| Popis: |
In this study, mass detection application is developed for mammograms from Zernike moments and Fast Fourier Transform (FFT) of convex mass boundary. During the development of the application, the Mammographic Image Analysis Society (MIAS) database, which is available to the researchers, is used. The MIAS database contains 322, 1024x1024 pixel resolution images of normal, benign, and malignant cancer. In the first phase of the study, noise reduction and image enhancement process is performed on the images. The pectoral muscles, which have similar features as region of interests (ROIs) are decomposed. After the decomposition process, images are enhanced by contrast to clarify ROIs. From ROIs, Zernike moments and FFT of convex mass boundary are calculated and feature vectors are obtained for each image. The new feature vector of each image was divided into training and test sets, and the labels of the test set were obtained with 100% accuracy. |
