System and method for indoor-outdoor scene classification
Embodiments include a scene classification system and method. In one embodiment, a method includes forming a first plurality of image features from an input image, processing the first plurality of image features in the first scene classifier.
1. A method of classifying a scene depicted in an digital image, the method comprising:
receiving an input image in a first scene classifier;
deriving a first image feature based on calculating an average color value of each of a plurality of a region of the input image, and forming a color histogram;
deriving a second image feature based on calculating an average hue value of each of the plurality of the region of the input image, and forming a color-position histogram; and
classifying the input image as an indoor scene or an outdoor scene based on the color histogram, the color-position histogram, or combination thereof for displaying on a device.
2. The method of claim 1 , wherein the first image feature is in an LUV color space.
3. The method of claim 1 , wherein the second image feature is in a HSV color space.
4. The method of claim 1 , further comprising deriving a third image feature based on a DCT coefficient.
5. The method of claim 1 , further comprising forming a third image feature based on dividing an intensity component of the input image into a plurality of a region.
6. A system for classifying a scene depicted in a digital image, the system comprising:
a processor is configured to receive an input image in a first scene classifier;
a memory having code executable by the processor is configured to:
derive a first plurality of an image feature from the input image;
derive a first feature based on calculating an average color value of each of a plurality of a region of the input image, and forming a color histogram;
derive a second image feature based on calculating an average hue value of each of the plurality of the region of the input image, and forming a color-position histogram;
process the first plurality of the image feature in a color position histogram in the first scene classifier; and
classify the input image as an indoor scene or an outdoor scene based on the color histogram, the color-position histogram, or combination thereof for displaying on a device.
7. The system of claim 6 , wherein one of the plurality of the image feature includes a histogram of edge orientations.
8. The system of claim 6 wherein one of the plurality of the image feature includes an entropy of the edge orientations.
9. The system of claim 6 wherein the processor is configured to determine a joint user profile for personalizing a multimedia experience.
10. The system of claim 6 wherein the processor is configured to derive a second plurality of the image features from the input image in a second scene classifier comprises obtaining the first plurality of the image feature from the first scene classifier.
11. The system of claim 6 , wherein the first plurality of the image feature comprises at least one of a same set of image features as a second plurality of the image feature.
12. The system of claim 6 , wherein the plurality of the image feature are each based on feature information contained in pixels of the input image, comprising at least one of a color, an entropy, an edge, and discrete cosine transform (DCT) information.
13. The system of claim 6 , wherein forming a second plurality of the image feature from the input image in the second scene classifier comprises obtaining the first plurality of the image features from the first scene classifier.
14. The system of claim 6 , wherein the processor is configured to form a third image feature based on dividing an intensity component of the input image into a plurality of a region.