{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:13:06Z","timestamp":1778494386986,"version":"3.51.4"},"reference-count":0,"publisher":"International Association of Online Engineering (IAOE)","issue":"05","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Onl. Eng."],"abstract":"<jats:p>Cervical cancer remains a major cause of mortality among women, particularly in low-resource settings, highlighting the need for reliable image-based screening methods. Visual Inspection with Acetic Acid (VIA) is widely used in clinical practice; however, its diagnostic accuracy strongly depends on operator experience and subjective interpretation. This study systematically evaluates a multi-representation feature extraction framework for cervical pre-cancer image classification by comparing three paradigms: conventional handcrafted features, convolutional neural network (CNN)-based deep features from pre-trained networks, and hybrid features combining both representations. Experiments are conducted on three image representations, namely original VIA images, Frangi-filtered images, and morphology-based vessel images, using AlexNet, ResNet-50, and EfficientNet as deep feature extractors. All feature representations are classified using KNN and SVM under a strict evaluation protocol. The results show that hybrid feature extraction performs best on original images, with HybridAlexNet achieving an accuracy, sensitivity, and specificity of 0.84. The findings indicate that representation-aware hybrid feature design provides a robust and interpretable solution for screening-oriented cervical pre-cancer detection.<\/jats:p>","DOI":"10.3991\/ijoe.v22i05.59729","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T09:45:05Z","timestamp":1778492705000},"source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Representation Hybrid CNN Feature Extraction Framework for Cervical Pre-Cancer Image Classification"],"prefix":"10.3991","volume":"22","author":[{"given":"Hilman","family":"Fauzi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8370-9434","authenticated-orcid":false,"given":"Salsabila","family":"Aurellia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Fenty Alia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"2371","published-online":{"date-parts":[[2026,5,11]]},"container-title":["International Journal of Online and Biomedical Engineering (iJOE)"],"original-title":[],"link":[{"URL":"https:\/\/online-journals.org\/index.php\/i-joe\/article\/download\/59729\/17237","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/online-journals.org\/index.php\/i-joe\/article\/download\/59729\/17237","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T09:45:05Z","timestamp":1778492705000},"score":1,"resource":{"primary":{"URL":"https:\/\/online-journals.org\/index.php\/i-joe\/article\/view\/59729"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":0,"journal-issue":{"issue":"05","published-online":{"date-parts":[[2026,5,11]]}},"URL":"https:\/\/doi.org\/10.3991\/ijoe.v22i05.59729","relation":{},"ISSN":["2626-8493"],"issn-type":[{"value":"2626-8493","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]}}}