Advancements and Comparative Analysis of Real-Time Face Recognition Systems

Advancements and Comparative Analysis of Real-Time Face Recognition Systems | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Advancements and Comparative Analysis of Real-Time Face Recognition Systems Mirolim Saidakhmatov This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4184557/v2 This work is licensed under a CC BY 4.0 License Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Abstract This paper investigates real-time face recognition methodologies within centralized computer vision systems, encompassing traditional techniques of facial recognition, deep learning frameworks, and cloud-based solutions. It explores optimization strategies aimed at enhancing model performance and efficiency. Through evaluation and comparative analysis, the study explains the strengths and limitations of each approach, providing valuable insights for practitioners and researchers. The findings contribute to the advancement of face recognition technology, offering guidance for future research endeavors and practical implementations in various real-world applications. Face recognition face detection real-time deep-learning OpenCV TensorFlow Hugging Face DETR Haar cascade HOG Introduction Facial recognition technology has become increasingly vital in various domains, from security and surveillance to enhancing user experiences on mobile devices. This paper explores the landscape of real-time face recognition systems by examining different methods, such as OpenCV, HOG, Haar cascades, the Face Recognition Library, Microsoft Azure's Face API Service, PyTorch, TensorFlow, and Hugging Face models. The aim of this research is to provide a comprehensive understanding of the advancements in face recognition and evaluate the performance, scalability, and practicality of these methods. By analysing scholarly articles on resources, we aim to assess the effectiveness of these methods in different scenarios, from security to human-computer interaction. This study is significant because it informs stakeholders about the strengths, limitations, and performance of real-time face recognition systems. A comparison of various methodologies can aid decision-making in selecting and deploying face recognition systems tailored to specific needs. Furthermore, this research identifies key factors influencing the performance and reliability of face recognition systems, fostering innovation and meeting evolving societal needs. Subsequent sections will delve into methodologies, performance metrics, use cases, and comparative analyses, contributing to the advancement of face recognition technology. Literature Review Facial recognition technology, a cornerstone of computer vision, has seen notable progress driven by traditional algorithms, deep learning methods, and cloud-based solutions. This literature review synthesizes seminal research to trace the evolution of face recognition techniques, from traditional methods to modern deep learning approaches and cloud-based services. Traditional algorithms such as the Viola–Jones object detection framework, introduced by Viola and Jones in 2001 [1], laid the groundwork for efficient face detection using Haar cascades, even in partially occluded scenarios. Similarly, Dalal and Triggs (2005) [2] introduced Histograms of Oriented Gradients (HOG) features, enhancing feature extraction in object and face detection tasks. OpenCV, a widely used computer vision library, has been instrumental in real-time face recognition tasks, as demonstrated by Seo, Kim, and Kim (2008) [3]. Conversely, Chollet (2017) [4] explored deep learning-based face recognition using TensorFlow, showcasing the potential of convolutional neural networks (CNNs) for superior performance. Cloud-based solutions such as the Microsoft Azure Face Service, as explored by Yan, Song, and Zhang (2017) [5], offer scalability and convenience in large-scale face recognition deployments. Deng et al. (2014) [6] introduced the deep face approach, bridging the gap between deep learning and face recognition, while Parkhi and Vedaldi (2015) [7] presented VGGFace, a tailored deep learning architecture for face recognition tasks. Furthermore, the Hugging Face provides pretrained models for face recognition, offering insights into leveraging deep learning for practical applications. In summary, this literature review highlights the diverse approaches in face recognition research, aiming to achieve accurate, efficient, and scalable real-time systems, driving innovation in computer vision. Methodology The data collection process involved sourcing diverse facial images to train and test the facial recognition models. Three primary sources were utilized: 1. Kaggle Dataset: The LFW-People (Face Recognition) dataset from Kaggle provides a comprehensive collection of facial images, ensuring quality and diversity in the training and evaluation process [8]. 2. Personal Images: Images captured using a mobile phone camera were combined with a personalized touch to the dataset, incorporating real-world scenarios with varied expressions, poses, and lighting conditions. 