Штучний інтелект

Науковий журнал

ISSN 2710-1673

ONLINE: ISSN 2710-1681

Виберіть свою мову


Preliminary processing of candidates at detection of car plates on images

Муригін К.В.1
1 Інститут проблем штучного інтелекту МОН України і НАН України

Повний текст (PDF)

УДК: 004.89, 004.93
Мова публікації: Російська
Stuc. intelekt. 2013; 18; (2):32–37

Анотація: The article is devoted to a problem of acceleration of objects detection process on images based on multiscale scanning technique. For the solution of this task it is offered to use preliminary processing of candidates with use of integrated characteristics. For a problem of detection of automobile registration plates the integrated characteristic, allowing to exclude from further consideration up to 60% of candidates at a zero error of the object missing is defined. Results of the made experiments can be extended to problems of search of other objects on images on condition of carrying out additional researches on determination of a satisfactory integrated characteristic that is connected with various properties of images of detected objects.

Ключові слова: image recognition, object detection, image analysis, image classification

Посилання:

  1. Paul Viola. Robust real-time object detection / Paul Viola, Michael J. Jones // In Proc. of IEEE Workshopon Statistical and ComputationalTheories ofVision, 2001.
  2. Bradski G. Learning-based computer vision with Intel’s open source computer vision library / Bradski G.,Kaehler A., Pisarevsky V. // Intel Technology Journal [Электронный ресурс]. – Режим доступа :http://develiper.intel.com/ technology/itj/index.htm.
  3. Schapire, Boosting the margin: A new explanation for the effectiveness of voting methods / [Robert E., Freund Y.,Bartlett P, Lee W.S.] // In Proc. Of the Fourteenth International Conference on Machine Learning, 1997
  4. Schapire, Boosting the margin: A new explanation for the effectiveness of voting methods / [Robert E., Freund Y.,Bartlett P, Lee W.S.] // In Proc. Of the Fourteenth International Conference on Machine Learning, 1997.
  5. Мурыгин К.В. Особенности реализации алгоритма AdaBoost для обнаружения объектов наизображениях / К.В. Мурыгин // Искусственный интеллект. – 2009. – № 3. – С. 573-581.
  6. Мурыгин К.В. Комбинирование бинарных свойств в виде МКВ-классификатора / К.В. Мурыгин //Искусственный интеллект. – 2010. – № 1. – С. 108-113.

Переглянути повний текст статті (PDF)