Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2, 1967-1979 2025 Publisher: Learning Gate DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate © 2025 by the authors; licensee Learning Gate History: Received: 17 December 2024; Revised: 24 January 2025; Accepted: 5 February 2025; Published: 22 February 2025 * Correspondence: hdenriquez39B@udenar.edu.co Artificial intelligence and vehicle license plate recognition: A literature review Hernán Darío Enríquez Martínez1*, Jesus Insuasti2 1,2Systems Engineering Department, University of Nariño, Pasto 52001, Colombia; hdenriquez39B@udenar.edu.co (H.D.E.M.) insuasti@udenar.edu.co (J.I.P.) Abstract: This study presents a systematic literature review on the application of artificial intelligence (AI) in vehicle license plate recognition, focusing on neural network-based technologies. The primary objective is to identify recent advancements that enhance traffic control automation and road safety. The research methodology involves a structured search and analysis of 90 significant publications selected from databases such as IEEE Xplore, ScienceDirect, Scopus, and DOAJ. Findings indicate that convolutional neural networks (CNNs) and deep learning models play a crucial role in improving recognition accuracy and efficiency, particularly through optimized image processing techniques and convolutional layers. However, challenges persist due to variations in license plate design and adverse environmental conditions affecting system performance. The study highlights the need for continued research on image preprocessing methods to enhance robustness and adaptability. The conclusions emphasize the critical role of AI-driven recognition systems in modern transportation infrastructure, advocating for further integration of advanced neural network architectures. From a practical perspective, these findings contribute to the development of more reliable and efficient vehicle identification systems, with implications for law enforcement, automated tolling, and smart city initiatives. Keywords: Artificial intelligence, License plates, Neural network, Recognition, Systematic literature review. 1. Introduction Vehicle license plate identification is crucial in various fields, from traffic control to public safety. Traditionally, this process has relied on centralized systems that can be costly and inefficient. In addition, the lack of transparency in transactions and the difficulty in adapting new technologies hinder the improvement of these systems. The systematic literature review has highlighted advanced technologies, such as neural networks, in vehicle license plate identification. Among these technologies, neural networks stand out for their ability to process large amounts of data efficiently and their adaptability to different conditions and environments. The results of this review highlight several key components used in vehicle license plate identification using neural networks, such as convolution layers, deep learning algorithms, and image processing techniques. These enable the efficient and accurate operation of the vehicle license plate recognition system. The review structure follows a systematic approach: the methodology is described in Section 2, the results are presented in Section 3, the discussion of the findings in Section 4, and the conclusions are given in Section 5. In addition, relevant references are included to support the findings and analysis. https://orcid.org/0009-0002-6155-4229 https://orcid.org/0000-0002-3233-3577 1968 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate 2. Methodology A systematic literature review was conducted using an approach focused on Software Engineering research processes [1-4]. The main goal was to provide a complete overview of the field of study and examine the number, types, and results of existing studies to develop a classification scheme and an appropriate structure. Specialists frequently use this approach since it facilitates the creation of knowledge from publications resulting from research processes [5]. Figure 1 shows the stages of the stipulated method. Figure 1. RSL structure. Source: Revelo Sanchez, et al. [6] According to Kitchenham and Brereton [7]. The reason for conducting a systematic literature review arises from the demand of researchers to comprehensively and impartially synthesize all available information on a specific topic. Conducting an RSL on applied technologies for electric power transactions allows for identifying, analyzing, and compiling the relevant literature related to this topic. These results will be a valid basis to share with the scientific community. 2.1. Research Questions Formulating research questions is a crucial task in conducting an RSL. These questions guide the search for primary studies and the extraction and synthesis of information needed to address them Revelo Sanchez, et al. [6]. This RSL includes two research questions, which are mentioned below. RQ1: What are the current neural network-based vehicle license plate recognition technologies? RQ2: What image pre-processing methods have been created specifically to enhance the performance of neural networks in vehicle license plate identification, and how do they influence the system's accuracy? 2.2. Search This activity aims to select genuinely relevant studies that contribute to answering the research questions [8]. The suggested search plan involves a general search in specialized databases. Search words and synonyms were used to cover various documents for analysis. Table 1 presents the terms, their synonyms, and the corresponding filters. The search was carried out in the databases indicated in Table 2, using fields such as title, keywords, abstract, and full text. Table 3 shows the results of the search strings for each term, including its synonyms and the relevant filters. Table 1. Term, synonyms, and filters to structure the search string. Term Synonyms Additional filters Vehicle license plate recognition with neural network Vehicle license plate recognition with deep learning Hybrid, Convolutional, transformers, for parking Vehicle license plate recognition with artificial intelligence Vehicle license plate recognition with automatic learning 1969 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate Table 2. Main term and databases. Term Database Vehicle license plate recognition with neural network IEEE Xplore, Science Direct, DOAJ, Scopus Table 3. Search string. Main term Search string Vehicle license plate recognition with neural network ("Vehicle license plate recognition with neural network" OR "Vehicle license plate recognition with artificial intelligence" OR "Vehicle license plate recognition with deep learning" OR "Vehicle license plate recognition with automatic learning" ) AND (hybrid OR convolutional OR transformers OR of parking) AND (publication year >= 2020). 