发明名称 |
Dynamic recognition of web addresses in video |
摘要 |
One embodiment described herein may take the form of a system or method for dynamically recognizing an Internet address within a video or audio component of a multimedia presentation on a distribution system or network such as, but not limited to, a satellite, cable or Internet network. In general, the embodiment may analyze the audio portion of the presentation or one or more frames of a video component to detect the presence of a web address within the one or more frames. In the embodiment where the audio portion is analyzed, the system may perform a voice recognition or a similar analysis on the audio portion to detect the utterance of a web address. Similarly, one embodiment analyzing the one or more frames of the video component may comprise performing an optical character recognition (OCR) of the frame. |
申请公布号 |
US8983191(B2) |
申请公布日期 |
2015.03.17 |
申请号 |
US201012906656 |
申请日期 |
2010.10.18 |
申请人 |
EchoStar UK Holdings Limited |
发明人 |
Robinson David John;Avison-Fell Craig |
分类号 |
G06K9/00;G06K9/46;G06K9/32 |
主分类号 |
G06K9/00 |
代理机构 |
Ingrassia Fisher & Lorenz, P.C. |
代理人 |
Ingrassia Fisher & Lorenz, P.C. |
主权项 |
1. A method executable by a television receiver to dynamically detect a web address in one or more frames of a video multimedia presentation, the method comprising:
receiving and decoding the video multimedia presentation by the television receiver; automatically extracting a first frame from the decoded video multimedia presentation, wherein the automatic extracting is initiated by the television receiver without input by the user; analyzing the first frame to identify a pattern of characters, wherein the pattern of characters comprises at least a portion of a web address associated with a website available on the Internet; if the pattern of characters is identified within the first frame, then obtaining the entire web address from the first frame, creating a selectable link that links to a website associated with the web address, and indicating the obtained web address within one or more frames of the video component; providing the first frame to a display device for display; bypassing analyzing a second frame in the video multimedia presentation, the second frame occurring later in time than the first frame; providing the second frame to the display device for display; analyzing a third frame to identify the pattern of characters, the third frame occurring later in time than the second frame; and providing the third frame to the display device for display. |
地址 |
Steeton GB |