EFFICIENCY OF TEXT RECOGNITION IN THE AUTOMATION OF INTERNATIONAL MARITIME TRANSPORT WITH THE HELP OF ARTIFICIAL INTELLIGENCE
DOI:
https://doi.org/10.32782/tnv-tech.2024.3.4Keywords:
text recognition, OCR, artificial intelligence (AI), logistics, automation, international transportation, document processing, system integrationAbstract
Modern technologies of optical character recognition (OCR) based on artificial intelligence have significantly improved the possibilities of automating the processing of text documents. They provide high accuracy and versatility, allowing efficient processing of documents of various types and languages. The choice of a specific OCR technology depends on the specifics of the task and requirements for accuracy, speed and integration with existing systems. The article examines the effectiveness of optical character recognition technologies based on artificial intelligence in the context of automation of international maritime transport. The growing complexity and volume of documents that accompany logistics processes require the implementation of innovative solutions to increase the efficiency of data processing and reduce operational costs. The purpose of the study is to study the possibilities and advantages of using AI-based OCR to improve the efficiency of text data processing in logistics. The tasks of the research include the analysis of modern OCR technologies, determination of the principles of operation of OCR systems, evaluation of their advantages and limitations, as well as providing recommendations for increasing the efficiency of their use. The study showed that the implementation of OCR systems in logistics processes ensures high accuracy of text recognition, a significant reduction in document processing time, and a reduction in the number of errors. Real-life examples of successful use of OCR technologies by leading logistics companies such as DHL, Maersk, Amazon, FedEx and UPS demonstrate the significant benefits of automating the processing of waybills, customs clearance, warehouse management and invoices. AI-based OCR technologies have great potential for automating and optimizing logistics processes. To achieve maximum results, it is recommended to improve the quality of input images, use modern algorithms and models, adapt them to specific tasks, ensure data security and confidentiality, integrate OCR systems with other information systems, regularly monitor and optimize the operation of systems, as well as train personnel. The use of OCR in logistics improves the efficiency, accuracy and speed of document processing, which is key to the successful functioning of international maritime transport.
References
Tang Q., Lee Y., Jung H. The Industrial Application of Artificial Intelligence-Based Optical Character Recognition in Modern Manufacturing Innovations. Sustainability. 2024. Vol. 16, no. 5. P. 2161. URL: https://doi.org/10.3390/su16052161 (date of access: 13.07.2024).
Haseeb M., Hussain H.I., Ślusarczyk B., Jermsittiparsert K. Industry 4.0: A Solution towards Technology Challenges of Sustainable Business Performance. Social Sciences. 2019. №8. Р. 154.
Woschank M., Rauch E., Zsifkovits H. A Review of Further Directions for Artificial Intelligence, Machine Learning, and Deep Learning in Smart Logistics. Sustainability. 2020. Vol. 12, no. 9. P. 3760. URL: https://doi.org/10.3390/su12093760 (date of access: 13.07.2024).
Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes / M. Liao et al. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2019. Vol.43(2). Р. 532–548. URL: https://doi.org/10.1109/tpami.2019.2937086 (date of access: 13.07.2024).
Boundary TextSpotter: Toward Arbitrary-Shaped Scene Text Spotting / P. Lu et al. IEEE Transactions on Image Processing. 2022. P. 1. URL: https://doi.org/10.1109/tip.2022.3206615 (date of access: 14.07.2024).
Raj R., Kos A. A Comprehensive Study of Optical Character Recognition. 2022 29th International Conference on Mixed Design of Integrated Circuits and System (MIX-DES), Wrocław, Poland, 23–24 June 2022. P. 151–154. URL: https://doi.org/10.23919/mixdes55591.2022.9837974 (date of access: 14.07.2024).
Implementation of Optical Character Recognition using Tesseract with the Javanese Script Target in Android Application / G. A. Robby et al. Procedia Computer Science. 2019. Vol. 157. P. 499–505. URL: https://doi.org/10.1016/j.procs.2019.09.006 (date of access: 14.07.2024).
Adedayo K. D., Agunloye A. O. Real-time Automated Detection and Recognition of Nigerian License Plates via Deep Learning Single Shot Detection and Optical Character Recognition. Computer and Information Science. 2021. Vol. 14, no. 4. P. 11. URL: https://doi.org/10.5539/cis.v14n4p11 (date of access: 14.07.2024).
Шевченко А. І., Кондратенко Ю. П. Щодо проєкту стратегії розвитку штучного інтелекту в Україні. Artificial Intelligence. 2022. № 1. С. 75-80. URL: https://www.slyusar.kiev.ua/AI_2022-1-1_ua.pdf. (дата звернення: 14.07.2024).
Стратегія розвитку штучного інтелекту в Україні: монографія; за заг. ред. А. І. Шевченка. Київ: ІПШІ, 2023. 305 с.
