Image classification of Kiziltepe cropland by using Gabor Wavelet Transform

Kurte

In this research, images of Kiziltepe (Mardin) agricultural land are classified based on development in different period of crops (1-sowing term, 2-little ripe term, 3-ripe term and 4-harvest term). The digital crop images are derived from TARIT (Agricultural Crop Forecast and Following Project) stations. The texture feature vectors are obtained from images of different crop periods with using Gabor Wavelet Transform (GWT) which is very popular method for image texture extraction. GWT based feature vectors are applied to different type of classifiers as inputs and the performance results of each system are compared. For classification the crop images, Multilayer Perceptron (MLP) neural network and k-Nearest Neighbor (k- NN) methods are used. Finally, the best average performance is observed as 98.01 % in 24-35-4 network structure of MLP neural network classifier.

Peyvên sereke

Jêgirtin

@inproceedings{imageclassificationofkiziltepe2012,
  title = {{Image classification of Kiziltepe cropland by using Gabor Wavelet Transform}},
  author = {Acar, Emrullah and Özerdem, Mehmet Siraç},
  year = {2012},
  publisher = {{IEEE}},
  school = {{Batman University}},
  doi = {10.1109/siu.2012.6204755}
}

TY  - CPAPER
AU  - Acar, Emrullah
AU  - Özerdem, Mehmet Siraç
TI  - Image classification of Kiziltepe cropland by using Gabor Wavelet Transform
PY  - 2012
T2  - 2012 20th Signal Processing and Communications Applications Conference (SIU)
PB  - IEEE
DO  - 10.1109/siu.2012.6204755
ER  - 

Çavkaniyên têkildar