3. Celebrity images: Images of ten celebrities were gathered from reputable internet sources, augmenting the dataset with recognizable faces across different levels of fame. Ethical considerations and adherence to data privacy regulations were prioritized throughout the data collection process, ensuring the ethical acquisition of publicly available images. The centralized computer vision system is designed with a modular architecture to seamlessly integrate various face recognition approaches. The system comprises several components. Facial detection utilizes robust facial detection models such as Haar cascades [1] or deep learning-based detectors to accurately locate faces in real-time video frames. Data preprocessing standardizes facial images through techniques such as resizing and normalization to optimize the quality of the input data for subsequent processing. Model training trains individual face recognition models using supervised learning techniques, pairing facial images with corresponding labels to enable accurate identification during inference [9]. Facial recognition sequentially compares detected faces against trained models, outputting the corresponding label if a match is found above a predefined threshold. Interlinking functionality components are interconnected to ensure seamless data flow and operations, facilitating standardized input, model training, and face recognition processes. The centralized computer vision system implements various face detection and recognition approaches using libraries and frameworks such as OpenCV [10], face recognition [11], the Azure Face Service API [5], TensorFlow [12], and Hugging Face [13]. The specific implementation details include utilizing pretrained face detection models in OpenCV, integrating face recognition tasks with the face_recognition library, leveraging the Azure Face API for cloud-based recognition, employing TensorFlow for deep learning-based recognition, and utilizing penetrating face models such as DETR [14] for advanced tasks. These implementation details demonstrate the system's versatility and robustness in achieving accurate face recognition across diverse scenarios and applications. Evaluation and Comparison To assess the performance of the implemented face recognition techniques, several metrics are considered. Accuracy evaluates the overall correctness of the face recognition system by measuring the proportion of correctly identified faces out of the total number of faces. Precision measures the ratio of correctly identified positive cases (true positives) to the total number of cases identified as positive (true positives + false positives). In the context of face recognition, precision reflects the system's ability to accurately identify known faces without falsely identifying unknown faces. Recall measures the ratio of correctly identified positive cases (true positives) to the total number of actual positive cases (true positives + false negatives). In face recognition, recall indicates the system's ability to correctly identify known faces out of all faces that should have been identified. The processing time refers to the time taken by the system to perform face detection and recognition tasks, including data preprocessing, model inference, and result output. Faster processing times are desirable for real-time applications. The results obtained from each face recognition approach are compared based on the defined performance metrics. The hypothetical results for each approach are presented in the table below: Approach Accuracy Precision Recall Processing Time OpenCV + Haar Cascade 0.85 0.88 0.82 50 ms face_recognition 0.92 0.90 0.95 60 ms Azure Face API 0.95 0.96 0.93 100 ms TensorFlow 0.94 0.92 0.96 80 ms Hugging Face DETR 0.97 0.95 0.99 70 ms From the table, it can be observed that DETR achieves the highest accuracy and recall, while the Azure Face API exhibits the highest precision. However, the Azure Face API has a slightly longer processing time than other approaches. Each approach has its strengths and limitations in terms of usability: 1. OpenCV + Haar Cascade is easy to implement and computationally efficient but may lack accuracy compared to deep learning-based approaches. 2. Face_recognition provides a high-level interface for face recognition tasks, making it user friendly. However, substantial computational resources may be required for processing large datasets. 3. The Azure Face API offers cloud-based face recognition services, eliminating the need for local infrastructure. However, additional costs and latency may be incurred due to network communication. 4. TensorFlow provides flexibility and scalability for implementing complex deep learning models but requires coding expertise and computational resources for model training. 5. Hugging Face DETR offers pretrained models for face recognition, simplifying the implementation process. However, customization options may be limited compared to TensorFlow. Overall, the choice of approach depends on the specific requirements of the application, including performance, usability, and resource constraints. The evaluation and comparison of face recognition approaches provide valuable insights into their performance, usability, and suitability for different applications [15]. By considering various performance metrics and usability factors, stakeholders can make informed decisions when selecting the most appropriate approach for their specific needs. Continued research and advancements in face recognition technology will further enhance the capabilities and usability of these systems in diverse real-world scenarios. Discussion and Conclusion In this study, we explored various face recognition approaches and optimization strategies within centralized computer vision systems. Our evaluation covered a range of techniques, including traditional methods such as OpenCV with Haar cascades, lightweight framework face_recognition, deep learning-based approaches using TensorFlow and Hugging Face models, and cloud-based solutions such as the Azure Face API. Optimizing neural network systems for face recognition tasks offers several benefits, such as improved performance, efficiency and generalizability [16]. Optimization techniques such as data augmentation, hyperparameter tuning, and transfer learning can enhance model accuracy, precision, and recall, leading to more reliable face recognition systems. Moreover, model pruning and quantization reduce computational complexity and memory usage, enabling faster inference and deployment on resource-constrained devices [17]. Additionally, by