Investigation of wave atom transform by using the classification of mammograms

- This paper presents an approach for breast cancer diagnosis in digital mammograms using wave atom transform.
- I examine the wave atom transform to determine which couple (scale, ratio of biggest coefficients) will give the highest classification rate.
- The system uses two sets of feature matrixes obtained from two different database; MIAS and DDSM database.
- These are tested with classifiers in changing ratios (10% and 90% of coefficients) for each scale.
- The classification is performed using two different classifiers; Support Vector Machine and k-Nearest Neighbors.