Standard

Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition. / Potapov, A.S.

Pattern Recognition and Image Analysis.. Springer Nature, 2012. p. 82-91.

Research output: Chapter in Book/Report/Conference proceeding › Article in an anthology

Harvard

Potapov, AS 2012, Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition. in Pattern Recognition and Image Analysis.. Springer Nature, pp. 82-91.

APA

Potapov, A. S. (2012). Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition. In Pattern Recognition and Image Analysis. (pp. 82-91). Springer Nature.

Vancouver

Potapov AS. Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition. In Pattern Recognition and Image Analysis.. Springer Nature. 2012. p. 82-91

Author

Potapov, A.S. / Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition. Pattern Recognition and Image Analysis.. Springer Nature, 2012. pp. 82-91

BibTeX

@inbook{61b33386a3c642fbb478a9b7a73324a2,
title = "Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition",
abstract = "Problems of decision criterion in the tasks of image analysis and pattern recognition are considered. Overlearning as a practical consequence of fundamental paradoxes in inductive inference is illustrated with examples. Theoretical (on the base of algorithmic complexity) and practical formulations of the minimum description length (MDL) principle are given. Decrease of the overlearning effect is shown in the examples of modern recognition, grouping, and segmentation methods modified with the MDL principle. Novel possibilities of construction of learnable image analysis algorithms by representation optimization on the base of the MDL principle are described",
author = "A.S. Potapov",
year = "2012",
language = "English",
isbn = "1054-6618",
pages = "82--91",
booktitle = "Pattern Recognition and Image Analysis.",
publisher = "Springer Nature",
address = "Germany",

}

RIS

TY - CHAP

T1 - Principle of Representational Minimum Description Length in Image Analysis and Pattern Recognition

AU - Potapov, A.S.

PY - 2012

Y1 - 2012

N2 - Problems of decision criterion in the tasks of image analysis and pattern recognition are considered. Overlearning as a practical consequence of fundamental paradoxes in inductive inference is illustrated with examples. Theoretical (on the base of algorithmic complexity) and practical formulations of the minimum description length (MDL) principle are given. Decrease of the overlearning effect is shown in the examples of modern recognition, grouping, and segmentation methods modified with the MDL principle. Novel possibilities of construction of learnable image analysis algorithms by representation optimization on the base of the MDL principle are described

AB - Problems of decision criterion in the tasks of image analysis and pattern recognition are considered. Overlearning as a practical consequence of fundamental paradoxes in inductive inference is illustrated with examples. Theoretical (on the base of algorithmic complexity) and practical formulations of the minimum description length (MDL) principle are given. Decrease of the overlearning effect is shown in the examples of modern recognition, grouping, and segmentation methods modified with the MDL principle. Novel possibilities of construction of learnable image analysis algorithms by representation optimization on the base of the MDL principle are described

M3 - Article in an anthology

SN - 1054-6618

SP - 82

EP - 91

BT - Pattern Recognition and Image Analysis.

PB - Springer Nature

ER -

ID: 4622136