A Genetic Algorithms Based Classifier for Object Classification in Images

Yilmaz T., Yildirim Y., YAZICI A.

26th Annual International Symposium on Computer and Information Science, London, Kanada, 26 - 28 Eylül 2011, ss.519-525 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1007/978-1-4471-2155-8_66
  • Basıldığı Şehir: London
  • Basıldığı Ülke: Kanada
  • Sayfa Sayıları: ss.519-525
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

Increase in the use of digital images has shown the need for modeling and querying the semantic content, which is usually defined using the objects in the images. In this paper, a Genetic Algorithm (GA) based object classification mechanism is developed for extracting the content of images. Objects are defined by using the Best Representative and Discriminative Feature (BRDF) model, where features are MPEG-7 descriptors. The classifier improves itself in time, with the genetic operations of GA.