Google has unveiled a public beta version of the Google Cloud Video intelligence API and has introduced enhancements in the Google Cloud Vision API by updating existing features.
The Google Cloud Video intelligence API, first released in March 2017, uses machine learning to make videos searchable and discoverable, by extracting metadata which is also used to index video content. Since the API contains a library of 20,000 labels, those not possessing extensive knowledge in machine learning or computer vision can also use it.
The API puts these labels to use to identify entities within the content of video. The API annotates videos stored on Google Cloud Storage identifying key entities within the video and as they occur.
Google Cloud Video intelligence API can be integrated with applications to introduce capabilities such as content moderation, content recommendations, and contextual advertising. Of the new features introduced in the beta release is pornographic content detection.
Enhancements to the updated Cloud Vision API include (but are not limited to) increased label detection model vocabulary (now more than 10,000 entities), improved text detection model specifically regarding recall on Latin languages, and the addition of Google Image Search-powered web detection.
The updated Cloud Vision API also includes capabilities for web and document detection for general use that enable users to search for and find similar images on the web as well as the associated video metadata.
The updates to the Google Cloud Vision API will be rolled out within the next three weeks.