eprintid: 19347
rev_number: 7
eprint_status: archive
userid: 6
dir: disk0/00/01/93/47
datestamp: 2016-02-16 03:42:06
lastmod: 2016-02-16 03:42:06
status_changed: 2016-02-16 03:42:06
type: article
metadata_visibility: show
creators_name: SHOFWATUL ‘UYUN, DKK
title: SELECTION MAMMOGRAM TEXTURE DESCRIPTORS BASED ON STATISTICS PROPERTIES BACKPROPAGATION STRUCTURE
ispublished: pub
subjects: sains
divisions: artkl
full_text_status: public
keywords: feature, extraction, mammogram, classification
abstract: Computer Aided Diagnosis (CAD) system has been developed for the early detection of breast cancer, one of the most deadly cancer for women. The benign of mammogram has different texture from malignant. There are fifty mammogram images used in this work which are divided for training and testing. Therefore, the selection of the right texture to determine the level of accuracy of CAD system is important. The first and second order statistics are the texture feature extraction methods which can be used on a mammogram. This work classifies texture descriptor into nine groups where the extraction of features is classified using backpropagation learning with two types of multi-layer perceptron (MLP). The best texture descriptor as selected when the value of regression 1 appears in both the MLP-1 and the MLP-2 with the number of epoches less than 1000. The results of testing show that the best selected texture descriptor is the second order (combination) using all direction that have twenty four descriptors.
Keywords : feature, extraction, mammogram, classification
date: 2013-05-01
date_type: published
publication: IJCSIS International Journal of Computer Science and Information Security
volume: Vol. 1
number: No. 5
publisher: IJCSIS International Journal of Computer Science and Information Security
pagerange: 1-5
id_number: http://sites.google.com/site/ijcsis/
refereed: TRUE
issn: 1947-5500
citation:   SHOFWATUL ‘UYUN, DKK  (2013) SELECTION MAMMOGRAM TEXTURE DESCRIPTORS BASED ON STATISTICS PROPERTIES BACKPROPAGATION STRUCTURE.  IJCSIS International Journal of Computer Science and Information Security, Vol. 1 (No. 5).  pp. 1-5.  ISSN 1947-5500     
document_url: https://digilib.uin-suka.ac.id/id/eprint/19347/1/SHOFWATUL%20%E2%80%98UYUN%2C%20DKK%20-%20SELECTION%20MAMMOGRAM%20TEXTURE%20DESCRIPTORS%20BASED%20ON%20STATISTICS%20PROPERTIES%20BACKPROPAGATION%20STRUCTURE.pdf