Pengenalan tulisan tangan huruf hijaiyah menggunakan ekstraksi fitur Scale-Invariant Feature Transform dan Support Vector Machine

Shidik, Tiara Oktaviani (2025) Pengenalan tulisan tangan huruf hijaiyah menggunakan ekstraksi fitur Scale-Invariant Feature Transform dan Support Vector Machine. Sarjana thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_cover.pdf

Download (57kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_abstrak.pdf

Download (160kB) | Preview
[img]
Preview
Text
3_skbebasplagiarism.pdf

Download (145kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
4_daftarisi.pdf

Download (53kB) | Preview
[img]
Preview
Text (BAB I)
5_bab1.pdf

Download (277kB) | Preview
[img] Text (BAB II)
6_bab2.pdf
Restricted to Registered users only

Download (338kB) | Request a copy
[img] Text (BAB III)
7_bab3.pdf
Restricted to Registered users only

Download (546kB) | Request a copy
[img] Text (BAB IV)
8_bab4.pdf
Restricted to Registered users only

Download (768kB) | Request a copy
[img] Text (BAB V)
9_bab5.pdf
Restricted to Registered users only

Download (102kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
10_daftarpustaka.pdf
Restricted to Registered users only

Download (119kB) | Request a copy
[img] Text (LAMPIRAN)
11_lampiran.pdf
Restricted to Repository staff only

Download (159kB) | Request a copy

Abstract

Penguasaan huruf Hijaiyah merupakan langkah awal yang sangat penting dalam proses literasi keagamaan umat Islam, terutama untuk membaca Al-Qur’an. Penelitian ini bertujuan untuk mengembangkan sistem otomatis yang mampu mengenali tulisan tangan huruf Hijaiyah, baik dalam bentuk huruf tunggal maupun sambung dua huruf, guna mendukung pembelajaran secara mandiri. Metode yang digunakan meliputi ekstraksi fitur menggunakan algoritma Scale-Invariant Feature Transform (SIFT) dan klasifikasi menggunakan Support Vector Machine (SVM), dengan representasi global melalui Bag of Visual Words (BoVW) dan Spatial Pyramid Matching (SPM). Data yang digunakan berasal dari dataset HMBD v1 dengan total 74 kelas huruf Hijaiyah dalam berbagai posisi penulisan. Pemodelan dilakukan melalui 12 skenario pengujian berdasarkan kombinasi parameter K, C, dan γ, serta dua jenis kernel SVM (RBF dan linier). Evaluasi model menggunakan teknik 2-fold cross-validation dan metrik akurasi, precision, recall, serta f1-score. Hasil penelitian menunjukkan bahwa kombinasi metode SIFT dan SVM mampu mengenali tulisan tangan huruf Hijaiyah dengan tingkat akurasi yang tinggi. Model terbaik diperoleh pada kombinasi parameter K = 128, C = 5, dan γ = 0.0001, dengan akurasi mencapai 97.89%, serta nilai precision, recall, dan f1-score masing-masing sebesar 98%. Sistem ini telah berhasil diimplementasikan dalam bentuk aplikasi web yang dapat digunakan secara mandiri oleh pengguna. Mastering Hijaiyah letters is a fundamental step in Islamic religious literacy, especially for reading the Qur’an. This study aims to develop an automated system capable of recognizing handwritten Hijaiyah letters, both single letters and two connected letters, to support independent learning. The method used includes feature extraction using the Scale-Invariant Feature Transform (SIFT) algorithm and classification using the Support Vector Machine (SVM), with global representation via Bag of Visual Words (BoVW) and Spatial Pyramid Matching (SPM). The data used is from the HMBD v1 dataset, consisting of 74 classes of Hijaiyah letters in various writing positions. Modeling was carried out through 12 testing scenarios based on combinations of parameters K, C, and γ, as well as two types of SVM kernels (RBF and linear). The model evaluation employed 2-fold cross-validation and performance metrics including accuracy, precision, recall, and f1-score. The results show that the combination of SIFT and SVM methods is capable of recognizing handwritten Hijaiyah letters with high accuracy. The best model was obtained with the combination K = 128, C = 5, and γ = 0.0001, achieving 97.89% accuracy and 98% for precision, recall, and f1-score. This system has been successfully implemented as a web-based application that can be used independently by learners.

Item Type: Thesis (Sarjana)
Uncontrolled Keywords: Huruf Hijaiyah; Pengenalan Tulisan Tangan; SIFT; SVM; BoVW; SPM
Subjects: Data Processing, Computer Science
Divisions: Fakultas Sains dan Teknologi > Program Studi Teknik Informatika
Depositing User: Tiara Oktaviani Shidik
Date Deposited: 28 Aug 2025 01:49
Last Modified: 28 Aug 2025 01:49
URI: https://digilib.uinsgd.ac.id/id/eprint/116399

Actions (login required)

View Item View Item