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 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. 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, the list of suggested tags including relevancy scores for respective ones of the tags in the list. Disclosed examples assign a tag from the list of suggested tags to the unknown media based on a comparison of the relevancy score for the tag to a threshold.
1. An apparatus to tag unknown media, the apparatus comprising:
at least one memory;
instructions in the apparatus; and
processor circuitry to execute the instructions to at least:
extract features from portions of the unknown media;
assign a first weight to a first feature extracted based on a first recognition technology to determine a weighted first feature, the first feature assigned to a first category of a plurality of categories;
assign a second weight to a second feature extracted based on a second recognition technology to determine a weighted second feature;
search a database of pre-tagged media with a combination of weighted features to generate a list of suggested tags for the unknown media, the list of suggested tags including relevancy scores for respective ones of the tags in the list, the combination of weighted features including the weighted first feature;
limit the search in the database to the pre-tagged media having category values that match the first category of the first feature; and
assign a tag from the list of suggested tags to the unknown media based on a comparison of the relevancy score for the tag to a threshold.
2. The apparatus of claim 1 , wherein the first recognition technology is an image-based recognition technology and the second recognition technology is an audio-based recognition technology.
3. The apparatus of claim 1 , wherein the portions of the unknown media include audio portions, and the processor circuitry is to extract the features from the audio portions of the unknown media using at least one of a speech recognition engine, a sound identifier, or a song or tune identifier.
4. The apparatus of claim 1 , wherein the portions of the unknown media include image portions, and the processor circuitry 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.
5. The apparatus of claim 1 , wherein the processor circuitry is to assign the tag from the list of suggested tags to the unknown media when the relevancy score for the tag exceeds the threshold.
6. The apparatus of claim 1 , wherein the processor circuitry is to store the tagged media and the assigned tag in the database of pre-tagged media.
7. The apparatus of claim 1 , wherein the first category includes at least one of a brand name, a product type, or a target market of a product.
8. The apparatus of claim 1 , wherein the first category includes at least one of a name of a company advertising a product or a name of a manufacturer creating the product.
9. The apparatus of claim 1 , wherein the first category includes a price range of a product.
10. A tangible computer readable medium comprising computer readable instructions which, when executed, cause a processor to at least:
extract features from portions of unknown media;
assign a first weight to a first feature extracted based on a first recognition technology to determine a weighted first feature, the first feature assigned to a first category of a plurality of categories;
assign a second weight to a second feature extracted based on a second recognition technology to determine a weighted second feature;
search a database of pre-tagged media with a combination of weighted features to generate a list of suggested tags for the unknown media, the list of suggested tags including relevancy scores for respective ones of the tags in the list, the combination of weighted features including the weighted first feature;
limit the search in the database to the pre-tagged media having category values that match the first category of the first feature; and
assign a tag from the list of suggested tags to the unknown media based on a comparison of the relevancy score for the tag to a threshold.
11. The computer readable medium of claim 10 , wherein the first recognition technology is an image-based recognition technology and the second recognition technology is an audio-based recognition technology.
12. The computer readable medium of claim 10 , wherein the portions of the unknown media include audio portions, and the instructions are to cause the processor to extract the features from the audio portions of the unknown media using at least one of a speech recognition engine, a sound identifier, or a song or tune identifier.
13. The computer readable medium of claim 10 , wherein the portions of the unknown media include image portions, and the instructions are to 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.
14. The computer readable medium of claim 10 , wherein the instructions are to cause the processor to assign the tag from the list of suggested tags to the unknown media when the relevancy score for the tag exceeds the threshold.
15. The computer readable medium of claim 10 , wherein the processor is to store the tagged media and the assigned tag in the database of pre-tagged media.
16. An apparatus to tag unknown media, the apparatus comprising:
means for extracting features from portions of the unknown media;
means for weighting to:
assign a first weight to a first feature extracted based on a first recognition technology to determine a weighted first feature, the first feature assigned to a first category of a plurality of categories; and
assign a second weight to a second feature extracted based on a second recognition technology to determine a weighted second feature;
means for searching to:
search a database of pre-tagged media with a combination of weighted features to generate a list of suggested tags for the unknown media, the list of suggested tags including relevancy scores for respective ones of the tags in the list, the combination of weighted features including the weighted first feature; and
limit the search in the database to the pre-tagged media having category values that match the first category of the first feature; and
means for assigning a tag from the list of suggested tags to the unknown media based on a comparison of the relevancy score for the tag to a threshold.
17. The apparatus of claim 16 , wherein the first recognition technology is an image-based recognition technology and the second recognition technology is an audio-based recognition technology.
18. The apparatus of claim 16 , wherein the portions of the unknown media include audio portions, and the means for extracting is to extract the features from the audio portions of the unknown media using at least one of a speech recognition engine, a sound identifier, or a song or tune identifier.
19. The apparatus of claim 16 , wherein the portions of the unknown media include image portions, and 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.
20. The apparatus of claim 16 , wherein the means for assigning is to assign the tag from the list of suggested tags to the unknown media when the relevancy score for the tag exceeds the threshold.