Open AccessA Hybrid the Nonsubsampled Contourlet Transform and Homomorphic Filtering for Enhancing Mammograms
Author(s) -
Khaddouj Taifi,
Rachid Ahdid,
Mohamed Fakir,
Saïd Safi
Publication year - 2015
Publication title -
telkomnika: indonesian journal of electrical engineering/telkomnika
Language(s) - English
Resource type - Journals
eISSN - 2460-7673
pISSN - 2302-4046
DOI - 10.11591/tijee.v16i3.1645
Subject(s) - homomorphic filtering , mammography , computer science , artificial intelligence , microcalcification , contourlet , unsharp masking , pattern recognition (psychology) , digital mammography , computer vision , measure (data warehouse) , image enhancement , wavelet transform , breast cancer , image (mathematics) , data mining , wavelet , medicine , cancer
Mammogram is important for early breast cancer detection. But due to the low contrast of microcalcifications and noise, it is difficult to detect microcalcification. This paper presents a comparative study in digital mammography image enhancement based on three different algorithms: homomorphic filtering, unsharp masking and our proposed methods. This latter use a hybrid method Combining contourlet and homomorphic filtering. Performance of the given technique has been measured in terms of distribution separation measure (DSM), target-to-background enhancement measure based on standard deviation (TBES) and target-to-background enhancement measure based on entropy (TBEE). The proposed methods were tested with the referents mammography data Base MiniMIAS. Experimental results show that the proposed method improves the visibility of microcalcification.