A study of different texture features based on local operator for benign-malignant mass classification Conference Paper
| Authors: | Rabidas, R.; Midya, A.; Chakraborty, J.; Arif, W. |
| Editors: | Mathew, J.; Krishna, D. D.; Jose, J. |
| Title: | A study of different texture features based on local operator for benign-malignant mass classification |
| Conference Title: | 6th International Conference On Advances In Computing and Communications, ICACC 2016 |
| Abstract: | In this paper, a comparative analysis of different texture features based on local operator has been produced for the determination of mammographic masses as benign or malignant. Local Binary Pattern (LBP), LBP Variance (LBPV), and Completed LBP (CLBP) descriptors are extracted to evaluate their potential for mass classification in a Computer-Aided Diagnosis (CAD) system. An Az value of 0.97 ± 0.02 and an accuracy of 92.25 ± 0.01% have been achieved, while experimenting on 200 mass cases from the DDSM database, by selecting the optimal set of features employing stepwise logistic regression method, followed by classification via Fisher Linear Discriminant Analysis (FLDA) using 10-fold cross validation. © 2016 The Authors. Published by Elsevier B.V. |
| Keywords: | breast cancer; mammography; discriminant analysis; regression analysis; computer aided diagnosis; classification (of information); bins; local binary patterns; completed lbp(clbp); lbp variance(lbpv); local binary pattern(lbp); mass classification; content based retrieval; face recognition; mass classifications |
| Journal Title | Procedia Computer Science |
| Volume: | 93 |
| Conference Dates: | 2016 Sep 6-8 |
| Conference Location: | Kochi, India |
| ISBN: | 1877-0509 |
| Publisher: | Elsevier Inc. |
| Date Published: | 2016-01-01 |
| Start Page: | 389 |
| End Page: | 395 |
| Language: | English |
| DOI: | 10.1016/j.procs.2016.07.225 |
| PROVIDER: | scopus |
| DOI/URL: | |
| Notes: | Conference Paper -- Conference code: 131418 -- Export Date: 3 October 2016 -- Source: Scopus |
