Image capture system incorporating metadata to facilitate transcoding

1. A method for generating an enhanced compressed digital image, for comprising the steps of:

a) capturing a digital image;

b) generating additional information from a main subject belief map, containing a continuum of belief values, relating to the importance of a photographed subject and its corresponding background regions within the digital image;

b1) extracting regions of homogeneous properties from the digital image;

b2) extracting for each of the regions, at least one structural saliency feature and at least one semantic saliency feature; and

b3) integrating the at least one structural saliency feature and the at least one semantic saliency feature using a probabilistic reasoning engine into an estimate of a belief that each region is the main subject;

c) compressing the digital image to form a compressed digital image;

d) associating the additional information with the compressed digital image to generate the enhanced compressed digital image; and

e) storing the enhanced compressed digital image in a data storage device.

2. The method claimed in claim 1 , wherein the additional information generated in step (b) is further compressed to generate compressed additional information before the associating step.

3. The method claimed in claim 2 , wherein the step of further compressing the additional information employs a lossless compression technique.

4. The method claimed in claim 1 wherein the digital image is one of a sequence of digital motion images.

5. The method claimed in claim 1 wherein the step of compressing the digital image employs JPEG compression technique.

6. The method claimed in claim 1 wherein the step of compressing the digital image employs JPEG 2000 compression technique.

7. The method claimed in claim 1 wherein generating the additional information further comprises the steps of:

b) collecting data from separate sensing elements, wherein all data is collected at the time of capturing the digital image.

8. The method claimed in claim 1 wherein generating the main subject belief map further comprises the steps of:

b4) collecting data from separate sensing elements, wherein all data is collected at the time of capturing the digital image; and

b5) utilizing the collected data for modifying the estimate of the belief that each region is the main subject.

9. The method claimed in claim 1 wherein the step of generating additional information includes the steps of:

a) calculating a representation of a relative strength of high-frequency components in regions of the image; and

b) compressing and encoding the representation of the relative strength of high-frequency components for inclusion with the compressed digital image.

10. The method claimed in claim 1 wherein the step of generating the additional information comprises the steps of:

a) tracking eye movement, during capture, using eye tracking sensors in a camera viewfinder;

b) generating gaze-tracking data from the eye tracking sensors; and

c) encoding the gaze-tracking data.

11. The method claimed in claim 1 wherein the step of generating the additional information comprises the steps of:

a) capturing a depth map of objects in each frame using a depth sensor;

b) generating depth data from the depth sensor; and

c) encoding the depth data.