2.3. Selection All studies included in this review were examined, considering criteria such as title, keywords, and abstract, to identify those that address models and technologies related to vehicle license plate recognition. Likewise, inclusion and exclusion criteria were defined, as shown in Table 4. Table 4. Criteria. The systematic literature review (SLR) process, depicted in Figure 2, follows a structured methodology to identify, filter, and analyze relevant research articles on vehicle license plate recognition. The process begins with a search string applied across four major academic databases: Scopus, IEEE Xplore, ScienceDirect, and DOAJ. Initially, a broad set of studies is retrieved, and a duplicate removal step is conducted to eliminate redundant entries. The pre-selection phase then applies filtering criteria based on titles, keywords, and abstracts, while also excluding review articles to ensure only primary research is considered. Following this, a more detailed selection phase is performed, where full-text reading and quality assessment criteria are applied to determine the final set of studies for inclusion. This structured approach ensures a rigorous and unbiased review of the most relevant literature, improving the reliability and comprehensiveness of the findings. Inclusion Criteria Exclusion Criteria Time (2020 - 2024). Studies that refer to technologies applied to vehicle license plate recognition. Title of the document related to technologies or automatic recognition of vehicle license plates. Research in languages other than English and Spanish will not be considered. Duplicate items. Literature reviews and studies that do not have the respective bibliographic citation are not considered. 1970 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate Figure 2. Results of study sources, adapted from. Source: Barón, et al. [9] 2.4. Quality Assessment The selected documents are evaluated using four criteria to ensure their quality: relevance of the content to address the key questions of the review, clarity of the research objectives, a detailed description of the context of the study, and clear presentation of the results. These criteria address three essential aspects: the minimum quality level, credibility, and relevance [7]. After carefully examining the 80 complete documents, 66 were selected that met the criteria established as essential sources for the systematic review. These documents are presented in Table 5 and their bibliographical references, ordered chronologically by year of publication. 2.5. Data Extraction and Synthesis The main objective of this systematic study is to evaluate the current state of license plate recognition. After searching for terms in each database and applying the two corresponding phases, the results obtained in the relevant files and the appropriate citations from their authors are presented below. 1971 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate Table 5. Studies included in systematic review Year Amount Reference 2020 22 Salazar Mayorga [10] ;Zhang, et al. [11] ; Tourani, et al. [12] ;Zou, et al. [13] ;Cai, et al. [14] ;Liu, et al. [15]; Rusakov [16] ;Pustokhina, et al. [17] ;Shrivastava, et al. [18];Darapaneni, et al. [19] ; Sarif, et al. [20]; Henry, et al. [21]; Mai, et al. [22]; Gong, et al. [23]; Liu, et al. [24]; Riaz, et al. [25]; Slimani, et al. [26]; Jamtsho, et al. [27] ;Acosta and Toruño [28];Espinoza Lopez and Portocarrero López [29] and Subhadhira, et al. [30] 2021 12 Suárez Mosquera, et al. [31]; Xu, et al. [32]; Kong, et al. [33]; Huang, et al. [34]; Duan, et al. [35];Shashirangana, et al. [36]; Joshua, et al. [37]; Ali, et al. [38]; Julius Fusic, et al. [39]; Awaimri, et al. [40]; Gonzáles [41]; Shariff, et al. [42] and Cáceres [43] 2022 13 Ilayarajaa, et al. [44]; Kukreja, et al. [45]; Rashtehroudi, et al. [46]; Suvon, et al. [47]; Weihong and Jiaoyang [48]; He and Hao [49]; Samadzadeh, et al. [50]; De Oliveira, et al. [51]; Onim, et al. [52]; Alghyaline [53]; Valdeos, et al. [54]; Martínez-Prado, et al. [55] and Pérez Silva [56] 2023 17 Naji, et al. [57]; Amato, et al. [58]; Aqaileh and Alkhateeb [59]; Kundrotas, et al. [60]; Danilenko [61]; Zhao, et al. [62]; Tsai, et al. [63]; Medvedeva, et al. [64]; Liu and Zhu [65]; Saitov and Filchenkov [66]; Sugiyono, et al. [67]; Jawale, et al. [68]; Corrales Estrella and Sánchez Bocanegra [69]; Vargas, et al. [70] and Satti Babu, et al. [71] 2024 2 Ramajo-Ballester, et al. [72] and Neupane, et al. [73] A detailed analysis of various vehicle license plate recognition technologies was carried out. In the research carried out by Salazar Mayorga [10] 34 videos were collected, of which 2,419 photographs were obtained with a resolution of 3,240 x 2,148 pixels. After choosing the most pertinent ones, a database with 10,299 images was generated, suitable for training, validation, and evaluation of the model. In the training, a convolutional neural network was used to categorize the occupancy of parking spaces, achieving an accuracy that exceeded 90% in tests with unknown images. However, restrictions were detected in situations of occlusions. The findings, comparable to previous research, corroborated the model's effectiveness, highlighting the impact of the camera's location and the environmental conditions on its accuracy. Scientists developed the ALPR system through the research mentioned in Tourani, et al. [12]. They use two independently trained and fine-tuned Yolo V3 networks to identify and recognize license plate characters. This method addresses common problems of optical character recognition (OCR) by treating character identification as a classification problem. In addition, several strategies were implemented to extend the training dataset. The experimental results demonstrate the accuracy and effectiveness of the system in real-world situations. The study mentioned in Cai, et al. [14] presents a novel algorithm for recognizing vehicle license plates in the United States. This approach combines several deep learning models. The process is divided