Feature-based image analysis

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Feature-based image analysis. / Lillholm, Martin; Nielsen, Mads; Griffin, Lewis D.

I: International Journal of Computer Vision, Bind 52, Nr. 2, 2003, s. 73-95.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Lillholm, M, Nielsen, M & Griffin, LD 2003, 'Feature-based image analysis', International Journal of Computer Vision, bind 52, nr. 2, s. 73-95. https://doi.org/10.1023/A:1022995822531

APA

Lillholm, M., Nielsen, M., & Griffin, L. D. (2003). Feature-based image analysis. International Journal of Computer Vision, 52(2), 73-95. https://doi.org/10.1023/A:1022995822531

Vancouver

Lillholm M, Nielsen M, Griffin LD. Feature-based image analysis. International Journal of Computer Vision. 2003;52(2):73-95. https://doi.org/10.1023/A:1022995822531

Author

Lillholm, Martin ; Nielsen, Mads ; Griffin, Lewis D. / Feature-based image analysis. I: International Journal of Computer Vision. 2003 ; Bind 52, Nr. 2. s. 73-95.

Bibtex

@article{8c49fa306dcb11dd8d9f000ea68e967b,
title = "Feature-based image analysis",
abstract = "According to Marr's paradigm of computational vision the first process is an extraction of relevant features. The goal of this paper is to quantify and characterize the information carried by features using image-structure measured at feature-points to reconstruct images. In this way, we indirectly evaluate the concept of feature-based image analysis. The main conclusions are that (i) a reasonably low number of features characterize the image to such a high degree, that visually appealing reconstructions are possible, (ii) different feature-types complement each other and all carry important information. The strategy is to define metamery classes of images and examine the information content of a canonical least informative representative of this class. Algorithms for identifying these are given. Finally, feature detectors localizing the most informative points relative to different complexity measures derived from models of natural image statistics, are given.",
author = "Martin Lillholm and Mads Nielsen and Griffin, {Lewis D.}",
year = "2003",
doi = "10.1023/A:1022995822531",
language = "English",
volume = "52",
pages = "73--95",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer",
number = "2",

}

RIS

TY - JOUR

T1 - Feature-based image analysis

AU - Lillholm, Martin

AU - Nielsen, Mads

AU - Griffin, Lewis D.

PY - 2003

Y1 - 2003

N2 - According to Marr's paradigm of computational vision the first process is an extraction of relevant features. The goal of this paper is to quantify and characterize the information carried by features using image-structure measured at feature-points to reconstruct images. In this way, we indirectly evaluate the concept of feature-based image analysis. The main conclusions are that (i) a reasonably low number of features characterize the image to such a high degree, that visually appealing reconstructions are possible, (ii) different feature-types complement each other and all carry important information. The strategy is to define metamery classes of images and examine the information content of a canonical least informative representative of this class. Algorithms for identifying these are given. Finally, feature detectors localizing the most informative points relative to different complexity measures derived from models of natural image statistics, are given.

AB - According to Marr's paradigm of computational vision the first process is an extraction of relevant features. The goal of this paper is to quantify and characterize the information carried by features using image-structure measured at feature-points to reconstruct images. In this way, we indirectly evaluate the concept of feature-based image analysis. The main conclusions are that (i) a reasonably low number of features characterize the image to such a high degree, that visually appealing reconstructions are possible, (ii) different feature-types complement each other and all carry important information. The strategy is to define metamery classes of images and examine the information content of a canonical least informative representative of this class. Algorithms for identifying these are given. Finally, feature detectors localizing the most informative points relative to different complexity measures derived from models of natural image statistics, are given.

U2 - 10.1023/A:1022995822531

DO - 10.1023/A:1022995822531

M3 - Journal article

VL - 52

SP - 73

EP - 95

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 2

ER -

ID: 5581031