Detection and Classification of Alopecia Areata Using Diverse Feature-Set

Authors

  • Amna Noreen University of Engineering and Technology Taxila, Pakistan
  • Haider Khan University of Engineering and Technology Taxila, Pakistan
  • Syed M Adnan Shah University of Engineering and Technology Taxila, Pakistan
  • Wakeel Ahmed University of Engineering and Technology Taxila, Pakistan
  • Syed Haseeb Amjad University of Engineering and Technology Taxila, Pakistan

Keywords:

machine learning, Deep Learning, computer vision, Image processing, Classification

Abstract

Alopecia areata is a prevalent autoimmune disorder resulting in hair loss on the scalp and other body parts, affecting millions worldwide. This condition can significantly impact one's psychological well-being and self-esteem, highlighting the importance of early detection for better disease management and potential hair regrowth. This study uses computer vision techniques to propose a comprehensive method for detecting alopecia areata from camera images. Two distinct datasets, Dermnet for alopecia areata images and Figaro1k for healthy images are employed, with a preprocessing phase involving histogram equalization to enhance image quality. Subsequently, color, texture, and shape features are extracted from the images, followed by feature fusion and selection to maximize the discriminative power of the dataset. Several popular classifiers, such as Random Forest, SVM, Decision Tree, Logistic Regression, Naive Bayes, ANN, and KNN, are employed to identify the most effective models. The proposed technique achieves a remarkable accuracy of 96.43%, outperforming related research methods. This study shows considerable promise for improving the early detection and treatment of Alopecia Areata by utilizing sophisticated computer vision and machine learning methods, leading to enhanced patient outcomes and a better quality of life.

Author Biographies

Amna Noreen, University of Engineering and Technology Taxila, Pakistan

I am Amna Noreen, and I have completed my Master’s degree from the Department of Computer Science, UET Taxila. My thesis was titled "Diagnosis of Alopecia Areata using Computer vision techniques" As the first author, I am highly motivated to publish my paper in this journal, as the scope and objectives of my article align well with the journal’s aims and scope.

Haider Khan, University of Engineering and Technology Taxila, Pakistan

Hi i am haider khan, who has also completed a Master’s degree in Computer Science from UET Taxila. He has contributed significantly to this research work and played an active role in the development and writing of this paper.

Syed M Adnan Shah, University of Engineering and Technology Taxila, Pakistan

The third author is Dr. Syed M .Adnan Shah, an Associate Professor in the Department of Computer Science at UET Taxila. He served as the supervisor for this research and provided valuable guidance, feedback, and contributions throughout the development of the paper.

Wakeel Ahmed, University of Engineering and Technology Taxila, Pakistan

The fourth author is Dr. Wakeel Ahmed, also a supervisor and faculty member at the Department of Computer Science, UET Taxila. He contributed valuable insights, reviewed the manuscript, and guided the research in terms of direction and technical depth.

Syed Haseeb Amjad, University of Engineering and Technology Taxila, Pakistan

The fifth author is Syed Haseeb Amjad, who has also completed a Master’s degree in Computer Science from UET Taxila. He was actively involved in the research process and contributed to the development, analysis, and writing of the paper.

Downloads

Published

2025-06-27

How to Cite

Amna Noreen, Haider Khan, Syed M Adnan Shah, Wakeel Ahmed, & Syed Haseeb Amjad. (2025). Detection and Classification of Alopecia Areata Using Diverse Feature-Set. Journal of Computers and Intelligent Systems, 3(2), 92–106. Retrieved from https://journals.iub.edu.pk/index.php/JCIS/article/view/3763