Image feature extraction represent part of fundamental of image analysis. The main target of image
feature extraction is can be differentiate an object with other object by paying attention computing complexity
in obtaining characteristic.
Feature extraction in this research is conducted at image result of thermography for breast cancer, using
wavelet method specially daubechies2, daubechies9, coiflet1, and symlet2. Image feature result of wavelet
transform can be obtained by calculating the energy which consist in each image subband, that is approximation
subband, horizontal detail subband, vertical detail subband, and diagonal detail subband.
This research using 44 data image of thermogram normal breast, 19 image of thermogram early breast
cancer, and 26 image of thermogram continue breast cancer. Image pre processing conducted by altering
thermogram colour image become thermogram grayscale image, continued with determination of ROI and
cropping method. Image result cropping method is extracted using 6 level wavelet decomposition. The biggest
energy at detail subband will be become feature at each thermogram image.
Image feature of thermogram result of examination get from detail subband. The biggest energy subband
there are at horizontal subband detail and vertical subband detail. Based on value of energy subband detail the
best accuration diagnose feature extraction used wavelet Db2 and Sym2 decomposition at 6 level decomposition,
while the ugly result of feature extraction used wavelet Db9 decomposition.
Keywords: Thermogram image, breast cancer, feature extraction, wavelet, subband energy
Copyrights © 2012