Technologie: Jurnal Sains dan Teknologi

Articles

Vol 1 No 1 (2026): Technologie: Jurnal Sains dan Teknologi

IDENTIFIKASI TULISAN TANGAN MENJADI TEKS DIGITAL MENGGUNAKAN ALGORITMA CNN

Telah diserahkan
April 20, 2026
Diterbitkan
2026-06-14

Abstrak

Digitization of handwritten documents is an essential component in digital transformation in various sectors. This research aims to develop a handwriting identification system into digital text using the Convolutional Neural Network (CNN) algorithm with architectural modifications in the form of adding residual connections. An experimental quantitative approach is applied with a dataset containing 50,000 handwritten images obtained from 500 respondents with diverse demographic distributions. Experimental results show that the proposed CNN architecture achieves 93.5% accuracy on the test dataset, an increase of 3.8% compared with conventional CNN. Performance analysis by character category revealed the highest accuracy in recognition of numbers (96.8%) and capital letters (95.3%), while special characters showed relatively lower accuracy (89.4%). The implementation of batch normalization and data augmentation strategies proved effective in improving the generalization of the model to variations in handwriting styles. Although the inference time increases slightly, this trade-off is acceptable considering the significant increase in accuracy. The main contribution of this research is the development of a robust handwriting recognition system with potential implementation in various applications such as digitizing historical archives, administrative document processing, and security systems based on handwriting biometrics.

Referensi

  1. Adhi Guna, E., Fransiska Sihombing, E., Nico Pasaribu, M., Syahputra, H., & Ramadhani, F. (2024). Implementasi Algoritma Cnn Dalam Mengidentifikasi Tingkat Keparahan Jerawat Pada Wajah. JATI (Jurnal Mahasiswa Teknik Informatika), 8(4), 5778–5782. https://doi.org/10.36040/jati.v8i4.10010
  2. Aryanto, R., Alfan Rosid, M., & Busono, S. (2023). Penerapan Deep Learning untuk Pengenalan Tulisan Tangan Bahasa Aksara Lota Ende dengan Menggunakan Metode Convolutional Neural Networks. Jurnal Informasi Dan Teknologi, 5(1), 258–264. https://doi.org/10.37034/jidt.v5i1.313
  3. Handoko, A. A., Rosid, M. A., & Indahyanti, U. (2024). Implementasi Convolutional Neural Network (CNN) Untuk Pengenalan Tulisan Tangan Aksara Bima. Smatika Jurnal, 14(01), 96–110. https://doi.org/10.32664/smatika.v14i01.1196
  4. Ibrahim, N. (2022). Klasifikasi Tingkat Kematangan Pucuk Daun Teh menggunakan Metode Convolutional Neural Network. ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, 10(1), 162. https://doi.org/10.26760/elkomika.v10i1.162
  5. Iglesias, L. L., Bellón, P. S., del Barrio, A. P., Fernández-Miranda, P. M., González, D. R., Vega, J. A., Mandly, A. A. G., & Blanco, J. A. P. (2021). A primer on deep learning and convolutional neural networks for clinicians. Insights into Imaging, 12(1). https://doi.org/10.1186/s13244-021-01052-z
  6. Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020). A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review, 53(8), 5455–5516. https://doi.org/10.1007/s10462-020-09825-6
  7. Pradana, A. I., & Wijiyanto, W. (2024). Identifikasi Jenis Kelamin Otomatis Berdasarkan Mata Manusia Menggunakan Convolutional Neural Network (CNN) dan Haar Cascade Classifier. G-Tech: Jurnal Teknologi Terapan, 8(1), 502–511. https://doi.org/10.33379/gtech.v8i1.3814
  8. Tilasefana, R. A., & Putra, R. E. (2023). Penerapan Metode Deep Learning Menggunakan Algoritma CNN Dengan Arsitektur VGG NET Untuk Pengenalan Cuaca. Journal of Informatics and Computer Science (JINACS), 05(1), 48–57.
  9. Toby Suwindra, M., Erlansari, A., & Supratman Kandang Limun, J. W. (2021). Analisis Kemiripan Jenis Burung Menggunakan Siamese Neural Network Analysis of Bird Species Similarity Using Siamese Neural Network. Jurnal Rekursif, 9(2). http://ejournal.unib.ac.id/index.php/rekursif/193
  10. Wahyuni, S., & Sulaeman, M. (2022). Penerapan Algoritma Deep Learning Untuk Sistem Absensi Kehadiran Deteksi Wajah Di PT Karya Komponen Presisi. Jurnal Informatika SIMANTIK, 7(1), 5–6. https://simantik.panca-sakti.ac.id/index.php/simantik/article/view/127
  11. Waldner, F., & Diakogiannis, F. I. (2020). Deep learning on edge: Extracting field boundaries from satellite images with a convolutional neural network. Remote Sensing of Environment, 245. https://doi.org/10.1016/j.rse.2020.111741
  12. Warjaya, A., Richi, A., Syahputra, H., & Ramadhani, F. (2024). Klasifikasi Citra Simbol Matematika Menggunakan Metode Convolution Neural Network (Cnn). JATI (Jurnal Mahasiswa Teknik Informatika), 8(4), 7226–7231. https://doi.org/10.36040/jati.v8i4.10234
  13. Yohannes, Y., Devella, S., & Arianto, K. (2020). Deteksi Penyakit Malaria Menggunakan Convolutional Neural Network Berbasis Saliency. JUITA: Jurnal Informatika, 8(1), 37. https://doi.org/10.30595/juita.v8i1.6671
  14. Yohannes, Y., Udjulawa, D., & Febbiola, F. (2021). Klasifikasi Lukisan Karya Van Gogh Menggunakan Convolutional Neural Network-Support Vector Machine. Jurnal Teknik Informatika Dan Sistem Informasi, 7(1), 192–205. https://doi.org/10.28932/jutisi.v7i1.3399
  15. Zewen Li, Fan Liu, Wenjie Yang, Shouheng Peng, & Jun Zhou. (2021). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Transactions on Neural Networks and Learning Systems, 33(12), 6999–7019