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

Takeshi Shakunaga, Fumihiko Sakaue

Research output: Chapter in Book/Report/Conference proceedingChapter

5 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages648-651
Number of pages4
Volume16
Edition1
Publication statusPublished - 2002

Fingerprint

Object recognition
Face recognition
Cones
Lighting
Rendering (computer graphics)

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Shakunaga, T., & Sakaue, F. (2002). Natural image correction by iterative projections to eigenspace constructed in normalized image space. In Proceedings - International Conference on Pattern Recognition (1 ed., Vol. 16, pp. 648-651)

Natural image correction by iterative projections to eigenspace constructed in normalized image space. / Shakunaga, Takeshi; Sakaue, Fumihiko.

Proceedings - International Conference on Pattern Recognition. Vol. 16 1. ed. 2002. p. 648-651.

Research output: Chapter in Book/Report/Conference proceedingChapter

Shakunaga, T & Sakaue, F 2002, Natural image correction by iterative projections to eigenspace constructed in normalized image space. in Proceedings - International Conference on Pattern Recognition. 1 edn, vol. 16, pp. 648-651.
Shakunaga T, Sakaue F. Natural image correction by iterative projections to eigenspace constructed in normalized image space. In Proceedings - International Conference on Pattern Recognition. 1 ed. Vol. 16. 2002. p. 648-651
Shakunaga, Takeshi ; Sakaue, Fumihiko. / Natural image correction by iterative projections to eigenspace constructed in normalized image space. Proceedings - International Conference on Pattern Recognition. Vol. 16 1. ed. 2002. pp. 648-651
@inbook{3e6553606b9e4a61a7bf7c670e464177,
title = "Natural image correction by iterative projections to eigenspace constructed in normalized image space",
abstract = "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.",
author = "Takeshi Shakunaga and Fumihiko Sakaue",
year = "2002",
language = "English",
volume = "16",
pages = "648--651",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "1",

}

TY - CHAP

T1 - Natural image correction by iterative projections to eigenspace constructed in normalized image space

AU - Shakunaga, Takeshi

AU - Sakaue, Fumihiko

PY - 2002

Y1 - 2002

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0842348686&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0842348686&partnerID=8YFLogxK

M3 - Chapter

VL - 16

SP - 648

EP - 651

BT - Proceedings - International Conference on Pattern Recognition

ER -