2008年
A Fast Algorithm of Video Super-Resolution Using Dimensionality Reduction by DCT and Example Selection
19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6
- ,
- ,
- ,
- 巻
- TuAT10.20
- 号
- 開始ページ
- 1174
- 終了ページ
- +
- 記述言語
- 英語
- 掲載種別
- 記事・総説・解説・論説等(商業誌、新聞、ウェブメディア)
- 出版者・発行元
- IEEE
In this paper we propose a novel learning-based video super resolution algorithm with less memory requirements and computational cost. To this end, we adopt discrete cosine transform (DCT) coefficients for feature vector components. Moreover we design an example selection procedure to construct a compact database. We conducted evaluative experiments using MPEG test sequences to synthesize a high resolution video. Experimental results show that our method can improve effectiveness of super-resolution algorithm, while preserving the quality of synthesized image.
- リンク情報
- ID情報
-
- ISSN : 1051-4651
- Web of Science ID : WOS:000264729000288