Application of wavelet transform and genetic algorithms for image processing

Artem A. Belousov, Vladimir G. Spitsyn, Dmitry V. Sidorov

Результат исследований: Материалы для книги/типы отчетовМатериалы для конференции

Аннотация

Getting clear high detailed images with high contrast is an important task in many spheres of science and engineering. However, it's not always possible because of imperfection of devices or environment conditions. This all leaded to development of different methods of image enhancement. In this article a developed two-phase full-color image enhancement algorithm is described. During the first phase noises are removed from the picture. Wavelet transformation has been chosen to perform it, because it allows easily remove high-frequency parts. Also, noise components, especially big random surges of signal, could be presented like set of local features of signals. Noise can be reduced by thresholding this features. During the second phase brightness and contrast are automatically tuned up using genetic algorithm. Genetic algorithms, which are effective methods of multidimensional optimization, allow quick selection of optimal values of transformation parameters, using objective optimization criterion.

Язык оригиналаАнглийский
Название основной публикацииProceedings of the 2009 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2009
Страницы846-851
Число страниц6
Том2
СостояниеОпубликовано - 2009
Событие2009 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2009 - Las Vegas, NV, Соединенные Штаты Америки
Продолжительность: 13 июл 200916 июл 2009

Другое

Другое2009 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2009
СтранаСоединенные Штаты Америки
ГородLas Vegas, NV
Период13.7.0916.7.09

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Fingerprint Подробные сведения о темах исследования «Application of wavelet transform and genetic algorithms for image processing». Вместе они формируют уникальный семантический отпечаток (fingerprint).

Цитировать