Methods and apparatus to determine tags for media using multiple media features
Example methods, apparatus, systems and articles of manufacture are disclosed to determine tags for unknown media using multiple media features. Disclosed examples extract features from audio and image portions of the unknown media. Disclosed examples weight the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, wherein disclosed examples assign a first weight to a first feature extracted by an image-based recognition technology, and assign a second weight, different from the first weight, to a second feature extracted by an audio-based recognition technology. Disclosed examples search a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media. Disclosed examples assign one or more tags from the list of suggested tags to the unknown media.
1. An apparatus to tag unknown media, the apparatus comprising:
memory including computer readable instructions; and
processor circuitry to execute the instructions to at least:
extract features from audio and image portions of the unknown media;
weight the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, a first weight assigned to a first feature extracted by an image-based recognition technology, and a second weight, different from the first weight, assigned to a second feature extracted by an audio-based recognition technology;
search a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media;
when the first feature is included in the combination of the weighted features and is assigned to a first category of a plurality of categories, limit the search in the database to pre-tagged media having category values matching the first category of the first feature; and
assign one or more tags from the list of suggested tags to the unknown media.
2. The apparatus of claim 1 , wherein the processor is to extract the features from the audio portion of the unknown media using at least one of a speech recognition engine, a sound identifier, or a song or tune identifier.
3. The apparatus of claim 1 , wherein the processor is to extract the features from the image portions of the unknown media using at least one of a logo recognition engine, an OCR engine, an object recognition engine, or a graphic recognition engine.
4. The apparatus of claim 1 , wherein the tags are approved by a user.
5. The apparatus of claim 1 , wherein the list of suggested tags includes relevancy scores indicating how relevant the tags are with respect to the unknown media, and the processor is to automatically approve a tag in the list of suggested tags when the relevancy score for the tag is above a threshold relevancy score.
6. An apparatus to tag unknown media, the apparatus comprising:
memory including computer readable instructions; and
processor circuitry to execute the instructions to at least:
extract features from audio and image portions of the unknown media;
weight the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, a highest weight assigned to ones of the features extracted by a logo recognition engine, a next highest weight assigned to ones of the features extracted by an optical character recognition (OCR) engine, a next highest weight assigned to ones of the features extracted by a speech recognition engine, and a lowest weight assigned to ones of the features extracted by a graphic recognition engine;
search a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media; and
assign one or more tags from the list of suggested tags to the unknown media.
7. A tangible computer readable medium comprising computer readable instructions which, when executed, cause a processor to at least:
extract features from audio and image portions of the unknown media;
weight the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, the instructions to cause the processor to assign a first weight to a first feature extracted by an image-based recognition technology, the instructions to cause the processor to assign a second weight, different from the first weight, to a second feature extracted by an audio-based recognition technology;
search a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media, when the first feature is included in the combination of the weighted features and is assigned to a first category of a plurality of categories, the instructions cause the processor to limit the search in the database to pre-tagged media having category values matching the first category of the first feature; and
assign one or more tags from the list of suggested tags to the unknown media.
8. The computer readable medium of claim 7 , wherein the instructions cause the processor to extract the features from the audio portion of the unknown media using at least one of a speech recognition engine, a sound identifier, or a song or tune identifier.
9. The computer readable medium of claim 7 , wherein the instructions cause the processor to extract the features from the image portions of the unknown media using at least one of a logo recognition engine, an OCR engine, an object recognition engine, or a graphic recognition engine.
10. The computer readable medium of claim 7 , wherein the tags are approved by a user.
11. The computer readable medium of claim 7 , wherein the list of suggested tags includes relevancy scores indicating how relevant the tags are with respect to the unknown media, and the instructions cause the processor to automatically approve a tag in the list of suggested tags when the relevancy score for the tag is above a threshold relevancy score.
12. A tangible computer readable medium comprising computer readable instructions which, when executed, cause a processor to at least:
extract features from audio and image portions of the unknown media;
weight the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, the instructions to cause the processor to assign a first weight to a first feature extracted by an image-based recognition technology, the instructions to cause the processor to assign a highest weight to ones of the features extracted by a logo recognition engine, a next highest weight to ones of the features extracted by an optical character recognition (OCR) engine, a next highest weight to ones of the features extracted by a speech recognition engine, and a lowest weight to ones of the features extracted by a graphic recognition engine;
search a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media; and
assign one or more tags from the list of suggested tags to the unknown media.
13. An apparatus to tag unknown media, the apparatus comprising:
means for extracting features from audio and image portions of the unknown media;
means for weighting the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, a first weight assigned to a first feature extracted by an image-based recognition technology, and a second weight, different from the first weight, assigned to a second feature extracted by an audio-based recognition technology;
means for searching a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media;
when the means for extracting assigns the first feature included in the combination of the weighted features to a first category of a plurality of categories, the means for searching is to limit the search in the database to pre-tagged media having category values matching the first category of the first feature; and
means for assigning one or more tags from the list of suggested tags to the unknown media.
14. The apparatus of claim 13 , wherein the means for extracting is to extract the features from the audio portion of the unknown media using at least one of a speech recognition engine, a sound identifier, or a song or tune identifier.
15. The apparatus of claim 13 , wherein the means for extracting is to extract the features from the image portions of the unknown media using at least one of a logo recognition engine, an OCR engine, an object recognition engine, or a graphic recognition engine.
16. The apparatus of claim 13 , wherein the tags are approved by a user.
17. The apparatus of claim 13 , wherein the list of suggested tags includes relevancy scores indicating how relevant the tags are with respect to the unknown media, and the means for assigning is to automatically approve a tag in the list of suggested tags when the relevancy score for the tag is above a threshold relevancy score.
18. An apparatus to tag unknown media, the apparatus comprising:
means for extracting features from audio and image portions of the unknown media;
means for weighting the features based at least partially on respective recognition technologies used to extract the features to determine corresponding weighted features, a highest weight assigned to ones of the features extracted by a logo recognition engine, a next highest weight assigned to ones of the features extracted by an optical character recognition (OCR) engine, a next highest weight assigned to ones of the features extracted by a speech recognition engine, and a lowest weight assigned to ones of the features extracted by a graphic recognition engine;
means for searching a database of pre-tagged media with a combination of the weighted features to generate a list of suggested tags for the unknown media; and
means for assigning one or more tags from the list of suggested tags to the unknown media.