into two main steps: first, the license plate and the state to which it belongs are identified, and then the characters are recognized. An optimized version of YOLO v3 is used for detection, while character recognition is performed with CRNN, and state classification is done with ResNet-50. The results demonstrate high accuracy in both tasks, which supports the effectiveness of the proposed model. The study mentioned in Rusakov [16] proposes a modular approach based on convolutional neural networks (CNN) to improve the speed and accuracy in license plate recognition. A Single Shot Detector (SSD) model detects license plates, which can accurately identify and locate the license plate within an 1972 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate image. Subsequently, a ResNet convolutional neural network is responsible for quickly recognizing and locating each character on the plate. The experimental results indicate that this modular strategy significantly improves the system's performance and speed while maintaining high accuracy levels compared to traditional methods. The study mentioned in Shrivastava, et al. [18] analyzes current technologies for non- polychromatic vehicle license plate recognition (VRNPR) and highlights the advantages of convolutional neural network (CNN)- based approaches over traditional methods. It proposes a five-step model for VRNPR that includes vehicle image capture, preprocessing, license plate localization, character segmentation, and subsequent recognition. The researchers conclude that the application of CNN significantly improves accuracy and processing speed compared to previous models, making it a fundamental tool for current traffic safety and regulation. The study in Darapaneni, et al. [19] describes a vehicle parking management system (VPMS) based on computer vision. This system aims to improve the management and control of parking spaces, especially in areas with high congestion. Due to the increase in the number of cars, optimizing the use of these spaces has become a significant challenge. The proposed solution is based on real-time license plate detection and recognition from video sequences, using the YOLOv3 algorithm and OpenCV to achieve high accuracy. The study in Sarif, et al. [20] presents a license plate recognition (LPR) system based on deep learning techniques designed for vehicles in Bangladesh. This system consists of three stages: first, it uses YOLOv3 to detect license plates; then, it applies a segmentation method adapted to the characteristics of license plates in the country; finally, it employs a convolutional neural network (CNN) to recognize characters. Using a dataset of 2000 images reflecting various environmental conditions, the system achieved an accuracy of 97.5%. The study mentioned in Gong, et al. [23] analyzes the recognition of Chinese vehicle license plates in complex environments, focusing on the challenges caused by the tilt and distortion of the captured images. To address these issues, an optimized convolutional recurrent neural network (CRNN) model is presented, which combines deep convolutional neural networks (DCNN), recurrent neural networks (RNN), spatial transformer networks (STN), and connectionist temporal classification (CTC). This combination of techniques enables end-to-end recognition without explicitly segmenting characters, thereby increasing accuracy and significantly reducing segmentation errors. The study referenced in Riaz, et al. [25] evaluates an automatic license plate recognition (ALPR) system that uses YOLOv3 for detection and CRNN for classification to improve vehicle identification. The researchers used the AOLP dataset and segmented the images into three categories: 40% for training, 20% for validation, and 40% for testing. The results reflected an overall recognition rate of 86%, with an accuracy of 88% for three-letter license plates and 99% for four-letter license plates. Furthermore, the recognition rate increased to 96% by integrating temporal redundancy. The research cited in Kong, et al. [33] deals with the application of federated learning in vehicle license plate recognition (FedLPR), using the ability of mobile devices to train the model and ensure user privacy efficiently. In this study, the progress of a model optimized for mobile devices is presented, which includes a license plate detection (LPD) and recognition (LPR) system, which consists of a tilt correction algorithm, to increase the registration accuracy. The experiments show the model's effectiveness in terms of accuracy and speed, even in challenging real-world contexts. In addition, a mobile application is launched to assess its performance more thoroughly. The report in Duan, et al. [35] analyzes the Vehicle License Plate Identification (LPR) technology, essential in Intelligent Transportation Systems. This method facilitates the identification of license plates through vehicle identification and character study in surveillance images or videos. They examine the challenges that affect the system's accuracy, such as the images' low quality and design. To address these issues, they suggest a practical solution based on the Single Shot MultiBox detector to identify license plates and a convolutional neural network for character interpretation. Likewise, the Deep 1973 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate Rebirth method reduces the model, improving its computing performance and simplifying real-time processing. The research cited in Joshua, et al. [37] examines an automated license plate recognition system to improve efficiency in Indonesian parking lots. Typically, parking staff manually perform license plate registration, which can be laborious and error-prone. To solve this problem, they suggest applying the YOLO (You Only Look Once (YOLO) model for image license plate identification and a ResNet neural network for categorizing the numeric characters of such license plates. In the research mentioned in Julius Fusic, et al. [39] convolutional neural networks, specifically the AlexNet model, recognize characters and segment vehicle license plates. The transfer learning method increased the model's accuracy using previously labeled images. An optical character recognition (OCR) system trained with a specific set of characters also facilitates highly accurate text extraction. The findings showed a notable increase in license plate recognition and identification accuracy. The study Awaimri, et