| 摘要 |
<p>A rule based video based classification system, which initiates classification with offline training 500. Sample video clips 502 of different categories are identified. Thereafter, an entropy-based inductive tree-learning algorithm is utilized to establish the trained knowledge base. A classifier 504 then accepts video of data 506 to be classified, and utilizes rules in conjunction with extracted video features to classify the input video or data 506. The classifier 504 then provides the classification results 508.</p> |
