parameters score for the human body based on an evaluation of body quality parameters;
detecting, in the image view of the scene, a non-human object;
computing an object quality parameters score for the non-human object based on an evaluation of object quality parameters;
determining whether the facial quality parameters score, the body quality parameters score, and the object quality parameters score each meet or exceed a pre-established threshold score; and
capturing a digital image of the scene when the facial quality parameters score, the body quality parameters score, and the object quality parameters score each meet or exceed the pre-established threshold score.
2. The Method of claim 1 , wherein the facial quality parameters comprise one or more parameters selected from the group consisting of: face size, face expression, and eye blink.
3. The method of claim 1 , wherein the body quality parameters comprise one or more parameters selected from the group consisting of: body size, body pose, and clothing type.
4. The method of claim 1 , wherein the object quality parameters comprise one or more parameters selected from the group consisting of: object size, object color, and object location in the scene.
5. The method of claim 1 , further comprising using a Bayes net reasoning engine to generate the facial quality parameters, the body quality parameters, and the object quality parameters through a classification process.
6. The method of claim 1 , further comprising determining the facial quality parameters, the body quality parameters, and the object quality parameters using one or more of the following classification methods: support vector machines, AdaBoost, linear discriminant analysis, artificial neural networks, non-parametric classification, or tree-structured classification.
7. The method of claim 1 , further comprising suggesting uses for the captured digital image based on the facial quality parameters score, the body quality parameters score, and the object quality parameters score.
8. The method of claim 7 , wherein suggesting uses for the captured digital image comprises suggesting a printing action, a sharing action, or a display action.
9. The method of claim 1 , wherein computing the facial quality parameters score, computing the body quality parameters score, and computing the object quality parameters score occur continuously as the scene changes and until the digital image of the scene is captured.
10. The method of claim 1 , further comprising the camera projecting an audio instruction or a video instruction to alter the scene to enhance one or more of the facial quality parameters score, the body quality parameters score, and the object quality parameters score.
11. The method of claim 1 , wherein the facial quality parameters are inferred from data associated with images in a preexisting collection of images.
12. The method of claim 1 , wherein the body quality parameters are inferred from data associated with images in a preexisting collection of images.
13. The method of claim 1 , wherein the object quality parameters are inferred from data associated with images in a preexisting collection of images.