Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Современные проблемы...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Детектор смазанности и расфокусировки на основе модели текста

Детектор смазанности и расфокусировки на основе модели текста

Abstract

В работе рассматривается подход к детектированию смаза и расфокусировки документов на основе модели текста, посредством анализа второй производной функций яркости, построенных в окрестностях границ объектов по направлениям градиента яркости. Даны описание модели текста, примеры искаженных изображений текста, рекомендации по выбору объективных показателей, на основании которых можно выявить наличие или отсутствие смаза и расфокусировки. Предложен способ, позволяющий перевести выбранные показатели к числовым признакам, инвариантным к различным видам неравномерностей среди локальных характеристик анализируемого изображения. Описаны особенности построения классификатора для данной задачи. Уделено внимание вопросам производительности использованных алгоритмов. Основной анализ и получение характерных признаков объектов реализуется на изображении разницы гауссиан (DoG), что имитирует функцию зрения человека.

The paper considers the problem of automatic blur and defocusing detecting on images of documents. The problem is solved based on text model and analysis of second derivative of brightness function along the brightness gradient. The paper gives text model description, examples of text distorted images and some advises on choosing descriptors for blur and defocusing detection and further distortion classification. The way for calculation of invariant number features by local nonuniformities of image from selected descriptors is proposed. The paper describes specificity for the classifier training. Particular attention is paid to the problem for performance of involved algorithms. Principal research is provided on difference of Gaussians image to mimic neural processing of the retina in human eye.

Keywords

АКТИВНОЕ ОБУЧЕНИЕ, КЛАССИФИКАЦИЯ, ИНВАРИАНТЫЕ МОМЕНТЫ, РАСПОЗНАВАНИЕ СИМВОЛОВ, ОБРАБОТКА ИЗОБРАЖЕНИЙ ДОКУМЕНТОВ, ЛАПЛАСИАН, МОДЕЛЬ ТЕКСТА, ОБРАБОТКА ТЕКСТА, ТЕКСТОВЫЙ ДОКУМЕНТ, ШУМ, ИСКАЖЕНИЕ, РАСФОКУСИРОВКА, СМАЗ

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
gold