Methods and apparatus for suggesting and/or associating tags corresponding to identified image content and/or storing said image content in association with tags to facilitate retrieval and use
Methods and apparatus for using one or more feature recognition system(s) to identify features in a scanned image and to associate tags with identified features are described. Probabilities of a feature being present are taken into consideration in some embodiments. In various embodiments once a tag has been determined as corresponding to a feature which has been confirmed as being in the scanned image synonyms for the tag word are identified and also associated with the scanned image. By using results of multiple automated feature recognition systems and generating overall probabilities that a feature is present in an image more reliable tagging can be implemented in an automated manner than in system which rely on a single AI system without the need for extensive operator input with respect to identification of all features in the image which are to be tagged.
1. A method of operating a customer premises device to associate tags with a scanned image, the method comprising:
i) generating a confidence level indicating a level of confidence with respect to a first feature being in a scanned image from multiple confidence values;
determining if the confidence level is over an upper confidence level threshold;
automatically associating a word corresponding to the first feature with the scanned image as a first tag when the confidence level is determined to be over the upper confidence level threshold; and
when the confidence level is below the upper confidence level threshold, discarding the first feature or obtaining user input on whether the word corresponding to the first feature should be used as a tag for the scanned image.
2. The method of claim 1 , further comprising:
determining if the confidence level is below a minimum confidence level threshold, the minimum confidence level threshold corresponding to a lower level of confidence that the first feature is in the scanned image than the upper confidence level threshold;
wherein the confidence level is below the upper confidence level threshold but not below the minimum confidence level threshold; and
wherein the method further comprises:
presenting the word to a user as a suggested tag for the scanned image when the confidence level is below the upper confidence level threshold and not below the minimum threshold level.
3. The method of claim 2 , further comprising:
receiving a user response to the tag suggestion; and
i) discarding the suggested tag when the user does not confirm that the tag should be used for the scanned image; and ii) when user confirms that the tag should be used designating the tag as a confirmed tag and associating the word to be used as a tag with the scanned image.
4. The method of claim 3 , further comprising:
identifying one or more synonyms corresponding to a user confirmed tag or tag automatically associated with the scanned image; and
associating the identified one or more synonyms with the scanned image.
5. The method of claim 4 , further comprising:
receiving a second confidence level indicating a level of confidence with respect to an additional feature being in the scanned image;
determining if the second confidence level is over the upper confidence level threshold; and
associating a word corresponding to the additional feature with the image as a tag when the confidence level is determined to be over the upper confidence level threshold.
6. The method of claim 2 ,
wherein said method includes generating the confidence level indicating the level of confidence with respect to the first feature being in a scanned image, said confidence level being an overall confidence level; and
wherein generating the overall confidence level includes:
receiving a first confidence level indicating a first feature detection system's level of confidence that the first feature is in the scanned image;
receiving a second confidence level indicating a second feature detection system's level of confidence that the first feature is in the scanned image; and
computing the overall confidence level from at least the first confidence level received from the first feature recognition system and the second confidence received from the second feature recognition system.
7. An apparatus comprising:
a receiver;
memory storing a scanned image; and
a processor configured to control the apparatus to:
generate a confidence level indicating a level of confidence with respect to a first feature being in a scanned image from multiple confidence values;
determine if the confidence level is over an upper confidence level threshold;
automatically associate a word corresponding to the first feature with the scanned image as a first tag when the confidence level is determined to be over the upper confidence level threshold; and
when the confidence level is below the upper confidence level threshold, discard the first feature or obtaining user input on whether the word corresponding to the first feature should be used as a tag for the scanned image.
8. The apparatus of claim 7 , wherein the confidence level is below the upper confidence level threshold but not below a minimum confidence level threshold, the minimum confidence level threshold corresponding to a lower level of confidence that the first feature is in the scanned image than the upper confidence level threshold; and
wherein the processor is further configured to control the apparatus to:
determine that the confidence level is below the minimum confidence level threshold; and
present the word to a user as a suggested tag for the scanned image when the confidence level is below the upper confidence level threshold and not below the minimum threshold level.
9. The apparatus of claim 7 , wherein the processor is further configured to control the apparatus to:
receive a user response to the tag suggestion; and
i) discard the suggested tag when the user does not confirm that the tag should be used for the scanned image and ii) when user confirms that the tag should be used, designate the tag as a confirmed tag and associate the word to be used as a tag with the scanned image.
10. The apparatus of claim 9 , wherein the processor is further configured to control the apparatus to:
identify one or more synonyms corresponding to a user confirmed tag or tag automatically associated with the scanned image; and
associate the identified one or more synonyms with the scanned image.
11. The apparatus of claim 10 , wherein the processor is further configured to control the apparatus to:
receive a second confidence level indicating a level of confidence with respect to an additional feature being in the scanned image;
determine if the second confidence level is over the upper confidence level threshold; and
associate a word corresponding to the additional feature with the image as a tag when the confidence level is determined to be over the upper confidence level threshold.
12. The apparatus of claim 11 , wherein said processor is configured to generate the confidence level indicating the level of confidence with respect to the first feature being in the scanned image, said confidence level being an overall confidence level; and
wherein, as part of generating the overall confidence level, the processor:
receives a first confidence level indicating a first feature detection system's level of confidence that the first feature is in the scanned image; and
receives a second confidence level indicating a second feature detection system's level of confidence that the first feature is in the scanned image; and
computes the overall confidence level from at least the first confidence level received from the first feature recognition system and the second confidence received from the second feature recognition system.
13. The apparatus of claim 7 , wherein the processor is configured to:
discard the first feature in response to determining that the confidence level is below a minimum confidence level threshold.
14. The method of claim 1 , further comprising:
determining that the confidence level is below a minimum confidence level threshold; and
discarding the first feature in response to determining that the confidence level is below the minimum confidence level threshold.