At its Google Cloud Next meeting in San Francisco, Google reported launch of another machine learning API yesterday that can recognize objects in video recordings and make them searchable.
The new Video Intelligence API is implied for developers to assemble applications that can consequently identify objects from a video. It was not very long ago, image recognition APIs was made accessible in the cloud and worked just in the same manner for still pictures, yet with the assistance of this new API, engineers will have the capacity to construct applications that let clients seek and discover information in video recordings
“Cloud Video Intelligence API uses powerful deep-learning models, built using frameworks like TensorFlow and applied on large-scale media platforms like YouTube,” Fei-Fei Li, chief scientist for Google Cloud artificial intelligence (AI) and machine learning, wrote in a blog post.
Remarkably, the API likewise permits you to label scene changes in a video. Video Recordings since a very long time have been a test for machine learning scientists. Google’s two cloud rivals, AWS and Microsoft Azure, don’t offer this functionality.
Moreover, Google additionally declared that its Cloud Machine Learning Engine, earlier known as Cloud Machine Learning, has now been launched out of beta. The same goes for Google’s Cloud Datalab.
Checkout Latest IT news at itvoir.com
Madhurima Goyal, From ITvoir News Desk