What question did this study set out to answer?

To evaluate the performance of AdaBoost classifier using handcrafted image features for automated skin disease diagnosis.

February 9, 2026Open Access

Performance Evaluation of Handcrafted Feature Descriptors with AdaBoost Classifier for Automated Skin Disease Diagnosis

Puntos clave

To evaluate the performance of AdaBoost classifier using handcrafted image features for automated skin disease diagnosis.
Assessed performance of six image feature extraction methods: Gabor Filter, JPEG Coefficient Filter, etc.
Utilized a dataset of 38,000 dermatological images across ten disease types.
Implemented 10-fold cross-validation for training within WEKA.
Evaluated using metrics like accuracy, precision, recall, and training time.
Gabor+AdaBoost achieved highest accuracy at 97.78% but had longer execution time of 14.4 seconds.
JPEGCF+AdaBoost maintained similar accuracy (97.59%) with a much quicker processing time of 0.21 seconds.
SCHF+AdaBoost provided 94.11% accuracy with rapid computing time of 0.06 seconds.

Resumen

The timely identification of dermatological diseases together with their precise diagnosis enables proper medical interventions that minimize further disease complications. The authors conduct a performance- based evaluation of AdaBoost classifier with handcrafted image features for automated skin disease classification systems. The researchers worked with a specific collection of 38,000 dermatological pictures which included ten different disease types from Melanoma to Eczema to Psoriasis to Fungal Infections. The research investigated six image feature extraction methods including Gabor Filter and JPEG Coefficient Filter (JPEGCF) and Pyramid Histogram of Oriented Gradients Filter (PHOGF) as well as Simple Color Histogram Filter (SCHF) and Fuzzy Color and Texture Histogram Filter (FCTH) with Fuzzy Opponent Histogram Filter (FOHF). The research used feature vectors extracted from AdaBoost classifiers in WEKA within 10-fold cross-validation procedures for training purposes. The evaluation metrics consisted of accuracy, precision, recall, ROC, PRC as well as training time. Within the examined models Gabor+AdaBoost demonstrated maximum rates of accuracy (97.78%) alongside precision (0.98) and recall (0.98) but it required the most execution time at 14.4s. When weighed against each other JPEGCF+AdaBoost maintained equivalent accuracy at 97.59% but required only 0.21 seconds to complete tasks thus earning status as a balanced choice for this system. SCHF+AdaBoost proved suitable for real-time operations by delivering 94.11% accuracy results within 0.06 seconds computing time. The study reveals that Gabor descriptors provide optimal predictive accuracy but JPEGCF along with SCHF demonstrate the best combination of performance with computational speed.

Me gusta

Guardar

Ver artículo completo