Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques

Arnav Sanjay Karnik; Nikhil Nair; Arham Dugar; V. G. Narendra

doi:10.1109/ICMLAS64557.2025.10968607

Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques

Arnav Sanjay Karnik
, Nikhil Nair
, Arham Dugar
, V. G. Narendra

School of Computer Engineering

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

Abstract

This study explores a feature-engineering approach for classifying skin lesions as benign or malignant. Many other approaches regarding feature extraction can be applied: color, texture, shape, Gabor filters, Histogram of Oriented Gradients (HOG), edge density, fractal dimension, wavelet analysis, and entropy. It then gives a computationally efficient alternative instead of deep learning models. A soft-voting approach based on an ensemble of machine learning classifiers: SVM, MLP, and Random Forest is proposed. The accuracy of the classification task is significantly improved through the soft-voting approach.

Original language	English
Title of host publication	2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	25-33
Number of pages	9
ISBN (Electronic)	9798331505745
DOIs	https://doi.org/10.1109/ICMLAS64557.2025.10968607
Publication status	Published - 2025
Event	2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Bangkok, Thailand Duration: 10-03-2025 → 12-03-2025

Publication series

Name	2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings

Conference

Conference	2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025
Country/Territory	Thailand
City	Bangkok
Period	10-03-25 → 12-03-25

All Science Journal Classification (ASJC) codes

Control and Optimization
Health Informatics
Artificial Intelligence
Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems and Management

Access to Document

10.1109/ICMLAS64557.2025.10968607

Cite this

Karnik, A. S., Nair, N., Dugar, A., & Narendra, V. G. (2025). Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques. In 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings (pp. 25-33). (2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMLAS64557.2025.10968607

Karnik, Arnav Sanjay ; Nair, Nikhil ; Dugar, Arham et al. / Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques. 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. pp. 25-33 (2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings).

@inproceedings{0ef94c961bce4ed58ef2ed0188a813a7,

title = "Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques",

abstract = "This study explores a feature-engineering approach for classifying skin lesions as benign or malignant. Many other approaches regarding feature extraction can be applied: color, texture, shape, Gabor filters, Histogram of Oriented Gradients (HOG), edge density, fractal dimension, wavelet analysis, and entropy. It then gives a computationally efficient alternative instead of deep learning models. A soft-voting approach based on an ensemble of machine learning classifiers: SVM, MLP, and Random Forest is proposed. The accuracy of the classification task is significantly improved through the soft-voting approach.",

author = "Karnik, \{Arnav Sanjay\} and Nikhil Nair and Arham Dugar and Narendra, \{V. G.\}",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 ; Conference date: 10-03-2025 Through 12-03-2025",

year = "2025",

doi = "10.1109/ICMLAS64557.2025.10968607",

language = "English",

series = "2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "25--33",

booktitle = "2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings",

address = "United States",

}

Karnik, AS, Nair, N, Dugar, A & Narendra, VG 2025, Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques. in 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings. 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 25-33, 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025, Bangkok, Thailand, 10-03-25. https://doi.org/10.1109/ICMLAS64557.2025.10968607

Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques. / Karnik, Arnav Sanjay; Nair, Nikhil; Dugar, Arham et al.
2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2025. p. 25-33 (2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings).

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

TY - GEN

T1 - Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques

AU - Karnik, Arnav Sanjay

AU - Nair, Nikhil

AU - Dugar, Arham

AU - Narendra, V. G.

PY - 2025

Y1 - 2025

N2 - This study explores a feature-engineering approach for classifying skin lesions as benign or malignant. Many other approaches regarding feature extraction can be applied: color, texture, shape, Gabor filters, Histogram of Oriented Gradients (HOG), edge density, fractal dimension, wavelet analysis, and entropy. It then gives a computationally efficient alternative instead of deep learning models. A soft-voting approach based on an ensemble of machine learning classifiers: SVM, MLP, and Random Forest is proposed. The accuracy of the classification task is significantly improved through the soft-voting approach.

AB - This study explores a feature-engineering approach for classifying skin lesions as benign or malignant. Many other approaches regarding feature extraction can be applied: color, texture, shape, Gabor filters, Histogram of Oriented Gradients (HOG), edge density, fractal dimension, wavelet analysis, and entropy. It then gives a computationally efficient alternative instead of deep learning models. A soft-voting approach based on an ensemble of machine learning classifiers: SVM, MLP, and Random Forest is proposed. The accuracy of the classification task is significantly improved through the soft-voting approach.

UR - https://www.scopus.com/pages/publications/105004804922

UR - https://www.scopus.com/pages/publications/105004804922#tab=citedBy

U2 - 10.1109/ICMLAS64557.2025.10968607

DO - 10.1109/ICMLAS64557.2025.10968607

M3 - Conference contribution

AN - SCOPUS:105004804922

T3 - 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings

SP - 25

EP - 33

BT - 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

Y2 - 10 March 2025 through 12 March 2025

ER -

Karnik AS, Nair N, Dugar A, Narendra VG. Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques. In 2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2025. p. 25-33. (2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025 - Proceedings). doi: 10.1109/ICMLAS64557.2025.10968607

Skin Lesion Classification Using Feature Extraction and Ensemble Machine Learning Techniques

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this