Estimating aesthetic quality of digital images

1. A method for estimating the aesthetic quality of an input digital image comprising using a digital image processor for performing the following:

a) determining one or more vanishing point(s) associated with the input digital image by automatically analyzing the digital image;

b) computing a compositional model from at least the positions of the vanishing point(s); and

c) producing an aesthetic quality parameter for the input digital image responsive to the compositional model, wherein the aesthetic quality parameter is an estimate for the aesthetic quality of the input digital image.

2. The method of claim 1 wherein the aesthetic quality parameter produced in step c) is further responsive to at least one of the following additional features that are computed from the input digital image: face location, face contrast, face brightness, face size, colorfulness, number of hues, color distribution, sharpness, edge spatial distribution, location of main subject, or size of main subject.

3. The method of claim 1 wherein step c) includes:

i. establishing true aesthetic quality values for each digital image in a training set;

ii. determining one or more vanishing point(s) associated with each digital image in the training set by automatically analyzing the digital images in the training set;

iii. computing compositional models for each digital image in the training set responsive to the one or more vanishing point(s)

iv. using the true aesthetic quality values and the compositional models determined for the training set to train a classifier to predict the aesthetic quality parameter as a function of the compositional model;

v. using the trained classifier to produce the aesthetic quality parameter for the input digital image responsive to the compositional model associated with the input digital image.

4. The method of claim 1 further including the step of suggesting possible uses for images having high aesthetic quality.

5. The method of claim 4 wherein the possible uses include one or more of the following: printing, sharing, displaying or using to produce specialty photographic products.

6. The method of claim 1 further including analyzing a set of input digital images for a particular photographer and suggesting ways that the particular photographer and can improve the aesthetic quality of his/her digital images.

7. The method of claim 1 wherein aesthetic quality parameters are determined for a set of digital images captured by a particular photographer, each digital image having an associated capture time, and further including producing an indication of the particular photographer's progress toward producing images with a high level of aesthetic quality using the aesthetic quality parameters for each digital image in the set and the corresponding associated capture times.

8. The method of claim 7 wherein the indication of the photographer's progress is a progress score.

9. The method of claim 7 wherein the indication of the photographer's progress is a display of the aesthetic quality via a graphical user interface that displays images.

10. The method of claim 7 wherein the indication of the photographer's progress is a plot of aesthetic quality over time.

11. The method of claim 1 wherein aesthetic quality parameters are determined for sets of digital images captured by a plurality of photographers, and further including providing a comparison between the aesthetic quality distributions of the photographers.

12. The method of claim 1 wherein the input digital image is captured using a digital camera and further including providing feedback regarding the aesthetic quality of the input digital image to the photographer by displaying a quality indicator on a user interface of the digital camera.

13. The method of claim 1 wherein the digital image is a frame of video sequence.

14. The method of claim 1 wherein the digital image is provided using a digital communications network.