al. [40] provides a methodical review of Automatic Number Plate Identification (ANPR) systems. The study includes several techniques and algorithms to identify and recognize number plates in images recorded by cameras and used in traffic management, vehicle protection, and parking regulation. The ANPR procedure includes four key stages: Image collection and pre-processing, Number plate identification, Character segmentation, and Character identification. The recognition rates of the algorithms evaluated in the study vary between 82% and 99%, demonstrating their effectiveness in different contexts and capture conditions. The research in Rashtehroudi, et al. [46] suggests an automatic license plate recognition (ALPR), focusing on Iranian license plates. This objective combines segmentation and optical character recognition (OCR) in a unified process based on deep learning methods, particularly the YOLO model. The study highlights the importance of image pre-processing to increase their quality and the relevance of procedures to obtain character features. These include conventional statistical evaluations and sophisticated methods based on convolutional neural networks. The findings indicate an accuracy of 99.2% in character identification, representing a considerable advance in previous research. The research mentioned in Onim, et al. [52] showcases BLPnet, a deep neural network (DNN) specially built for the Automatic License Plate Recognition (ALPR) of Bengal vehicles. Its structure consists of three stages: The first one uses an adapted version of NASNet Mobile, to identify the vehicle region effectively; The second, a customized model based on InceptionV3, facilitates accurate license plate identification; and the third, an innovative Bengali OCR engine, can process artifacts, such as motion blur. Compared to baseline models such as YOLO and Tesseract, BLPnet achieves a 5% increase in detection accuracy and a 20% decrease in processing time. The research in Valdeos, et al. [54] shows a system for accurately identifying and recognizing vehicle license plates based on convolutional neural networks trained explicitly with YOLOv4. Python and OpenCV are used for image processing. The newly employed database incorporates vehicle registrations from Peru, which improves the system's performance and enables 100% accuracy without false positives. The study's findings highlight that this method provides faster and more reliable processing than previous models, particularly those created in Europe, with significant implications for future vehicle management. The research in Amato, et al. [58] offers a detection approach based on convolutional neural networks (CNN), designed to work efficiently even under fluctuating environmental circumstances. Its ability to generalize is demonstrated when evaluated with images taken from viewpoints different from those used during training. In addition, it includes a comparative study with existing techniques, showing that its CNN-based approach matches or exceeds conventional methods in terms of accuracy and effectiveness. The research mentioned in Kundrotas, et al. [60] employs a modified Hourglass neural network based on the CenterNet framework for object detection. This alteration decreases the network size by 40%, resulting in highly effective performance with an accuracy of 96.19% and a processing speed of 2.71 ms (or 405 FPS). The algorithm is verified through publicly accessible data sets, which shows 1974 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate remarkable advances in the speed and effectiveness of license plate recognition systems, particularly in challenging contexts. In the research mentioned in Tsai, et al. [63] the writers suggest a three-phase license plate identification procedure: localization, character segmentation, and recognition. To increase the accuracy, they implement a convolutional neural network. The identification is efficiently carried out through OpenCV, which facilitates the localization of license plates with high accuracy in different circumstances, including those with blue and yellow hues. By improving the network parameters and implementing error back-propagation methods, the system achieves an accuracy rate exceeding 97%. The research in [66] shows a deep convolutional YOLOv8 neural network for license plate identification, achieving a mean accuracy (mAP@50) of 0.983. These findings demonstrate significant speed and accuracy compared to existing systems. The study uses the TrOCR transformer model for optical character recognition, which increases the accuracy in identifying license plates from nations such as Armenia, Kazakhstan, Ukraine, and Moldova. Furthermore, the research highlights the challenges in license plate identification, including variability in design and environmental conditions such as light and noise. In the study cited in Jawale, et al. [68] on character recognition, four models were analyzed and compared: CNN, MobileNet, Inception V3, and ResNet50. CNN performed the best, achieving an accuracy of 98.5% and a loss of 4.25%. The authors conclude that the proposed ALPDR system, especially with the convolutional neural network model, is highly effective under various conditions, such as low illumination, blur, and tilt. 3. Discussion This section answers the research questions posed above. RQ1: The current state of neural network-based technologies for license plate recognition is highly advanced and constantly evolving. Neural networks, especially convolutional neural networks (CNNs), have emerged as the primary tool to address challenges in license plate recognition due to their ability to learn and extract relevant features from images. 3.1. Techniques Used: • CNNs are highly effective for image processing. They can identify patterns and features at different scales and levels of complexity. CNNs are particularly useful for recognizing alphanumeric characters on license plates. • Recently, models such as YOLO (You Only Look Once) and variants of it, such as YOLOv3, YOLOv4, and YOLOv8, have also been used. These models allow real-time detection, which is essential for applications such as traffic control and public safety. 3.2. Technical Challenges: • Despite advances, significant challenges remain, such as variability in license plate design, different lighting conditions, or occlusions. These factors can affect the accuracy of the recognition system. • Image quality also plays a crucial role; blurry or low-resolution images make it difficult to identify characters correctly. 