Automated identification of product or brand-related metadata candidates for a commercial using consistency between audio and image elements of products of brands detected in commercials
A method and system are provided for assigning metadata candidates to a commercial by performing image analysis on a plurality of the video frames to identify video frames that include one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text which appear in the video frames, performing audio analysis on the commercial to identify audio associated with one or more identifiable products or brands in the commercial, comparing the products and brands identified by the image analysis with the products and brands identified by the audio analysis, and identifying similar products and brands; and assigning to the commercial a product or brand as a primary metadata candidate when a similar product or brand is identified by the image analysis and the audio analysis.
1. An automated method of identifying primary metadata candidates associated with a commercial and assigning the primary metadata candidates to the commercial, wherein the commercial is defined by video frames, the method comprising:
(a) performing image analysis using a media processor on a plurality of the video frames to identify video frames that include image elements associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text which appear in the video frames;
(b) performing audio analysis on the commercial using the media processor to identify audio associated with one or more identifiable products or brands in the commercial;
(c) comparing, using the media processor, the products and brands identified by the image analysis with the products and brands identified by the audio analysis, and identifying similar products and brands;
(d) assigning to the commercial, by a content processing platform, a product or brand as a primary metadata candidate when a similar product or brand is identified by the image analysis and the audio analysis,
wherein the primary metadata candidates have relative accuracy strengths, the method further comprising for the identified products or brands which were found to be similar in the comparison of step (c):
(e) comparing, using the media processor, the temporal position within the commercial of the video frames having products and brands identified by the image analysis with the temporal position within the commercial of the products and brands identified by the audio analysis, and identifying similar temporal positions; and
(f) assigning, by the content processing platform, to the products and brands having similar temporal positions higher relative accuracy strengths than products and brands having different temporal positions.
2. The automated method of claim 1 wherein step (d) further comprises assigning to the commercial, by the content processing platform, the identified products or brands which were not found to be similar in the comparison of step (c) as secondary metadata candidates.
3. The automated method of claim 1 wherein the image analysis is performed on all of the video frames in the commercial.
4. The automated method of claim 1 wherein the image analysis is performed on a sampled subset of the video frames in the commercial, the sampled subset of video frames being evenly sampled throughout the length of the commercial.
5. An automated system for identifying primary metadata candidates associated with a commercial and assigning the primary metadata candidates to the commercial, wherein the commercial is defined by video frames, the system comprising:
(a) a media processor configured to:
(i) perform image analysis on a plurality of the video frames to identify video frames that include image elements associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text which appear in the video frames,
(ii) perform audio analysis on the commercial using the media processor to identify audio associated with one or more identifiable products or brands in the commercial, and
(iii) compare the products and brands identified by the image analysis with the products and brands identified by the audio analysis, and identify similar products and brands; and
(b) a content processing platform configured to assign to the commercial a product or brand as a primary metadata candidate when a similar product or brand is identified by the image analysis and the audio analysis,
wherein the primary metadata candidates have relative accuracy strengths, the automated system further comprising for the identified products or brands which were found to be similar in the comparison, the media processor is further configured to:
(iv) compare the temporal position within the commercial of the video frames having products and brands identified by the image analysis with the temporal position within the commercial of the products and brands identified by the audio analysis, and identifying similar temporal positions,
wherein the content processing platform is further configured to assign to the products and brands having similar temporal positions higher relative accuracy strengths than products and brands having different temporal positions.
6. The automated system of claim 5 wherein the content processing platform is further configured to assign the identified products or brands which were not found to be similar in the comparison as secondary metadata candidates.
7. The automated system of claim 5 wherein the image analysis is performed on all of the video frames in the commercial.
8. The automated system of claim 5 wherein the image analysis is performed on a sampled subset of the video frames in the commercial, the sampled subset of video frames being evenly sampled throughout the length of the commercial.