MUMBAI, India, Sept. 5 -- Intellectual Property India has published a patent application (202348047950 A) filed by Google Llc, Mountain View, U.S.A., on July 17, 2023, for 'optimal format selection for video players based on predicted visual quality using machine learning.'
Inventor(s) include Wang, Yilin; Guo, Yue; and Adsumilli, Balineedu, Chowdary.
The application for the patent was published on Sept. 5, under issue no. 36/2025.
According to the abstract released by the Intellectual Property India: "A method and apparatus are disclosed for optimal format selection for video players based on predicted visual quality. The method comprises: providing sampled frames of a video as input to a trained machine learning model; obtaining a plurality of outputs of the trained machine learning model; extracting, from the plurality of outputs, a plurality of quality scores each associated with a unique combination of one of a plurality of video formats, one of a plurality of transcoding configurations, and one of a plurality of display resolutions, wherein the plurality of quality scores comprises a first quality score associated with a first combination of a first video format, a first transcoding configuration, and a first display resolution; and causing a first video format to be selected for a client device from the plurality of video formats based on the first quality score that is associated with a first combination including the first display resolution that matches a display resolution of the client device."
The patent application was internationally filed on Dec. 31, 2019, under International application No.PCT/US2019/069055.
Disclaimer: Curated by HT Syndication.