3.3. The Future • Research continues to improve deep learning models, image preprocessing algorithms, and transfer learning approaches to develop more robust and accurate systems. RQ2: Pre-processing methods are essential to improve the quality of images before they are fed into neural networks, increasing the accuracy of license plate recognition. 1975 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate 3.4. Common Pre-Processing Techniques • Contrast and Brightness Adjustment: These techniques improve the visibility of characters in different lighting conditions. • Normalization: Ensures images are consistent in size and format, making it easier to train the neural network. • Noise Removal: Filters and techniques such as mathematical morphology are applied to remove background noise that could confuse the system. • Image Segmentation involves locating and extracting the region of interest (the license plate) from the entire image, removing unwanted elements, and focusing solely on the license plate. 3.5. Impact on Accuracy • Implementing these pre-processing techniques can significantly increase the correct recognition rate. For example, adjusting the contrast can make the characters on a license plate more contrasting against the background, making the model's task more manageable. • Segmentation techniques also allow neural networks to focus on the relevant part of the image, improving recognition accuracy and efficiency. 3.6. Integration with Deep Learning Models • Some modern approaches integrate preprocessing directly into the deep learning model pipeline, using neural networks to perform fine-tuning and segmentation automatically. This can result in a more efficient system with lower computational overhead. 4. Conclusions Neural networks, especially convolutional neural networks (CNN), are identified as crucial tools in license plate recognition. Their ability to learn and extract meaningful features from images significantly improves the accuracy and speed of the process. Implementing these systems automates recognition and increases efficiency in critical applications such as traffic control and public safety. Despite progress, technical challenges affecting recognition effectiveness include variability in license plate designs, adverse lighting conditions, and occlusions. These difficulties can negatively impact the overall accuracy of recognition systems. Recognition success depends heavily on image preprocessing methods. Techniques such as contrast adjustment, normalization, and segmentation are critical to improving the quality of images before they are analyzed by neural networks, which can considerably increase recognition rates. The evolution of deep learning algorithms and the development of methodological benchmarks provide a viable framework for future research. This includes moving towards more robust models that integrate pre-processing techniques directly into the deep learning workflow. Transparency: The authors confirm that the manuscript is an honest, accurate, and transparent account of the study; that no vital features of the study have been omitted; and that any discrepancies from the study as planned have been explained. This study followed all ethical practices during writing. Copyright: © 2025 by the authors. This open-access article is distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). References [1] K. Petersen, R. Feldt, S. Mujtaba, and M. Mattsson, "Systematic mapping studies in software engineering," in In EASE'08 Proceedings of the 12th International conference on Evaluation and Assessment in Software Engineering, Italy, 2008. https://creativecommons.org/licenses/by/4.0/ 1976 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate Available at: Systematic Mapping Studies in Software Engineering | Proceedings of the 12th international conference on Evaluation and Assessment in Software Engineering. Available in: https://doi.org/10.1016/j.jss.2020.110736 2008. [2] B. Kitchenham, O. P. Brereton, D. Budgen, M. Turner, J. Bailey, and S. Linkman, "Systematic literature reviews in software engineering–a systematic literature review," Information and Software Technology, vol. 51, no. 1, pp. 7-15, 2009. https://doi.org/10.1016/j.infsof.2008.09.009 [3] B. A. Kitchenham, T. Dyba, and M. Jorgensen, "Evidence-based software engineering," in Proceedings. 26th International Conference on Software Engineering, 2019, pp. 273–281. https://doi.org/10.1109/ICSE.2004.1317449 2019. [4] B. Kitchenham et al., "Systematic literature reviews in software engineering–a tertiary study," Information and Software Technology, vol. 52, no. 8, pp. 792-805, 2010. https://doi.org/10.1016/j.infsof.2010.03.006 [5] O. Revelo-Sánchez, C. A. Collazos-Ordóñez, and J. A. Jiménez-Toledo, "Collaborative work as a didactic strategy for teaching/learning programming: A systematic literature review," TecnoLógicas, vol. 21, no. 41, pp. 115-134, 2018. https://doi.org/10.22430/22565337.731 [6] O. Revelo Sanchez, C. A. Collazos Ordonez, and J. A. Jimenez Toledo, "Gamification as a didactic strategy for teaching/learning programming: A systematic mapping of the literature," Revista Digital Lampsakos, vol. 19, pp. 31- 46, 2018. https://doi.org/10.21501/21454086.2347 [7] B. Kitchenham and P. Brereton, "A systematic review of systematic review process research in software engineering," Information and Software Technology, vol. 55, no. 12, pp. 2049-2075, 2013. https://doi.org/10.1016/j.infsof.2013.07.010 [8] B. A. Kitchenham and Charters, "Guidelines for performing systematic literature reviews in software engineering,” Tech. Report, Ver. 2.3 EBSE Tech. Report. EBSE, vol. 1," Retrieved: https://docs.edtechhub.org/lib/EDAG684W, 2019. [9] S. A. Á. Barón, J. H. I. Portilla, and A. N. M. Jurado, "Blockchain and electricity transactions: A literature review," Revista Colombiana De Tecnologias De Avanzada, vol. 1, no. 43, pp. 35-43, 2024. https://doi.org/10.24054/rcta.v1i43.2802 [10] J. L. Salazar Mayorga, "Design, development and implementation of an IoT device for the automation of vehicle parking spaces with computer vision and deep learning," 2020. [11] Y. Zhang, M. Qiu, Y. Ni, and Q. Wang, "A novel deep learning-based number plate detect algorithm under dark lighting conditions," presented at the International Conference on Communication Technology Proceedings, ICCT, 2020- October 1412–1417. Available