公开(公告)号：US4739398A

公开(公告)日：1988-04-19

申请号：US859134

申请日：1986-05-02

申请人： William L. Thomas ,  Steven J. Sletten ,  John W. Mathews, Jr. ,  Jeffrey C. Swinehart ,  Michael W. Fellinger ,  John E. Hershey ,  George P. Hyatt ,  Robert F. Kubichek

发明人： William L. Thomas ,  Steven J. Sletten ,  John W. Mathews, Jr. ,  Jeffrey C. Swinehart ,  Michael W. Fellinger ,  John E. Hershey ,  George P. Hyatt ,  Robert F. Kubichek

IPC分类号： G06K9/00 ,  H04H1/00 ,  H04H60/37 ,  H04H60/58 ,  H04H60/59 ,  H04N17/00 ,  H04H9/00

CPC分类号： G06K9/00711 ,  G11B27/28 ,  H04H60/37 ,  H04H60/58 ,  H04H60/59

摘要： 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.

摘要翻译： 提供了一种方法，装置和系统，用于通过连续模式识别实时地识别诸如商业广告的广播片段，而无需诉诸广播信号中的提示或代码。 每个广播帧被参数化以产生数字字，并且通过根据一组预定义规则从整个段中的随机位置中选择一组单词并将其与偏移信息一起存储来构建用于要被识别的段的签名 指示他们的相对位置。 当广播信号被监视时，以相同的方式对其进行参数化，并且通过存储的偏移量将特征库与每个数字字和与其偏移的字进行比较。 数据缩减技术最大限度地减少了仍然维护大型数据库所需的比较数量。