Analisis Citra Digital Untuk Ekstraksi Ciri Kemiringan Dan Ketebalan Tulisan Tangan Berdasarkan Grafologi Konvensional
DOI:
https://doi.org/10.29407/gcj37374Abstract
Grafologi konvensional memanfaatkan karakteristik fisik tulisan tangan sebagai sumber informasi, namun proses pengukurannya masih banyak dilakukan secara manual sehingga rentan terhadap subjektivitas. Penelitian ini bertujuan mengimplementasikan pengolahan citra digital untuk mengekstraksi ciri kemiringan dan ketebalan tulisan tangan secara otomatis. Dataset yang digunakan terdiri dari 108 citra tulisan tangan yang berasal dari empat kelompok data, yaitu EKONOMI, KESEHATAN, SOSHUM, dan TEKNIK. Tahapan penelitian meliputi preprocessing citra menggunakan grayscale, Gaussian blur, thresholding, dan edge detection, dilanjutkan dengan segmentasi baseline serta ekstraksi fitur. Kemiringan tulisan dihitung menggunakan metode PCA Orientation, sedangkan ketebalan tulisan dihitung menggunakan Pixel Density Analysis. Hasil pengujian menunjukkan bahwa seluruh citra berhasil diproses dengan tingkat keberhasilan 100%. Nilai rata-rata kemiringan tulisan sebesar 13,44° dan rata-rata ketebalan tulisan sebesar 0,007839. Selain itu, waktu komputasi rata-rata metode PCA Orientation sebesar 0,02065 detik per citra. Hasil penelitian menunjukkan bahwa metode yang digunakan mampu menghasilkan data karakteristik tulisan tangan secara cepat dan konsisten.
Keywords:
pengolahan citra digital, PCA Orientation, Pixel Density Analysis, tulisan tangan.##plugins.themes.default.displayStats.downloads##
References
[1] S. Mukherjee and I. Ghosh, “Automated Personality Analysis from Handwriting: A
Systematic Survey,” SN Computer Science, vol. 6, 2025, doi: 10.1007/s42979-025-04150-7.
[2] I. Maulana, I. Y. Mustofa, D. P. Pamungkas, and C. I. Isniawan, “Identifikasi Kepribadian
Dari Tulisan Tangan Menggunakan Euclidean Distance,” Prosiding Seminar Nasional
Inovasi Teknologi, 2023.
[3] S. B. Bhaskoro, R. A. Pratama, and S. A. H. Darmawan, “Deteksi dan Interpretasi Tulisan
Tangan Bahasa Indonesia melalui Pemrosesan Citra dan Optical Character Recognition
(OCR),” JTRM (Jurnal Teknologi dan Rekayasa Manufaktur), vol. 7, no. 1, pp. 48–64, 2025,
doi: 10.48182/jtrm.v7i1.193.
[4] F. Syah et al., “Implementasi CNN untuk Penerjemahan Bahasa melalui Pengenalan Citra
Tulisan Tangan,” Jurnal Dinamika Informatika, vol. 13, no. 2, 2024.
[5] D. T. Susetianingtias, D. Pernadi, E. Patriya, and R. Arianty, “The Implementation of
Artificial Neural Network (ANN) on Offline Cursive Handwriting Image Recognition,”
ILKOM Jurnal Ilmiah, vol. 14, no. 1, pp. 63–73, 2022, doi: 10.33096/ilkom.v14i1.1113.63-
73.
[6] D. T. Susetianingtias, R. Arianty, and E. Patriya, “Pembentukan Model Recurrent Neural
Network dan Connectionist Temporal Classification pada Pengenalan Kata Tulisan Tangan
Offline,” Decode: Jurnal Pendidikan Teknologi Informasi, vol. 3, no. 2, pp. 172–183, 2023.
[7] I. Kurniastuti et al., “Improved Edge Detection Using Morphological Operation and Adaptive
Thresholding for Image Segmentation,” Journal of Electrical Engineering, Electronics,
Informatics, and Medical Engineering, vol. 7, no. 1, 2025.
[8] “Segmentasi Teks pada Citra Tulisan Tangan Kalimat Menggunakan Metode Connected
Component,” Jurnal Teknosains, 2024.
[9] N. Khunafa Qudsi et al., “Identifikasi Citra Tulisan Tangan Digital Menggunakan
Convolutional Neural Network (CNN),” 2023.
[10] S. Mahadevkar, S. Patil, and K. Kotecha, “Enhancement of Handwritten Text
Recognition Using AI-Based Hybrid Approach,” MethodsX, vol. 12, 2024, doi:
10.1016/j.mex.2024.102654.
[11] I. Riadi et al., “Identifikasi Tulisan Tangan Huruf Katakana Jepang Dengan Metode
Euclidean,” J-SAKTI (Jurnal Sains Komputer dan Informatika), vol. 4, no. 1, pp. 29–37, 2020.
[12] R. Lu et al., “Correction of Slanted Text Pictures Based on Modified OpenCV,” Taiwan
Ubiquitous Information, vol. 6, no. 2, 2021.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
