Natural image correction by iterative projections to eigenspace constructed in normalized image space

Takeshi Shakunaga, Fumihiko Sakaue

研究成果査読

6 被引用数 (Scopus)

抄録

Image correction is discussed for realizing both effective object recognition and realistic image-based rendering. Three image normalizations are compared in relation with the linear subspaces and eigenspaces, and we conclude that the normalization by L1-norm, which normalizes the total sum of intensities, is the best for our purposes. Based on noise analysis in the normalized image space(NIS), an image correction algorithm is constructed, which is accomplished by iterative projections along with corrections of an image to an eigenspace in NIS. Experimental results show that the proposed method works well for natural images which include various kinds of noise shadows, reflections and occlusions. The proposed method provides a feasible solution to the object recognition based on the illumination cone [2]. The technique can also be extended to face detection of unknown person and registration/ recognition using eigenfaces.

本文言語English
ページ(範囲)648-651
ページ数4
ジャーナルProceedings - International Conference on Pattern Recognition
16
1
出版ステータスPublished - 2002
外部発表はい

ASJC Scopus subject areas

  • コンピュータ ビジョンおよびパターン認識

フィンガープリント

「Natural image correction by iterative projections to eigenspace constructed in normalized image space」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル