Transformer-Based Detection Model for Number Recognition on Electric kWh Meters

Leni Fitriani; Ahmad Sanusi; Rita Rismala; Dewi Tresnawati

doi:10.30595/juita.v13i2.26161

Authors

Leni Fitriani Institut Teknologi Garut
Ahmad Sanusi Institut Teknologi Garut
Rita Rismala Telkom University
Dewi Tresnawati Institut Teknologi Garut

DOI:

https://doi.org/10.30595/juita.v13i2.26161

Keywords:

Detection Transformer, KWh, MLLC, Mean Average Precision, Optical Character Recognition

Abstract

Manual recording of analog kWh meters frequently results in user complaints due to discrepancies between recorded and actual electricity usage. These issues stem from the continued reliance on manual data collection. This study proposes a model that automatically detects and extracts numerical values from kWh electricity meters using the Detection Transformer (DETR) for object detection and EasyOCR for optical character recognition (OCR). The model was developed using the Machine Learning Life Cycle (MLLC) methodology, comprising data acquisition, preprocessing, modeling, evaluation, and deployment. Evaluation using the Mean Average Precision (mAP) metric yielded a score of 96.83%, demonstrating high object detection accuracy. The trained model was integrated into a simple web application built with the Flask framework. While the model performed well on high-quality images, its effectiveness declined on low-quality images, such as blurry or distant captures. This study highlights the potential of DETR for object detection and OCR-based text extraction in analog meter reading, while also identifying challenges in handling suboptimal image conditions for future improvements

References

[1] Napis, M. Farhan, Rahmatulloh, A. R. Hakim, and M. T. Apriyanto, “MENINGKATKAN KESADARAN MASYARAKAT DALAM BUDAYA HEMAT ENERGI MELALUI PENYULUHAN EFISIENSI PENGGUNAAN LISTRIK RUMAH TANGGA,” J. Pendidik. Dan Pengabdi. Masy., vol. 6, no. 2, pp. 107–115, May 2023, doi: 10.29303/jppm.v6i2.4980.

[2] D. S. Markovic, D. Zivkovic, I. Branovic, R. Popovic, and D. Cvetkovic, “Smart power grid and cloud computing,” Renew. Sustain. Energy Rev., vol. 24, pp. 566–577, 2013, doi: https://doi.org/10.1016/j.rser.2013.03.068.

[1] Napis, M. Farhan, Rahmatulloh, A. R. Hakim, and M. T. Apriyanto, “MENINGKATKAN KESADARAN MASYARAKAT DALAM BUDAYA HEMAT ENERGI MELALUI PENYULUHAN EFISIENSI PENGGUNAAN LISTRIK RUMAH TANGGA,” J. Pendidik. Dan Pengabdi. Masy., vol. 6, no. 2, pp. 107–115, May 2023, doi: 10.29303/jppm.v6i2.4980.

[2] D. S. Markovic, D. Zivkovic, I. Branovic, R. Popovic, and D. Cvetkovic, “Smart power grid and cloud computing,” Renew. Sustain. Energy Rev., vol. 24, pp. 566–577, 2013, doi: https://doi.org/10.1016/j.rser.2013.03.068.

[3] A. N. Waldi, “Akurasi Pengukuran kWh Meter Analog Terhadap Losses Energi Listrik,” Sutet, vol. 11, no. 2, pp. 105–113, 2021, doi: 10.33322/sutet.v11i2.1577.

[4] J. Son, “Analisa Data Hasil Pengukuran Beban Motor Listrik 1 Fasa pada kWh Analog dan kWh Digital,” Electr. J. Rekayasa Dan Teknol. Elektro, vol. 15, no. 3, Art. no. 3, Sep. 2021, doi: 10.23960/elc.v15n3.2219.

[5] D. Permata et al., “Sistem Perhitungan kW Meter Listrik Prabayar (LPB) untuk Pelanggan Daya 900 Va PT. PLN (Persero) Area Palembang,” J. Teliska ISSN, vol. 5, no. 2, pp. 53–61, 2013.

[6] D. D. Prihartomo, R. D. Nyoto, and A. S. Sukamto, “Rancang Bangun Aplikasi Pencatatan dan Pengolahan Data Pemakaian KWH (Kilowatt Hour) Listrik Digital,” Justin J. Sist. Dan Teknol. Inf., vol. 4, no. 2, pp. 1–5, 2016.

[7] I. Wijaya and C. Lubis, “Pengimplementasian Ocr Menggunakan Cnn Untuk Ekstraksi Teks Pada Gambar,” J. Ilmu Komput. Dan Sist. Inf., vol. 10, no. 1, 2022, doi: 10.24912/jiksi.v10i1.17836.

[8] A. Haris, “Sistem Pencatat Kwh Meter Terintegrasi Komputer Untuk Meningkatkan Layanan Pada Pelanggan,” KILAT, vol. 6, no. 1, Art. no. 1, 2017, doi: 10.33322/kilat.v6i1.664.

