Informatics Publishing Limited

Mohsen A. M. El-Bendary ¹, H. Abdellatif ², M. El-Tokgy ², T. E. Taha ², Sayed M. EL-Rabaie ², O. F. Zahran ², W. Al-Nauimy ³, Saleh Ahmad ², F. E. Abd El-Samie ²

Affiliations
1 Department of Electronics Technology, Helwan University, Cairo, EG
2 Menofia University, EG
3 Electrical Engineering and Electronics, University of Liverpool, Brownlow Hill, L693GJ, Liverpool, GB

Abstract

Mammography is well known method for detection of breast tumors. Early detection and removal of the primary tumor is an essential and effective method to enhance survival rate and reduce mortality. Breast tumor segmentation is needed for monitoring and quantifying breast cancer. However, automated tumor segmentation in mammograms poses many challenges with regard to characteristics of an image. In this paper we propose a fully automatic algorithm for segmentation of a breast masses, using two types of image segmentation, Normalized graph cuts to delineate pectoral muscle and optimal threshold based on the two-dimensional entropy for masses detection.

Keywords

Mammography, Image Segmentation, Thresholding, Entropy, Normalized Graph Cuts.

Full Text

     

A. A. Mahmoud ¹, S. EL. Rabaie ², T. E. Taha ², F. E. Abd El-Samie ³, O. Zahran ², W. Al-Nauimy ⁴

Affiliations
1 Department of Electronics and Electrical Communications, Menoufia University, 32952, Menouf, EG
2 Department of Electronics and Electrical Communications, Menoufia University, 32952, Menouf, EG
3 Department of Electronics and Electrical Communications, Menoufia University, 32952, Menouf, EG
4 University of Liverpool, GB

Abstract

Image denoising involves processing of the image data to produce a visually high quality image. The denoising algorithms may be classified into two categories, spatial filtering algorithms (Wiener filter, Gaussian filter, Gabor filter and Median filter) and wavelet based algorithms (Wiener filter in the wavelet domain and Log Gabor filter in the wavelet domain). In this paper a comparative study for the previous mentioned algorithms based on calculating the Peak Signal to Noise Ratio (PSNR) value as a metric since for such images the visual evaluation is not appropriate. The quantitative results of comparison are tabulated by calculating the PSNR of the output image.

Keywords

PSNR, DWT.

Full Text