Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis

Automated skin lesion classification using machine learning techniques is crucial for early and accurate skin cancer detection. This study proposes a hybrid method combining the Hermite, Radial Fourier–Mellin, and Hilbert transform to extract comprehensive features from skin lesion images. By separa...

Full description

Saved in:
Bibliographic Details
Main Authors: Luis Felipe López-Ávila, Josué Álvarez-Borrego
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/5860
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129865190146048
author Luis Felipe López-Ávila
Josué Álvarez-Borrego
author_facet Luis Felipe López-Ávila
Josué Álvarez-Borrego
author_sort Luis Felipe López-Ávila
collection DOAJ
description Automated skin lesion classification using machine learning techniques is crucial for early and accurate skin cancer detection. This study proposes a hybrid method combining the Hermite, Radial Fourier–Mellin, and Hilbert transform to extract comprehensive features from skin lesion images. By separating the images into red, green, and blue (RGB) channels and grayscale, unique textural and structural information specific to each channel is analyzed. The Hermite transform captures localized spatial features, while the Radial Fourier–Mellin and Hilbert transforms ensure global invariance to scale, translation, and rotation. Texture information for each channel is also obtained based on the Local Binary Pattern (<i>LBP</i>) technique. The proposed hybrid transform-based feature extraction was applied to multiple lesion classes using the International Skin Imaging Collaboration (ISIC) 2019 dataset, preprocessed with data augmentation. Experimental results demonstrate that the proposed method improves classification accuracy and robustness, highlighting its potential as a non-invasive AI-based tool for dermatological diagnosis.
format Article
id doaj-art-c87fd4c445574b839a4f896b90dd4522
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c87fd4c445574b839a4f896b90dd45222025-08-20T02:32:50ZengMDPI AGApplied Sciences2076-34172025-05-011511586010.3390/app15115860Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale AnalysisLuis Felipe López-Ávila0Josué Álvarez-Borrego1Centro de Investigación Científica y de Educación Superior de Ensenada, B. C. (CICESE), Carretera Ensenada-Tijuana No. 3918, Zona Playitas, Ensenada 22860, BC, MexicoCentro de Investigación Científica y de Educación Superior de Ensenada, B. C. (CICESE), Carretera Ensenada-Tijuana No. 3918, Zona Playitas, Ensenada 22860, BC, MexicoAutomated skin lesion classification using machine learning techniques is crucial for early and accurate skin cancer detection. This study proposes a hybrid method combining the Hermite, Radial Fourier–Mellin, and Hilbert transform to extract comprehensive features from skin lesion images. By separating the images into red, green, and blue (RGB) channels and grayscale, unique textural and structural information specific to each channel is analyzed. The Hermite transform captures localized spatial features, while the Radial Fourier–Mellin and Hilbert transforms ensure global invariance to scale, translation, and rotation. Texture information for each channel is also obtained based on the Local Binary Pattern (<i>LBP</i>) technique. The proposed hybrid transform-based feature extraction was applied to multiple lesion classes using the International Skin Imaging Collaboration (ISIC) 2019 dataset, preprocessed with data augmentation. Experimental results demonstrate that the proposed method improves classification accuracy and robustness, highlighting its potential as a non-invasive AI-based tool for dermatological diagnosis.https://www.mdpi.com/2076-3417/15/11/5860skin lesion classificationHermite transformradial Fourier–Mellin transform
spellingShingle Luis Felipe López-Ávila
Josué Álvarez-Borrego
Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis
Applied Sciences
skin lesion classification
Hermite transform
radial Fourier–Mellin transform
title Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis
title_full Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis
title_fullStr Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis
title_full_unstemmed Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis
title_short Hybrid Transform-Based Feature Extraction for Skin Lesion Classification Using RGB and Grayscale Analysis
title_sort hybrid transform based feature extraction for skin lesion classification using rgb and grayscale analysis
topic skin lesion classification
Hermite transform
radial Fourier–Mellin transform
url https://www.mdpi.com/2076-3417/15/11/5860
work_keys_str_mv AT luisfelipelopezavila hybridtransformbasedfeatureextractionforskinlesionclassificationusingrgbandgrayscaleanalysis
AT josuealvarezborrego hybridtransformbasedfeatureextractionforskinlesionclassificationusingrgbandgrayscaleanalysis