IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - Vocational School
      • UF - Software Engineering Technology
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - Vocational School
      • UF - Software Engineering Technology
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Pengembangan Verify id Berbasis V-Model dengan Integrasi Donut dan DeepFace untuk Evaluasi Performa Multimodal

      Thumbnail
      View/Open
      Cover (357.1Kb)
      Fulltext (2.256Mb)
      Lampiran (3.694Mb)
      Date
      2026
      Author
      Devyanti, Kharisma Nur
      Fami, Amata
      Metadata
      Show full item record
      Abstract
      Penelitian ini bertujuan untuk mengembangkan Verify id, aplikasi verifikasi identitas digital untuk mengatasi pemalsuan data dan penipuan wajah (face spoofing) pada pendaftaran online. Menggunakan metode V-Model, aplikasi ini menggabungkan tiga teknologi utama lewat sistem keputusan satu pintu (Late Fusion). Teknologi tersebut adalah model Donut untuk membaca teks KTP, DeepFace dengan algoritma ArcFace untuk mencocokkan wajah, serta fitur liveness detection untuk memastikan keaslian wajah. Hasil pengujian fitur dengan Black Box Testing pada 50 skenario menunjukkan tingkat keberhasilan penuh sebesar 100%. Uji performa menggunakan matriks konfusi juga menghasilkan nilai sempurna sebesar 1,00 pada semua parameter (Precision, Recall, dan F1-Score). Meskipun kemampuan model Donut dalam membaca teks terbatas pada angka 73,07%, sistem Late Fusion terbukti mampu menjaga ketepatan keputusan akhir dengan mengutamakan hasil verifikasi wajah yang bernilai positif. Dengan demikian, aplikasi Verify id dinyatakan valid dan siap digunakan sebagai solusi verifikasi identitas yang aman serta akurat.
       
      This study aimed to develop Verify id, a digital identity verification application to address data forgery and facial fraud (face spoofing) in online registration. Using the V-Model method, this application combines three core technologies through a single-gate decision system (late fusion). These technologies are the Donut model for ID card text extraction, DeepFace with the ArcFace algorithm for facial matching, and a liveness detection feature to ensure facial authenticity. Feature testing results using Black Box Testing on 50 scenarios show a full success rate of 100%. Performance testing using a confusion matrix also yields a perfect score of 1.00 for all parameters (Precision, Recall, and F1-Score). Although the Donut model text reading ability is limited to 73.07%, the Late Fusion system successfully maintains final decision accuracy by prioritizing positive facial verification results. Consequently, the Verify id application is declared valid and ready for deployment as a secure and accurate identity verification solution.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/179235
      Collections
      • UF - Software Engineering Technology [307]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository