本論文提出了一個應用MPEG-7以及支持向量機 (SVM) 的檢索技術,此一新技術稱之為Color Image Retrieval Based on MPEG-7 and SVM (CIRMS) 。首先分別運用MPEG-7的Color Layout Descriptor (CLD) 和Image Vector (IV) 擷取彩色影像的特徵,接著結合方法所擷取的特徵,最後導入SVM以提升系統的分類效能,降低搜尋複雜度,加速影像搜尋比對的速度。經過實驗證明,能有效提升分類能力,達到良好的檢索效能,並且勝過其他已存在且著名的方法。
This thesis proposes a novel retrieval technique, called Color Image Retrieval based on MPEG-7 and SVM (CIRMS) , to retrieve color images from the database. The technique employs MPEG-7 Color Layout Descriptor (CLD) and Image Vector (IV) respectively to device the retrieval algorithm. It utilizes support vector machine (SVM) to improve the classification performance, experimental results demonstrate that the CIRMS technique can effectively enhance classifying performance, powerfully achieve satisfying retrieval results performance and outperforms the existing well-known methods.