최소 단어 이상 선택하여야 합니다.
최대 10 단어까지만 선택 가능합니다.
다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
NTIS 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
DataON 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Edison 바로가기다음과 같은 기능을 한번의 로그인으로 사용 할 수 있습니다.
Kafe 바로가기국가/구분 | United States(US) Patent 등록 |
---|---|
국제특허분류(IPC7판) |
|
출원번호 | US-0859134 (1986-05-02) |
발명자 / 주소 |
|
출원인 / 주소 |
|
인용정보 | 피인용 횟수 : 404 인용 특허 : 0 |
A method, apparatus and system are provided for recognizing broadcast segments, such as commercials, in real time by continuous pattern recognition without resorting to cues or codes in the broadcast signal. Each broadcast frame is parametized to yield a digital word and a signature is constructed f
A method, apparatus and system are provided for recognizing broadcast segments, such as commercials, in real time by continuous pattern recognition without resorting to cues or codes in the broadcast signal. Each broadcast frame is parametized to yield a digital word and a signature is constructed for segments to be recognized by selecting, in accordance with a set of predefined rules, a number of words from among random locations throughout the segment and storing them along with offset information indicating their relative locations. As a broadcast signal is monitored, it is parametized in the same way and the library of signatures is compared against each digital word and words offset therefrom by the stored offset amounts. A data reduction technique minimizes the number of comparisons required while still maintaining a large database.
A method for continuous pattern recognition of broadcast segments, each of said segments having at least one of an audio portion and a video portion, said method comprising: constructing a digital signature from a known sample of a segment to be recongnized by digitally parametizing said segment, se
A method for continuous pattern recognition of broadcast segments, each of said segments having at least one of an audio portion and a video portion, said method comprising: constructing a digital signature from a known sample of a segment to be recongnized by digitally parametizing said segment, selecting frames from among random frame locations throughout said parametized segment in accordance with a set of predefined rules to form said signature, and associating with said signature the locations of said selected frames relative to a reference location; storing said signature and said associated frame locations in a library of signatures, each signature in said library being identified with a particular segment to be recognized; monitoring a broadcast signal; digitally parametizing said monitored signal; and for each frame of said parametized monitored signal, searching said library for signatures potentially associated therewith and, using the frame location information associated with said potentially associated stored signatures, comparing each of said potentially associated stored signatures to the appropriate frames of said parametized monitored signal. A method for continuous patern recognition of broadcast segments, each of said sgements having at least one of an audio portion and a video portion and further having a first portion that is the same each time the segment is broadcast and a second portion that may differ each time the segment is broadcast, said method comprising: constructing a signature from a known sample of the first portion of such a segment to be recognized; recording additional data from known samples of said second portion; storing said signature and said additional data; associating with said stored signature an indication of the existence of said second portion; monitoring a broadcast signal; identifying the first portion of a broadcast segment in said monitored broadcast signal with said signature; and using said additional data to identify the second portion of said broadcast segment.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.