泰山学院学报
泰山學院學報
태산학원학보
JOURNAL OF TAISHAN UNIVERSITY
2011年
6期
34-39
,共6页
语义视频检索%相似度算法%查询预处理%概念检测器过滤%映射数目
語義視頻檢索%相似度算法%查詢預處理%概唸檢測器過濾%映射數目
어의시빈검색%상사도산법%사순예처리%개념검측기과려%영사수목
content-based video retrieval%semantic relatedness%query preprocess%concepts detector filter%reflection number
为了实现基于概念视频检索中从底层内容到查询的语义贯通,应用基于WordNet词典的语义相似度算法,通过对三种不同原理的算法对比应用,得出基于信息量算法在本应用中更有优势,语义匹配可以提高检索精度,最优映射数目为2至3个,以及在目前发展水平下,映射到合适的概念比检测器精度更合适四个重要结论.
為瞭實現基于概唸視頻檢索中從底層內容到查詢的語義貫通,應用基于WordNet詞典的語義相似度算法,通過對三種不同原理的算法對比應用,得齣基于信息量算法在本應用中更有優勢,語義匹配可以提高檢索精度,最優映射數目為2至3箇,以及在目前髮展水平下,映射到閤適的概唸比檢測器精度更閤適四箇重要結論.
위료실현기우개념시빈검색중종저층내용도사순적어의관통,응용기우WordNet사전적어의상사도산법,통과대삼충불동원리적산법대비응용,득출기우신식량산법재본응용중경유우세,어의필배가이제고검색정도,최우영사수목위2지3개,이급재목전발전수평하,영사도합괄적개념비검측기정도경합괄사개중요결론.
In order to run semantic linking through the bottom content to users' query in concept-based video retrieval, we apply semantic similarity algorithm based on WordNet to video retrieval. By comparing the effects of three different principles algorithm, we get four important conclusions. Algorithm based on information entropy is better for use here than others, semantic matching can improve retrieval precision, the optimal number of maps is 2 to 3, and in the current development level, mapping to the appropriate detector is important than the detector accuracy.