in: https://doi.org/10.1109/ICCT50939.2020.9295720, 2020. [12] A. Tourani, A. Shahbahrami, S. Soroori, S. Khazaee, and C. Y. Suen, "A robust deep learning approach for automatic iranian vehicle license plate detection and recognition for surveillance systems," IEEE Access, vol. 8, pp. 201317- 201330, 2020. https://doi.org/10.1109/ACCESS.2020.3035992 [13] Y. Zou et al., "A robust license plate recognition model based on bi-lstm," IEEE Access, vol. 8, pp. 211630-211641, 2020. https://doi.org/10.1109/ACCESS.2020.3040238 [14] Y. Cai, Y. Zhang, and J. Huang, "American license plate recognition algorithm based on deep multi-model fusion," in Proceedings - 2020 Chinese Automation Congress, CAC 2020, 6432–6437. Available in: https://doi.org/10.1109/CAC51589.2020.9326762, 2020. [15] Y. Liu, Y. Li, G. Chen, and H. Gao, "An edge-end based fast car license plate recognition method," in Proceedings - 2020 International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE 2020, 394–397. Available in: https://doi.org/10.1109/ICBASE51474.2020.00090, 2020. [16] K. D. Rusakov, "Automatic modular license plate recognition system using fast convolutional neural networks," in Proceedings of 2020 13th International Conference Management of Large-Scale System Development, MLSD 2020, 20–23. https://doi.org/10.1109/MLSD49919.2020.9247817, 2020. [17] I. V. Pustokhina et al., "Automatic vehicle license plate recognition using optimal K-means with convolutional neural network for intelligent transportation systems," LEEE Access, vol. 8, pp. 92907-92917, 2020. https://doi.org/10.1109/ACCESS.2020.2993008 [18] S. Shrivastava, S. K. Singh, K. Shrivastava, and V. Sharma, "CNN-based automated vehicle registration number plate recognition system," in Proceedings - IEEE 2020 2nd International Conference on Advances in Computing, Communication Control and Networking, ICACCCN 2020, 795–802. https://doi.org/10.1109/ICACCCN51052.2020.9362737, 2020. [19] N. Darapaneni et al., "Computer vision-based license plate detection for automated vehicle parking management system," presented at the IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference, UEMCON 2020, 0800–0805. Available in: https://doi.org/10.1109/UEMCON51285.2020.9298091, 2020. [20] M. M. Sarif, T. S. Pias, T. Helaly, M. S. R. Tutul, and M. N. Rahman, "Deep learning-based Bangladeshi license plate recognition system," in 4th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2020 - Proceedings. https://doi.org/10.1109/ISMSIT50672.2020.9254748, 2020. [21] C. Henry, S. Y. Ahn, and S.-W. Lee, "Multinational license plate recognition using generalized character sequence detection," LEEE Access, vol. 8, pp. 35185-35199, 2020. https://doi.org/10.1109/ACCESS.2020.2974973 [22] L. Mai, X. Z. Chen, C. W. Yu, and Y. L. Chen, "Multi-view vehicle re-identification method based on siamese convolutional neural network structure," presented at the IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020, 2020–2021. https://doi.org/10.1109/ICCE-Taiwan49838.2020.9257994, 2020. https://doi.org/10.1016/j.jss.2020.110736 https://doi.org/10.1016/j.infsof.2008.09.009 https://doi.org/10.1109/ICSE.2004.1317449 https://doi.org/10.1016/j.infsof.2010.03.006 https://doi.org/10.22430/22565337.731 https://doi.org/10.21501/21454086.2347 https://doi.org/10.1016/j.infsof.2013.07.010 https://docs.edtechhub.org/lib/EDAG684W https://doi.org/10.24054/rcta.v1i43.2802 https://doi.org/10.1109/ICCT50939.2020.9295720 https://doi.org/10.1109/ACCESS.2020.3035992 https://doi.org/10.1109/ACCESS.2020.3040238 https://doi.org/10.1109/CAC51589.2020.9326762 https://doi.org/10.1109/ICBASE51474.2020.00090 https://doi.org/10.1109/MLSD49919.2020.9247817 https://doi.org/10.1109/ACCESS.2020.2993008 https://doi.org/10.1109/ICACCCN51052.2020.9362737 https://doi.org/10.1109/UEMCON51285.2020.9298091 https://doi.org/10.1109/ISMSIT50672.2020.9254748 https://doi.org/10.1109/ACCESS.2020.2974973 https://doi.org/10.1109/ICCE-Taiwan49838.2020.9257994 1977 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate [23] W. Gong, S. Z. S. Bin, and Q. Ji, "Non-segmented chinese license plate recognition algorithm based on deep neural networks," in Proceedings of the 32nd Chinese Control and Decision Conference, CCDC 2020, 66–71. https://doi.org/10.1109/CCDC49329.2020.9163986, 2020. [24] Y. Liu, J. Yan, and Y. Xiang, "Research on license plate recognition algorithm based on ABCNet," in Proceedings of 2020 IEEE 3rd International Conference on Information Systems and Computer Aided Education, ICISCAE 2020, 465–469. Available in: https://doi.org/10.1109/ICISCAE51034.2020.9236855, 2020. [25] W. Riaz, A. Azeem, G. Chenqiang, Z. Yuxi, Saifullah, and W. Khalid, "YOLO based recognition method for automatic license plate recognition," in Proceedings of 2020 IEEE International Conference on Advances in Electrical Engineering and Computer Applications, AEECA 2020, 87–90. Available in: https://doi.org/10.1109/AEECA49918.2020.9213506, 2020. [26] I. Slimani, A. Zaarane, W. Al Okaishi, I. Atouf, and A. Hamdoun, "An automated license plate detection and recognition system based on wavelet decomposition and CNN," Array, vol. 8, p. 100040, 2020. https://doi.org/10.1016/j.array.2020.100040 [27] Y. Jamtsho, P. Riyamongkol, and R. Waranusast, "Real-time Bhutanese license plate localization using YOLO," ICT Express, vol. 6, no. 2, pp. 121-124, 2020. https://doi.org/10.1016/j.icte.2019.11.001 [28] R. Acosta and L. Toruño, "Vehicle license plate recognition using digital image processing in Python-OpenCV," Retrieved: http://riul.unanleon.edu.ni:8080/jspui/handle/123456789/8177, 2020. [29] A. Espinoza Lopez and R. Portocarrero López, "Automatic license plate recognition, using a convolutional neural network for vehicle entry at Ricardo Palma University," vol. 15, pp. 169–177, 2020. [30] S. Subhadhira, U. Juithonglang, P. Sakulkoo, and P. Horata, "License plate recognition application using extreme learning machines," in Proceedings of the 2014 3rd ICT International Senior Project Conference, ICT-ISPC 2014, 8(12), 103–106. https://doi.org/10.1109/ICT-ISPC.2014.6923228, 2020. [31] F. Suárez Mosquera, C. D. Ballén Martínez, and G. A. Castang Montiel, "Telematic artificial vision prototype for recognition of characteristics in people and vehicles," Visión Electrónica, vol. 15, no. 1, pp. 104-112, 2021. [32] H. Xu, Z. H. Guo, D. H. Wang, X. D. Zhou, and Y. Shi, "2D license plate recognition based on automatic perspective rectification," in Proceedings - International Conference on Pattern Recognition, 202–208. https://doi.org/10.1109/ICPR48806.2021.9413152, 2021. [33] X. Kong et al., "A federated learning-based license plate recognition scheme for 5G-enabled internet of vehicles," IEEE Transactions on Industrial Informatics, vol. 17, no. 12, pp. 8523-8530, 2021. https://doi.org/10.1109/TII.2021.3067324 [34] Q. Huang, Z. Cai, and T. Lan, "A single neural network for mixed style license plate detection and recognition," IEEE Access, vol. 9, pp. 21777-21785, 2021. https://doi.org/10.1109/ACCESS.2021.3055243 [35] N. Duan, J. Cui, L. Liu, and L. Zheng, "An end to end recognition for license plates using convolutional neural networks," IEEE Intelligent Transportation Systems Magazine, vol. 13, no. 2, pp. 177-188, 2019. https://doi.org/10.1109/MITS.2019.2898967 [36] J. Shashirangana, H. Padmasiri, D. Meedeniya, and C. Perera, "Automated license plate recognition: A survey on methods and techniques," IEEE Access, vol. 9, pp. 11203-11225, 2020. https://doi.org/10.1109/ACCESS.2020.3047929 [37] Joshua, J. Hendryli, and D. E. Herwindiati, "Automatic license plate recognition for parking system using convolutional neural networks," in Proceedings of 2020 International Conference on Information Management and Technology, ICIMTech 2020, August, 71–74. Available in: https://doi.org/10.1109/ICIMTech50083.2020.9211173, 2021. [38] S. T. A. Ali, A. H. Usama, I. R. Khan, M. M. Khan, and A. Siddiq, "Mobile registration number plate recognition using artificial intelligence," presented at the In 2021 IEEE International Conference on Image Processing (ICIP) (pp. 944-948), 2021. [39] S. Julius Fusic, S. Karthikeyan, H. Ramesh, and A. N. Subbiah, "Vehicle license plate detection and recognition using neural network," presented at the 4th Int. Conf. Comput. Commun. Signal Process. ICCCSP 2020. https://doi.org/10.1109/ICCCSP49186.2020.9315206, 2020. [40] M. Awaimri, S. Al Fageeri, A. Moyaid, and A. Alhasanat, "Vehicles number plate recognition systems a systematic review," in Proceedings of 2020 International Conference on Computer, Control, Electrical, and Electronics Engineering, ICCCEEE 2020, 0–5. https://doi.org/10.1109/ICCCEEE49695.2021.9429605, 2021. [41] P. Gonzáles, "Deep learning in IoT: Convolutional neural networks with images applied to an autonomous vehicle," Retrieved: https://hdl.handle.net/20.500.14352/5145, 2021. [42] A. M. Shariff, R. Bhatia, R. Kuma, and S. Jha, "Vehicle number plate detection using python and open cv," presented at the In 2021 International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) (pp. 525-529), 2021. [43] P. Cáceres, "Implementation of an intelligent system for vehicle identification," Retrieved: https://repositorio.uta.edu.ec/handle/123456789/33199, 2021. [44] K. T. Ilayarajaa, V. Vijayakumar, M. Sugadev, and T. Ravi, "Text recognition in moving vehicles using deep learning neural networks," in Proceedings - International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021, 279– 283. Available in: https://doi.org/10.1109/ICAIS50930.2021.9395980, 2022. https://doi.org/10.1109/CCDC49329.2020.9163986 https://doi.org/10.1109/ICISCAE51034.2020.9236855 https://doi.org/10.1109/AEECA49918.2020.9213506 https://doi.org/10.1016/j.array.2020.100040 https://doi.org/10.1016/j.icte.2019.11.001 http://riul.unanleon.edu.ni:8080/jspui/handle/123456789/8177 https://doi.org/10.1109/ICT-ISPC.2014.6923228 https://doi.org/10.1109/ICPR48806.2021.9413152 https://doi.org/10.1109/TII.2021.3067324 https://doi.org/10.1109/ACCESS.2021.3055243 https://doi.org/10.1109/MITS.2019.2898967 https://doi.org/10.1109/ACCESS.2020.3047929 https://doi.org/10.1109/ICIMTech50083.2020.9211173 https://doi.org/10.1109/ICCCSP49186.2020.9315206 https://doi.org/10.1109/ICCCEEE49695.2021.9429605 https://hdl.handle.net/20.500.14352/5145 https://repositorio.uta.edu.ec/handle/123456789/33199 https://doi.org/10.1109/ICAIS50930.2021.9395980 1978 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate [45] V. Kukreja, D. Kumar, A. Kaur, Geetanjali, and Sakshi, "GAN-based synthetic data augmentation for increased CNN performance in vehicle number plate recognition," in Proceedings of the 4th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2020, 1190–1195. https://doi.org/10.1109/ICECA49313.2020.9297625, 2022. [46] A. R. Rashtehroudi, A. Shahbahrami, and A. Akoushideh, "Iranian license plate recognition using deep learning," presented at the Iranian Conference on Machine Vision and Image Processing, MVIP, 2020- February. https://doi.org/10.1109/MVIP49855.2020.9116897, 2022. [47] M. N. I. Suvon, R. Khan, and M. Ferdous, "Real-time bangla number plate recognition using computer vision and convolutional neural network," presented at the IEEE International Conference on Artificial Intelligence in Engineering and Technology, IICAIET 2020, 12–17. https://doi.org/10.1109/IICAIET49801.2020.9257843, 2022. [48] W. Weihong and T. Jiaoyang, "Research on license plate recognition algorithms based on deep learning in complex environment," IEEE Access, vol. 8, pp. 91661-91675, 2020. https://doi.org/10.1109/ACCESS.2020.2994287 [49] M.-X. He and P. Hao, "Robust automatic recognition of Chinese license plates in natural scenes," LEEE Access, vol. 8, pp. 173804-173814, 2020. https://doi.org/10.1109/ACCESS.2020.3026181 [50] A. Samadzadeh, A. M. Shayan, B. Rouhani, A. Nickabadi, and M. Rahmati, "RILP: Robust Iranian license plate recognition designed for complex conditions," presented at the Iranian Conference on Machine Vision and Image Processing, MVIP, 2020- Feb. https://doi.org/10.1109/MVIP49855.2020.9116910, 2022. [51] I. O. De Oliveira, R. Laroca, D. Menotti, K. V. O. Fonseca, and R. Minetto, "Vehicle-Rear: A new dataset to explore feature fusion for vehicle identification using convolutional neural networks," IEEE Access, vol. 9, pp. 101065-101077, 2021. https://doi.org/10.1109/ACCESS.2021.3097964 [52] M. S. H. Onim et al., "Blpnet: A new dnn model and bengali ocr engine for automatic licence plate recognition," Array, vol. 15, p. 100244, 2022. https://doi.org/10.1016/j.array.2022.100244 [53] S. Alghyaline, "Real-time Jordanian license plate recognition using deep learning," Journal of King Saud University- Computer and Information Sciences, vol. 34, no. 6, pp. 2601-2609, 2022. https://doi.org/10.1016/j.jksuci.2020.09.018 [54] M. Valdeos, A. S. V. Velazco, M. G. P. Paredes, and R. M. A. Velásquez, "Methodology for an automatic license plate recognition system using Convolutional