Method and apparatus for providing classification of quality characteristics of images

1. A method comprising:

retrieving, by a processor, digital data associated with an image utilized in a map application or navigation system, wherein the image is associated with metadata providing at least information about a geo-location where the image was captured and type of equipment used to capture the image;

selecting, by the processor, a region of interest in the image based on a subset of the digital data associated with a section of the image, wherein the selecting includes excluding portions of the image including features or objects that are of no or low interest;

processing, by the processor, of the subset of the digital data to determine one or more quality attributes associated with the region of interest, wherein the quality attributes are based, at least in part, on exposure-sensitive attributes including highlights, shadows, dark pixels, washed-out pixels, under-saturated pixels, over-saturated pixels, or a combination thereof, and wherein the exposure-sensitive attributes are represented by features within the region of interest;

comparing the one or more quality attributes to one or more criteria;

generating one or more classifications for the image based, at least in part, on the comparison; and

determining the one or more criteria based, at least in part, on one or more other classifications associated with one or more other images and one or more user inputs, wherein the one or more user inputs include subjective exposure level information of the one or more other images previously determined by one or more human inspectors.

2. The method of claim 1 , further comprising:

determining the region of interest based, at least in part, on one or more parameters associated with the image.

3. The method of claim 1 , further comprising:

training one or more classification models based, at least in part, on the one or more classifications; and

classifying one or more other images based, at least in part, on the one or more classification models.

4. The method of claim 1 , further comprising:

classifying pixels in the region of interest as dark pixels based, at least in part, on a percentage of gray pixels being less than a threshold.

5. The method of claim 1 , further comprising:

classifying pixels in the region of interest as washed-out pixels based, at least in part, on a percentage of gray pixels being greater than a threshold.

6. The method of claim 1 , further comprising:

classifying pixels in the region of interest as under-saturated pixels based, at least in part, on a percentage of saturation pixels being less than a threshold.

7. The method of claim 1 , further comprising:

classifying pixels in the region of interest as over-saturated pixels based, at least in part, on a percentage of saturation pixels being greater than a threshold.

8. The method of claim 1 , wherein the one or more classifications include one or more scores associated with a normal exposure, over exposure, under exposure, or a combination thereof.

9. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following:

retrieve digital data associated with an image utilized in a map application or navigation system, wherein the image is associated with metadata providing at least information about a geo-location where the image was captured and type of equipment used to capture the image;

select a region of interest in the image based on a subset of the digital data associated with a section of the image, wherein the selecting includes excluding portions of the image including features or objects that are of no or low interest;

process the subset of the digital data to determine one or more quality attributes associated with the region of interest, wherein the quality attributes are based, at least in part, on exposure-sensitive attributes including highlights, shadows, dark pixels, washed-out pixels, under-saturated pixels, over-saturated pixels, or a combination thereof, and wherein the exposure-sensitive attributes are represented by features within the region of interest;

compare the one or more quality attributes to one or more criteria;

generate one or more classifications for the image based, at least in part, on the comparison; and

determine the one or more criteria based, at least in part, on one or more other classifications associated with one or more other images and one or more user inputs, wherein the one or more user inputs include subjective exposure level information of the one or more other images previously determined by one or more human inspectors.

10. The apparatus of claim 9 , wherein the apparatus is further caused to:

determine the region of interest based, at least in part, on one or more parameters associated with the image.

11. The apparatus of claim 9 , wherein the apparatus is further caused to:

train one or more classification models based, at least in part, on the one or more classifications; and

classify one or more other images based, at least in part, on the one or more classification models.

12. The apparatus of claim 9 , wherein the apparatus is further caused to:

classify pixels in the region of interest as dark pixels based, at least in part, on a percentage of gray pixels being less than a threshold; and

classify pixels in the region of interest as washed-out pixels based, at least in part, on a percentage of gray pixels being greater than a threshold.

13. The apparatus of claim 9 , wherein the apparatus is further caused to:

classify pixels in the region of interest as under-saturated pixels based, at least in part, on a percentage of saturation pixels being less than a threshold; and

classify pixels in the region of interest as over-saturated pixels based, at least in part, on a percentage of saturation pixels being greater than a threshold.

14. A computer-readable non-transitory storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform:

retrieve digital data associated with an image utilized in a map application or navigation system, wherein the image is associated with metadata providing at least information about a geo-location where the image was captured and type of equipment used to capture the image;

select a region of interest in the image based on a subset of the digital data associated with a section of the image, wherein the selecting includes excluding portions of the image including features or objects that are of no or low interest;

process the subset of the digital data to determine one or more quality attributes associated with the region of interest, wherein the quality attributes are based, at least in part, on exposure-sensitive attributes including highlights, shadows, dark pixels, washed-out pixels, under-saturated pixels, over-saturated pixels, or a combination thereof, and wherein the exposure-sensitive attributes are represented by features within the region of interest;

compare the one or more quality attributes to one or more criteria;

generate one or more classifications for the image based, at least in part, on the comparison; and

determine the one or more criteria based, at least in part, on one or more other classifications associated with one or more other images and one or more user inputs, wherein the one or more user inputs include subjective exposure level information of the one or more other images previously determined by one or more human inspectors.

15. The computer-readable non-transitory storage medium of claim 14 , wherein the apparatus is further caused to perform:

train one or more classification models based, at least in part, on the one or more classifications; and

classify one or more other images based, at least in part, on the one or more classification models.