Google is apparently working on a technology that will help in improving the contextual relevance of image and video ads. A recently published patent explains how the newly developed technology works.
Google explains the need for such a technology with the following example
“However, providing ads and other documents based on user-related content does not ensure the propriety of that content for a particular audience. For instance, a beer advertisement may not be appropriate on a website for recovering alcoholics, even though the ad and the content of the website are related by subject matter.”
The newly developed technology will scan through images and videos for appropriateness as well as contextual relevance. An extract from the patent reads
“An embodiment of the present invention provides for uploading a document such as a graphical advertisement and comparing the document to other documents. The document can be compared to other documents by a document processor (e.g., automatically by an image processor). The processor may process images, sound files, and other data to identify text and images (as well as spoken words and other data) in the image ad. For instance, text may be identified in an image using optical character recognition (OCR) technology. By comparing the document to other documents, content can be identified in and associated with the document, and the document can be accordingly rated and approved based on this content and the status of the ratings of the comparison documents. The document can also be associated with content-based concepts (e.g., keywords, subject matter, etc.) that relate to a service or product associated with the documents.”
This definitely sounds a very interesting way to expedite the process of approving image and video ads as well as while delivering them contextually. You may view the patent abstract by clicking here (temporary link)