Neural Networks for a Peruvian case study," IEEE Latin America Transactions, vol. 20, no. 6, pp. 1032-1039, 2022. https://doi.org/10.1109/TLA.2022.9757747 [55] G. Martínez-Prado, M. Pescador-Hernandez, J. García-Ponce, and A. Pérez-Cebreros, "Model for the identification of license plates in Mexico city using machine learning algorithms," TAYACAJA, vol. 4, no. 2, pp. 147-151, 2021. https://doi.org/10.46908/tayacaja.v4i2.184 [56] E. W. Pérez Silva, "Vehicle license plate recognition using computer vision to improve access to a parking lot," 2022. https://orcid.org/0000-0003-3345-8774 [57] K. Naji, S. Gowid, and S. Ghani, "AI and IoT-based concrete column base cover localization and degradation detection algorithm using deep learning techniques," Ain Shams Engineering Journal, vol. 14, no. 11, p. 102520, 2023. https://doi.org/10.1016/j.asej.2023.102520 [58] G. Amato, F. Carrara, F. Falchi, C. Gennaro, and C. Vairo, "Car parking occupancy detection using smart camera networks and deep learning," in Proceedings - IEEE Symposium on Computers and Communications, 2016-August (Dl), 1212–1217. https://doi.org/10.1109/ISCC.2016.7543901, 2023. [59] T. Aqaileh and F. Alkhateeb, "Automatic jordanian license plate detection and recognition system using deep learning techniques," Journal of Imaging, vol. 9, no. 10, p. 201, 2023. https://doi.org/10.3390/jimaging9100201 [60] M. Kundrotas, J. Janutėnaitė-Bogdanienė, and D. Šešok, "Two-step algorithm for license plate identification using deep neural networks," Applied Sciences, vol. 13, no. 8, p. 4902, 2023. https://doi.org/10.3390/app13084902 [61] A. Danilenko, "License plate detection and recognition using convolution networks," in Proceedings of ITNT 2020 - 6th IEEE International Conference on Information Technology and Nanotechnology. https://doi.org/10.1109/ITNT49337.2020.9253353, 2023. [62] L. Zhao, F. Dai, F. Li, and Z. Zhao, "License plate recognition method based on convolutional neural network," in Proceedings - 2023 3rd International Conference on Frontiers of Electronics, Information and Computation Technologies, ICFEICT 2023, 154–160. https://doi.org/10.1109/ICFEICT59519.2023.00036, 2023. [63] T. Y. Tsai, Z. Y. Lu, and C. C. Huang, "License plate recognition system based on deep learning," presented at the IEEE International Conference on Consumer Electronics - Taiwan, ICCE-TW 2019, 1300–1303. https://doi.org/10.1109/ICCE-TW46550.2019.8991985, 2023. [64] E. Medvedeva, I. Trubin, and P. Kasper, "Vehicle license plate recognition based on edge detection," presented at the Conference of Open Innovation Association, FRUCT, 2020-April, 291–296. https://doi.org/10.23919/FRUCT48808.2020.9087537, 2023. [65] Z. Liu and Y. Zhu, "Vehicle license plate recognition in complex scenes," presented at the 2020 IEEE 5th International Conference on Intelligent Transportation Engineering, ICITE 2020, 235–239. https://doi.org/10.1109/ICITE50838.2020.9231424, 2023. [66] I. Saitov and A. Filchenkov, "CIS multilingual license plate detection and recognition based on convolutional and transformer neural networks," Procedia Computer Science, vol. 229, pp. 149-157, 2023. https://doi.org/10.1016/j.procs.2023.12.016 https://doi.org/10.1109/ICECA49313.2020.9297625 https://doi.org/10.1109/MVIP49855.2020.9116897 https://doi.org/10.1109/IICAIET49801.2020.9257843 https://doi.org/10.1109/ACCESS.2020.2994287 https://doi.org/10.1109/ACCESS.2020.3026181 https://doi.org/10.1109/MVIP49855.2020.9116910 https://doi.org/10.1109/ACCESS.2021.3097964 https://doi.org/10.1016/j.array.2022.100244 https://doi.org/10.1016/j.jksuci.2020.09.018 https://doi.org/10.1109/TLA.2022.9757747 https://doi.org/10.46908/tayacaja.v4i2.184 https://orcid.org/0000-0003-3345-8774 https://doi.org/10.1016/j.asej.2023.102520 https://doi.org/10.1109/ISCC.2016.7543901 https://doi.org/10.3390/jimaging9100201 https://doi.org/10.3390/app13084902 https://doi.org/10.1109/ITNT49337.2020.9253353 https://doi.org/10.1109/ICFEICT59519.2023.00036 https://doi.org/10.1109/ICCE-TW46550.2019.8991985 https://doi.org/10.23919/FRUCT48808.2020.9087537 https://doi.org/10.1109/ICITE50838.2020.9231424 https://doi.org/10.1016/j.procs.2023.12.016 1979 Edelweiss Applied Science and Technology ISSN: 2576-8484 Vol. 9, No. 2: 1967-1979, 2025 DOI: 10.55214/25768484.v9i2.4984 © 2025 by the authors; licensee Learning Gate [67] A. Y. Sugiyono, K. Adrio, K. Tanuwijaya, and K. M. Suryaningrum, "Extracting information from vehicle registration plate using OCR tesseract," Procedia Computer Science, vol. 227, pp. 932-938, 2023. https://doi.org/10.1016/j.procs.2023.10.600 [68] M. Jawale, P. William, A. Pawar, and N. Marriwala, "Implementation of number plate detection system for vehicle registration using IOT and recognition using CNN," Measurement: Sensors, vol. 27, p. 100761, 2023. https://doi.org/10.1016/j.measen.2023.100761 [69] F. Corrales Estrella and C. Sánchez Bocanegra, "Classification of radiological images using transformers models," Retrieved: https://openaccess.uoc.edu/bitstream/10609/147433/4/javicorralesTFM0123memoria.pdf, 2023. [70] H. Vargas, Y. Vladimir Tutor, and P. Palacios, "Comparison and evaluation of transformer models in the classification of medical images from the NIH Chest X-rays dataset," Retrieved: https://riunet.upv.es/bitstream/handle/10251/198542/Huallpa, 2023. [71] D. Satti Babu, T. V. Prasad, B. Revanth Sai, G. D. N. S. Sudheshna, N. Venkata Kishore, and P. Chandra Vamsi, "License plate recognition using neural networks," presented at the In International Conference on Frontiers of Intelligent Computing: Theory and Applications (pp. 341-350). Singapore: Springer Nature Singapore, 2023. [72] Á. Ramajo-Ballester, J. M. A. Moreno, and A. de la Escalera Hueso, "Dual license plate recognition and visual features encoding for vehicle identification," Robotics and Autonomous Systems, vol. 172, p. 104608, 2024. https://doi.org/10.1016/j.robot.2023.104608 [73] D. Neupane, A. Bhattarai, S. Aryal, M. R. Bouadjenek, U. Seok, and J. Seok, "Shine: A deep learning-based accessible parking management system," Expert Systems with Applications, vol. 238, p. 122205, 2024. https://doi.org/10.1016/j.eswa.2023.122205 https://doi.org/10.1016/j.procs.2023.10.600 https://doi.org/10.1016/j.measen.2023.100761 https://openaccess.uoc.edu/bitstream/10609/147433/4/javicorralesTFM0123memoria.pdf https://riunet.upv.es/bitstream/handle/10251/198542/Huallpa https://doi.org/10.1016/j.robot.2023.104608 https://doi.org/10.1016/j.eswa.2023.122205