Digital Mammograms Classification Using a Wavelet Based Feature Extraction Method

Faye, Ibrahima and Brahim Belhaouari , Samir and Eltoukhy, Mohamed M. M. (2009) Digital Mammograms Classification Using a Wavelet Based Feature Extraction Method. In: International Conference Computer and Electrical Engineering.

[img] PDF
Restricted to Registered users only



This paper introduces a new method of feature extraction from Wavelet coefficients for classification of digital mammograms. A matrix is constructed by putting Wavelet coefficients of each image of a building set as a row vector. The method consists then on selecting by threshold, the columns which will maximize the Euclidian distances between the different class representatives. The selected columns are then used as features for classification. The method is tested using a set of images provided by the Mammographic Image Analysis Society (MIAS) to classify between normal and abnormal and then between benign and malignant tissues. For both classifications, a high accuracy rate (98%) is achieved.

Item Type:Conference or Workshop Item (Paper)
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments / MOR / COE:Centre of Excellence > Center for Intelligent Signal and Imaging Research
Departments > Fundamental & Applied Sciences
ID Code:7872
Deposited By: Dr Ibrahima Faye
Deposited On:14 Aug 2012 03:09
Last Modified:19 Jan 2017 08:25

Repository Staff Only: item control page

Document Downloads

More statistics for this item...