A comparative analysis of HOG and LBP feature extraction techniques in AdaBoost for image recognition

Aziz Ilyas Ozturk () and Osman Yildirim ()

International Journal of Innovative Research and Scientific Studies, 2025, vol. 8, issue 2, 696-703

Abstract: Arachnoid cysts are cerebrospinal fluid-filled sacs located between the brain or spinal cord and the arachnoid membrane. Detection of these cysts is critical for early diagnosis and treatment planning. In this study, deep learning algorithms were developed and applied to improve the detection of arachnoid cysts in brain MRI scans. Two separate feature extraction methods, namely Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG), combined with the AdaBoost classifier, were tested. The results showed that the AdaBoost classifier with LBP achieved an accuracy of 0.77, while the AdaBoost classifier with HOG performed significantly better with an accuracy of 0.95. These findings suggest that HOG features are more effective in distinguishing arachnoid cysts from normal brain tissue. This study contributes to the growing body of research on automatic brain anomaly detection and highlights the potential for improving diagnostic accuracy using advanced machine learning techniques.

Keywords: AdaBoost; Arachnoid cyst; Histogram of oriented gradients; Local binary patterns. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijirss.com/index.php/ijirss/article/view/5290/881 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:aac:ijirss:v:8:y:2025:i:2:p:696-703:id:5290

Access Statistics for this article

International Journal of Innovative Research and Scientific Studies is currently edited by Natalie Jean

More articles in International Journal of Innovative Research and Scientific Studies from Innovative Research Publishing
Bibliographic data for series maintained by Natalie Jean ().