Automatic generation of a photo guide
View Patent ↗An apparatus, method and an image quality guide document are disclosed. The method includes, for at least one image in a set of images undergoing image enhancement, identifying image quality-related features for the image based on enhancements being applied to the image, identifying image content-related features based on content of the image, determining a content-based degradation of the image based on the identified image quality-related features and image content-related features, and generating a thumbnail of the image. The method further includes generating an image quality guide document for the set of images in which at least one of the thumbnails is associated with a respective text description that is based on the determined content-based degradation.
1. An automated method for generating an image quality guide document comprising:
for at least one image in a set of images undergoing image enhancement:
identifying image quality-related features for the image based on enhancements being automatically applied to the image,
identifying image content-related features based on content of the image,
determining a content-based degradation of the image based on the identified image quality-related features and image content-related features, and
retrieving a photograph shooting tip for correcting the degradation in the image, based on the determined content-based degradation;
generating a thumbnail of each of the images; and
generating an image quality guide document including the thumbnails for the images in the set of images in which at least one of the thumbnails is associated with a respective text description that is based on the determined content-based degradation, the text description including the shooting tip associated with the thumbnail of the image.
2. The method of claim 1 , wherein the method further comprises retrieving a photograph shooting tip for the image based on the content-based degradation, the shooting tip comprising a suggestion for avoiding the content-based degradation in future, and wherein in the image quality guide document, the shooting tip is associated with the thumbnail of the image.
3. The method of claim 1 , wherein the identifying of image quality-related features for the image includes identifying image quality-related features related to a set of predefined quality-related categories.
4. The method of claim 3 , wherein the identifying of image quality-related features includes computing a features vector based on the identified image quality-related features.
5. The method of claim 1 , wherein the identifying of image quality-related features for the image includes examining logs of image enhancements performed.
6. The method of claim 1 , wherein the identifying of image quality-related features includes identifying image enhancements applied to the image for which an identified image quality parameter actuating the enhancement meets a predetermined threshold.
7. The method of claim 1 , wherein the identifying of the image content-related features includes identifying image content-related features related to a set of predefined semantic content based categories.
8. The method of claim 7 , wherein the identifying of image content-related features includes computing a features vector based on the identified content-related features.
9. The method of claim 7 , wherein the content categories include a category selected from the group consisting of winter, indoors, portraits, landscapes, seascapes, urban, night lights, and flowers.
10. The method of claim 1 , wherein the identifying of the image content-related features includes identifying low level features of the image and classifying the image based on the low level features using a classifier which has been trained on images that are each manually assigned to a semantic category selected from a set of predefined semantic content based categories.
11. The method of claim 1 , wherein the determining of the content-based degradation of the image includes combining a first features vector which represents the identified image quality-related features with a second features vector which represents the image content-related features to form a combined vector and inputting the combined vector to a degradation classifier which has been trained on a pool of images which have each been manually classified according to degradation.
12. The method of claim 1 , wherein the text description includes a description of the content-based degradation and a corresponding image enhancement applied.
13. The method of claim 1 , wherein each of a plurality of the thumbnails is associated with a respective text description that is based on its determined content-based degradation.
14. The method of claim 1 , wherein the images in the set comprise photographs.
15. An image quality guide document generated by the method of claim 1 .
16. The method of claim 1 , wherein the thumbnails comprise image data derived from the images.
17. A non-transitory computer program product encoding instructions, which when executed on a computer causes the computer to perform the method of claim 1 .
18. The method of claim 1 , wherein the image quality-related features are selected from the group consisting of image contrast values, saturation, exposure, color balance, brightness, background color, red eye detection, and combinations thereof.
19. An apparatus for generating an image quality guide document for a set of images comprising:
an enhancement detector which outputs image quality-related features for images in the set based on enhancements being applied to the images;
an image content analyzer which outputs image semantic content-related features for images in the set the image content analyzer identifying low level features of the image and classifying the image based on the low level features using a classifier which has been trained on images that are each manually assigned to a semantic category selected from a set of predefined semantic content based categories;
a degradation classifier which receives the output image quality-related features and image semantic content-related features and outputs a content-based degradation for at least one of the images in the set; and
a thumbnail generator which generates thumbnails for images in the set; and
an image quality guide document generator which generates an image quality guide document for the set of images in which at least one of the thumbnails is associated with a respective text description that is based on the determined content-based degradation.
20. An image processing system comprising the apparatus of claim 19 , and an image enhancement module which outputs information to the enhancement module related to enhancements being applied.
21. An image processing method comprising:
applying at least one automated image enhancement to at least one of a set of input images to generate a set of enhanced images including automatically evaluating image quality features for the input image to determine whether the image meets predetermined acceptable values for the image quality features;
identifying image quality-related features for the at least one input image based on a stored log of the at least one applied enhancement;
identifying image content-related features based on content of the at least one image;
generating thumbnails of the images; and
generating an image quality guide document for the set of images in which at least one of the thumbnails is associated with a respective text description that is based on the identified image quality-related features and image content-related features.