New patents are issued on Tuesdays by the USPTO. This week's Spotlight Patents concern aspects of digital fingerprinting. Assigned to Turner Broadcasting System, the first patent addresses techniques for logo identification based on automatic content recognition. Assigned to Google, the second patent addresses techniques for endpoint based video fingerprinting.
9,137,568, "Method and system for logo identification based on automatic content recognition," assigned to Turner Broadcasting System.
Abstract
A method and system for logo identification based on automatic content recognition (ACR) are described in which a connected television (TV) or other end-user device may be provided with instructions to fingerprint certain regions in a video frame to identify the source of the content being displayed. Such instructions may be provided when, for example, fingerprint matching is able to identify content that is provided by multiple sources but is unable to identify the particular source of the content. In those instances, one or more additional locations may be determined for taking fingerprints in the video frame. These locations correspond to region of the video frame in which a graphical item that represents the network television station is typically displayed. A profile with these locations is generated and sent to the connected TV to take additional fingerprints to enable the identification of the network television station providing content.9,135,674, "Endpoint based video fingerprinting," assigned to Google.
Abstract
A method and system generates and compares fingerprints for videos in a video library. The video fingerprints provide a compact representation of the temporal locations of discontinuities in the video that can be used to quickly and efficiently identify video content. Discontinuities can be, for example, shot boundaries in the video frame sequence or silent points in the audio stream. Because the fingerprints are based on structural discontinuity characteristics rather than exact bit sequences, visual content of videos can be effectively compared even when there are small differences between the videos in compression factors, source resolutions, start and stop times, frame rates, and so on. Comparison of video fingerprints can be used, for example, to search for and remove copyright protected videos from a video library. Furthermore, duplicate videos can be detected and discarded in order to preserve storage space.