Automated identification of product or brand-related metadata candidates for a commercial using dominance and prominence of product or brand-related text or objects in video frames of the commercial

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:

(i) 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, and

(ii) calculate a percentage of the total video frame area that is taken up by the image elements associated with the identified product-related logos, brand-related logos, product-related text, or brand-related text;

(b) comparing in the media processor the percentage of the total video frame area that is taken up by the image elements associated with the identified product-related logos, brand-related logos, product-related text, or brand-related text to a predetermined threshold percentage; and

(c) assigning to the commercial, by a content processing platform, the identified products or brands as primary metadata candidates when the percentage exceeds the predetermined threshold percentage, wherein the primary metadata candidates are associated solely with the commercial, and not with any program type content that is played in a video data stream that includes the commercial.

2. The automated method of claim 1 wherein the image analysis is performed on all of the video frames in the commercial.

3. 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.

4. 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:

(ii) 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,

(iii) calculate a percentage of the total video frame area that is taken up by the image elements associated with the identified product-related logos, brand-related logos, product-related text, or brand-related text, and

(iv) compare the percentage of the total video frame area that is taken up by the image elements associated with the identified product-related logos, brand-related logos, product-related text, or brand-related text to a predetermined threshold percentage; and

(b) a content processing platform configured to assign to the commercial the identified products or brands as primary metadata candidates when the percentage exceeds the predetermined threshold percentage, wherein the primary metadata candidates are associated solely with the commercial, and not with any program type content that is played in a video data stream that includes the commercial.

5. The automated system of claim 4 wherein the image analysis is performed on all of the video frames in the commercial.

6. The automated system of claim 4 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.

7. 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:

(i) image elements in the plurality of video frames that are 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, and

(ii) image elements in the plurality of the video frames that are not 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) calculating using the media processor for each identified product or brand a relative size of each of the identified image elements for the product or brand in comparison with the identified image elements that are not 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;

(c) comparing in the media processor for each of the identified products or brands the relative size for the image elements in the plurality of video frames that are associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text to a predetermined threshold value; and

(d) assigning to the commercial, by a content processing platform, the identified products or brands as primary metadata candidates when the relative size for the identifiable product-related logos, brand-related logos, product-related text, or brand-related text exceeds the predetermined threshold value, wherein the primary metadata candidates are associated solely with the commercial, and not with any program type content that is played in a video data stream that includes the commercial.

8. The automated method of claim 7 wherein the relative size calculation is based on an average or median size of the image elements that are associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text, and the average or median size of the image elements that are not associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text.

9. The automated method of claim 7 wherein the image analysis is performed on all of the video frames in the commercial.

10. The automated method of claim 7 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.

11. 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:

(A) image elements in the plurality of video frames that are 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, and

(B) image elements in the plurality of the video frames that are not 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) calculate for each identified product or brand a relative size of each of the identified image elements for the product or brand in comparison with the identified image elements that are not 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, and

(iii) compare for each of the identified products or brands the relative size for the image elements in the plurality of video frames that are associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text to a predetermined threshold value; and

(b) a content processing platform configured to assign to the commercial the identified products or brands as primary metadata candidates when the relative size for the identifiable product-related logos, brand-related logos, product-related text, or brand-related text exceeds the predetermined threshold value, wherein the primary metadata candidates are associated solely with the commercial, and not with any program type content that is played in a video data stream that includes the commercial.

12. The automated system of claim 11 wherein the relative size calculation is based on an average or median size of the image elements that are associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text, and the average or median size of the image elements that are not associated with one or more of identifiable product-related logos, brand-related logos, product-related text, or brand-related text.

13. The automated system of claim 11 wherein the image analysis is performed on all of the video frames in the commercial.

14. The automated system of claim 11 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.