Identifying objects in an image

1. A method for identifying objects in an image, the method comprising:

receiving, by a computer, an image;

identifying, by the computer, one or more first objects in the image based on information in a first database of objects, wherein one or more second objects in the image are unidentified based on the information in the first database of objects;

identifying, by the computer, one or more salient objects in the image based on execution of a saliency algorithm;

determining, by the computer, a generic location for the image, based on the one or more identified salient objects and information in a second database that associates objects with generic locations; and

identifying, by the computer, the one or more second objects, based on the determined generic location for the image, wherein identifying the one or more second objects comprises:

accessing, by the computer, a third database that defines a set of known objects for each of a list of generic locations;

increasing, by the computer, an assigned likelihood for a second object of the one or more second objects if the second object is in the set of known objects for the determined generic location for the image; and

identifying, by the computer, the second object if the increased assigned likelihood is greater than a threshold.

2. A method in accordance with claim 1 , wherein identifying an object of the one or more first objects in the image comprises:

identifying, by the computer, features of the object;

identifying the object if a number of identified features of the object is above a predetermined threshold value; and

assigning a likelihood to a semantic label for the object based on the identified features.

3. A method in accordance with claim 1 , wherein the saliency algorithm is selected from the group consisting of image segmentation and saliency maps.

4. A method in accordance with claim 1 , wherein determining a generic location for the image based on the identified salient objects comprises:

accessing, by the computer, the second database that associates objects with generic locations, wherein the generic locations in the second database includes generic location likelihoods for the identified salient objects;

summing, by the computer, the generic location likelihoods for the identified salient objects; and

selecting, by the computer, the general location with a highest total of summed generic location likelihoods for the identified salient objects.

5. A method in accordance with claim 1 , further comprising:

providing, by the computer, an output specifying the determined generic location for the image, the identified first objects, the identified second objects, and an assigned likelihood for each of the identified first objects and identified second objects, the assigned likelihood defining a probability that the respective identified first object or identified second object is present in the image.

6. A computer system for identifying objects in an image, the computer system comprising:

one or more processors;

one or more computer readable storage media; and

program instructions stored on at least one of the one or more computer readable storage media, which when executed cause at least one of the one or more processors to perform a method comprising:

receiving, by a computer, an image;

identifying, by the computer, one or more first objects in the image based on information in a first database of objects, wherein one or more second objects in the image are unidentified based on the information in the first database of objects;

identifying, by the computer, one or more salient objects in the image based on execution of a saliency algorithm;

determining, by the computer, a generic location for the image, based on the one or more identified salient objects and information in a second database that associates objects with generic locations; and

identifying, by the computer, the one or more second objects, based on the determined generic location for the image, wherein identifying the one or more second objects comprises:

accessing, by the computer, a third database that defines a set of known objects for each of a list of generic locations;

increasing, by the computer, an assigned likelihood for a second object of the one or more second objects if the second object is in the set of known objects for the determined generic location for the image; and

identifying, by the computer, the second object if the increased assigned likelihood is greater than a threshold.

7. A computer system in accordance with claim 6 , wherein identifying an object of the one or more first objects in the image comprises:

identifying, by the computer, features of the object;

identifying the object if a number of identified features of the object is above a predetermined threshold value; and

assigning a likelihood to a semantic label for the object based on the identified features.

8. A computer system in accordance with claim 6 , wherein the saliency algorithm is selected from the group consisting of image segmentation and saliency maps.

9. A computer system in accordance with claim 6 , wherein determining a generic location for the image based on the identified salient objects comprises:

accessing, by the computer, the second database that associates objects with generic locations, wherein the generic locations in the second database includes generic location likelihoods for the identified salient objects;

summing, by the computer, the generic location likelihoods for the identified salient objects; and

selecting, by the computer, the general location with a highest total of summed generic location likelihoods for the identified salient objects.

10. A computer system in accordance with claim 6 , wherein the method further comprises:

providing, by the computer, an output specifying the determined generic location for the image, the identified first objects, the identified second objects, and an assigned likelihood for each of the identified first objects and identified second objects, the assigned likelihood defining a probability that the respective identified first object or identified second object is present in the image.

11. A computer program product for identifying objects in an image, the computer program product comprising:

one or more non-transitory computer readable storage media and program instructions stored on at least one of the one or more non-transitory computer readable storage media, the program instructions, when executed by a computer, cause the computer to perform a method comprising:

receiving, by a computer, an image;

identifying, by the computer, one or more first objects in the image based on information in a first database of objects, wherein one or more second objects in the image are unidentified based on the information in the first database of objects;

identifying, by the computer, one or more salient objects in the image based on execution of a saliency algorithm;

determining, by the computer, a generic location for the image, based on the one or more identified salient objects and information in a second database that associates objects with generic locations; and

identifying, by the computer, the one or more second objects, based on the determined generic location for the image, wherein identifying the one or more second objects comprises:

accessing, by the computer, a third database that defines a set of known objects for each of a list of generic locations;

increasing, by the computer, an assigned likelihood for a second object of the one or more second objects if the second object is in the set of known objects for the determined generic location for the image; and

identifying, by the computer, the second object if the increased assigned likelihood is greater than a threshold.

12. A computer program product in accordance with claim 11 , wherein identifying an object of the one or more first objects in the image comprises:

identifying, by the computer, features of the object;

identifying the object if a number of identified features of the object is above a predetermined threshold value; and

assigning a likelihood to a semantic label for the object based on the identified features.

13. A computer program product in accordance with claim 11 , wherein the saliency algorithm is selected from the group consisting of image segmentation and saliency maps.

14. A computer program product in accordance with claim 11 , wherein determining a generic location for the image based on the identified salient objects comprises:

accessing, by the computer, the second database that associates objects with generic locations, wherein the generic locations in the second database includes generic location likelihoods for the identified salient objects;

summing, by the computer, the generic location likelihoods for the identified salient objects; and

selecting, by the computer, the general location with a highest total of summed generic location likelihoods for the identified salient objects.

15. A computer program product in accordance with claim 11 , wherein the method further comprises:

providing, by the computer, an output specifying the determined generic location for the image, the identified first objects, the identified second objects, and an assigned likelihood for each of the identified first objects and identified second objects, the assigned likelihood defining a probability that the respective identified first object or identified second object is present in the image.