Classification of Skin Cancer Images Using Local Binary Pattern and SVM Classifier

Faouzi Adjed; Ibrahima Faye; Fakhreddine Ababsa; Syed Jamal Gardezi; Sarat Chandra Dass

doi:10.1063/1.4968145

Classification of Skin Cancer Images Using Local Binary Pattern and SVM Classifier

Faouzi Adjed
, Ibrahima Faye
, Fakhreddine Ababsa
, Syed Jamal Gardezi
, Sarat Chandra Dass

School of Mathematical & Computer Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

22 Citations (Scopus)

Abstract

In this paper, a classification method for melanoma and non-melanoma skin cancer images has been presented using the local binary patterns (LBP). The LBP computes the local texture information from the skin cancer images, which is later used to compute some statistical features that have capability to discriminate the melanoma and non-melanoma skin tissues. Support vector machine (SVM) is applied on the feature matrix for classification into two skin image classes (malignant and benign). The method achieves good classification accuracy of 76.1% with sensitivity of 75.6% and specificity of 76.7%.

Original language	English
Title of host publication	Proceeding of the 4th International Conference of Fundamental and Applied Sciences 2016
Publisher	AIP Publishing
ISBN (Print)	9780735414518
DOIs	https://doi.org/10.1063/1.4968145
Publication status	Published - 1 Nov 2016

Publication series

Name	AIP Conference Proceedings
Number	1
Volume	1787
ISSN (Print)	0094-243X

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1063/1.4968145

Cite this

@inproceedings{a2aaa9076f184c288f3baf663fdaa3c9,

title = "Classification of Skin Cancer Images Using Local Binary Pattern and SVM Classifier",

abstract = "In this paper, a classification method for melanoma and non-melanoma skin cancer images has been presented using the local binary patterns (LBP). The LBP computes the local texture information from the skin cancer images, which is later used to compute some statistical features that have capability to discriminate the melanoma and non-melanoma skin tissues. Support vector machine (SVM) is applied on the feature matrix for classification into two skin image classes (malignant and benign). The method achieves good classification accuracy of 76.1\% with sensitivity of 75.6\% and specificity of 76.7\%.",

author = "Faouzi Adjed and Ibrahima Faye and Fakhreddine Ababsa and Gardezi, \{Syed Jamal\} and Dass, \{Sarat Chandra\}",

year = "2016",

month = nov,

day = "1",

doi = "10.1063/1.4968145",

language = "English",

isbn = "9780735414518",

series = "AIP Conference Proceedings",

publisher = "AIP Publishing",

number = "1",

booktitle = "Proceeding of the 4th International Conference of Fundamental and Applied Sciences 2016",

address = "United States",

}

Classification of Skin Cancer Images Using Local Binary Pattern and SVM Classifier. / Adjed, Faouzi; Faye, Ibrahima; Ababsa, Fakhreddine et al.
Proceeding of the 4th International Conference of Fundamental and Applied Sciences 2016. AIP Publishing, 2016. 080006 (AIP Conference Proceedings; Vol. 1787, No. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Classification of Skin Cancer Images Using Local Binary Pattern and SVM Classifier

AU - Adjed, Faouzi

AU - Faye, Ibrahima

AU - Ababsa, Fakhreddine

AU - Gardezi, Syed Jamal

AU - Dass, Sarat Chandra

PY - 2016/11/1

Y1 - 2016/11/1

N2 - In this paper, a classification method for melanoma and non-melanoma skin cancer images has been presented using the local binary patterns (LBP). The LBP computes the local texture information from the skin cancer images, which is later used to compute some statistical features that have capability to discriminate the melanoma and non-melanoma skin tissues. Support vector machine (SVM) is applied on the feature matrix for classification into two skin image classes (malignant and benign). The method achieves good classification accuracy of 76.1% with sensitivity of 75.6% and specificity of 76.7%.

AB - In this paper, a classification method for melanoma and non-melanoma skin cancer images has been presented using the local binary patterns (LBP). The LBP computes the local texture information from the skin cancer images, which is later used to compute some statistical features that have capability to discriminate the melanoma and non-melanoma skin tissues. Support vector machine (SVM) is applied on the feature matrix for classification into two skin image classes (malignant and benign). The method achieves good classification accuracy of 76.1% with sensitivity of 75.6% and specificity of 76.7%.

U2 - 10.1063/1.4968145

DO - 10.1063/1.4968145

M3 - Conference contribution

SN - 9780735414518

T3 - AIP Conference Proceedings

BT - Proceeding of the 4th International Conference of Fundamental and Applied Sciences 2016

PB - AIP Publishing

ER -

Classification of Skin Cancer Images Using Local Binary Pattern and SVM Classifier

Abstract

Publication series

UN SDGs

Access to Document

Fingerprint

Cite this