[9] N. Kholis and F. Baskoro, “Rancang Bangun Sistem Deteksi Label Kardus Berbasis Model Kecerdasan Buatan YOLO dan EasyOCR serta ESP32-CAM Rancang Bangun Sistem Deteksi Label Kardus Berbasis Model Kecerdasan Buatan YOLO dan EasyOCR serta ESP32-CAM Stefanus Adhie Nugroho Abstrak,” pp. 190–200, 2022, doi: https://doi.org/10.26740/jte.v11n2.p190-200.

[10] M. Tanzib Hosain, A. Zaman, M. R. Abir, S. Akter, S. Mursalin, and S. S. Khan, “Synchronizing Object Detection: Applications, Advancements and Existing Challenges,” IEEE Access, vol. 12, no. April, pp. 54129–54167, 2024, doi: 10.1109/ACCESS.2024.3388889.

[11] N. Carion, F. Massa, G. Synnaeve, N. Usunier, A. Kirillov, and S. Zagoruyko, “End-to-End Object Detection with Transformers,” Lect. Notes Comput. Sci. Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinforma., vol. 12346 LNCS, pp. 213–229, 2020, doi: 10.1007/978-3-030-58452-8_13.

[12] E. Suherman, B. Rahman, D. Hindarto, and H. Santoso, “Implementation of ResNet-50 on End-to-End Object Detection (DETR) on Objects,” SinkrOn, vol. 8, no. 2, pp. 1085–1096, 2023, doi: 10.33395/sinkron.v8i2.12378.

[13] X. Chen, F. Wei, G. Zeng, and J. Wang, “Conditional DETR V2: Efficient Detection Transformer with Box Queries,” Jul. 18, 2022, arXiv: arXiv:2207.08914. doi: 10.48550/arXiv.2207.08914.

[14] J. Yang, S. Deng, F. Zhang, A. Pan, and Y. Yang, “FATCNet : Feature Adaptive Transformer and CNN for Infrared Small Target Detection,” IEEE Trans. Aerosp. Electron. Syst., vol. 60, no. 6, pp. 9231–9246, Dec. 2024, doi: 10.1109/TAES.2024.3441551.

[15] F. Luo, Y. Dai, J. Fuentes, W. Ding, and X. Zhang, “M-DETR: Multi-scale DETR for Optical Music Recognition,” Expert Syst. Appl., vol. 249, 2024, doi: 10.1016/j.eswa.2024.123664.

[16] R. Laroca, V. Barroso, M. A. Diniz, G. R. Gonçalves, W. R. Schwartz, and D. Menotti, “Convolutional Neural Networks for Automatic Meter Reading,” J. Electron. Imaging, vol. 28, no. 01, p. 1, Feb. 2019, doi: 10.1117/1.JEI.28.1.013023.

[17] F. Khan, S. Rafique, and G. M. Khan, “Low-Cost Smart Metering Using Deep Learning,” Int. J. Innov. Sci. Technol., vol. 6, no. 5, Art. no. 5, May 2024.

[18] A. Combs, Python Machine Learning Blueprints Second Edition, no. July. 2020.

[19] L. Fitriani, D. Tresnawati, and M. B. Sukriyansah, “Image Classification On Garutan Batik Using Convolutional Neural Network with Data Augmentation,” JUITA J. Inform., vol. 11, no. 1, p. 107, 2023, doi: 10.30595/juita.v11i1.16166.

[20] V. R. Joseph and A. Vakayil, “SPlit: An Optimal Method for Data Splitting,” Technometrics, vol. 64, no. 2, pp. 166–176, 2022, doi: 10.1080/00401706.2021.1921037.

[21] J. Terven and D. Cordova-Esparza, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680–1716, Nov. 2023, doi: 10.3390/make5040083.

[22] W. Muldayani, “Implementasi Sistem Object Tracking Untuk Mendeteksi Dua Objek Berbasis Deep Learning,” Simetris J. Tek. Mesin Elektro Dan Ilmu Komput., vol. 14, no. 1, pp. 1–14, 2023, doi: 10.24176/simet.v14i1.9236.

[23] G. J. N. Ang et al., “A Novel real-time arrhythmia detection model using YOLOv8,” Jan. 08, 2024, arXiv: arXiv:2305.16727. doi: 10.48550/arXiv.2305.16727.

[24] Z. Ebrahimi, M. Loni, M. Daneshtalab, and A. Gharehbaghi, “A review on deep learning methods for ECG arrhythmia classification,” Expert Syst. Appl. X, vol. 7, p. 100033, 2020, doi: 10.1016/j.eswax.2020.100033.

[25] L. Fitriani, A. Latifah, and M. R. Cahyadiputra, “Image Classification of Room Tidiness Using VGGNet with Data Augmentation,” JUITA J. Inform., vol. 12, no. 1, p. 111, May 2024, doi: 10.30595/juita.v12i1.21204.

[26] X. Chen, F. Wei, G. Zeng, and J. Wang, “Conditional DETR V2: Efficient Detection Transformer with Box Queries,” Jul. 18, 2022, arXiv: arXiv:2207.08914. doi: 10.48550/arXiv.2207.08914.