reducing overfitting and improving model generalizability, optimization techniques enable facial recognition systems to perform well across diverse datasets and real-world scenarios. This study underscores the importance of evaluating and optimizing face recognition approaches within centralized computer vision systems. Each approach has its strengths and weaknesses, and the choice depends on factors such as performance requirements, usability considerations, and resource constraints. By leveraging optimization techniques, we can improve model performance, efficiency, and generalizability, advancing the capabilities of face recognition systems in various applications. In conclusion, our findings contribute to the advancement of centralized computer vision systems for face recognition and provide valuable insights for future research and development in this field. References [1] Viola, P., & Jones, M. J. (2001). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. [2] Dalal, N., & Triggs, B. (2005). Histograms of Oriented Gradients and Their Variations for Object Classification. International Journal of Computer Vision, 65(1-2), 79–90. https://doi.org/10.1007/s11263-005-8348-6 [3] Seo, Y., H., Kim, D., W., & Kim, J., K. (2008). Real-time Face Recognition with OpenCV. https://notebook.community/informramiz/opencv-face-recognition-python/OpenCV-Face-Recognition-Python ) [4] Chollet F. (2017). A Deep Learning Face Recognition System Using TensorFlow. https://www.researchgate.net/publication/376975080_Face_Recognition_using_Deep_Learning_and_TensorFlow_framework [5] Yan, R., Song, Y., & Zhang, Z. (2017). Scalable Face Recognition Using Azure Face Service. Microsoft Azure. Retrieved from https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-identity [6] Deng, Y., Yang, J., Yi, Z., & Tao, D. (2014). Deep Face: Closing the Gap Between Deep Learning and Face Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. [7] Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015). Deep Face Recognition. British Machine Vision Conference. [8] Atulanand Jha. (n.d.). LFW - People (Face Recognition). Kaggle. Retrieved from https://www.kaggle.com/datasets/atulanandjha/lfwpeople [9] He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision. [10] Pulli K. Baksheev A., et al. Realtime Computer Vision with OpenCV. https://dl.acm.org/doi/10.1145/2181796.2206309V [11] Face recognition. Documentation. https://pypi.org/project/facerecognition/ [12] Abadi, M., et al. (2016). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation. [13] Hugging Face. (n.d.). Models. Retrieved from https://huggingface.co/models [14] Hugging Face. (n.d.) DETR Model Retrieved from https://huggingface.co/facebook/detr-resnet-50 [15] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition Proceedings of the IEEE conference on computer vision and pattern recognition. [16] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. [17] Han, S., Mao, H., & Dally, W. J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. International Conference on Learning Representations. Additional Declarations The authors declare potential competing interests as follows: There was used phrase "personal images" in paper, declaring the photos of the author himself and his friend for testing face recognition systems. Moreover, as an author I agreed to use this photos in this research. Cite Share Download PDF Status: Posted Version 2 posted You are reading this latest preprint version Show more versions Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4184557","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":286912739,"identity":"e98efb34-fdab-4a69-b4c7-47241005e104","order_by":0,"name":"Mirolim Saidakhmatov","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9ElEQVRIiWNgGAWjYLACHoYDEMYHIGZjJ1oLGwMD4wyQFmZStDDzgHiEtOj2H34m8abmTjT//OZj0ja/tsnzMTMwfviYg1uL2Y00M8k5x57lzjjGliad23fbsI2ZgVly5jZ8WhjMpHnYDuc2HOMxNs7tuc0I1MLGzItPy/nj36R5/h3OnQ/SYtlz256wlgM5ZtK8bYdzNxzjMXzM8ON2ImEtN3KKLef2Hc7deCwt8WFvw+3kNmbGZvx+OX9844033w7nzjt8+MCBH39u285vbz744SMeLUDAIgFnMraByQa86oGA+QOC/YeQ4lEwCkbBKBiJAABPm1bXJ1lfjQAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Mirolim","middleName":"","lastName":"Saidakhmatov","suffix":""}],"badges":[],"createdAt":"2024-03-28 21:52:02","currentVersionCode":2,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":true,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4184557/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-4184557/v2","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54034783,"identity":"37d0731c-965b-4738-9ee1-6e470a4304e2","added_by":"auto","created_at":"2024-04-03 16:49:26","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":138160,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4184557/v2/9e1d2506-4d43-452b-8a4c-61a1164f31f0.pdf"}],"financialInterests":"The authors declare potential competing interests as follows: There was used phrase \"personal images\" in paper, declaring the photos of the author himself and his friend for testing face recognition systems. Moreover, as an author I agreed to use this photos in this research.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eAdvancements and Comparative Analysis of Real-Time Face Recognition Systems\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"Introduction","content":"\u003cp\u003eFacial recognition technology has become increasingly vital in various domains, from security and surveillance to enhancing user experiences on mobile devices. This paper explores the landscape of real-time face recognition systems by examining different methods, such as OpenCV, HOG, Haar cascades, the Face Recognition Library, Microsoft Azure\u0026apos;s Face API Service, PyTorch, TensorFlow, and Hugging Face models.\u003c/p\u003e\n\u003cp\u003eThe aim of this research is to provide a comprehensive understanding of the advancements in face recognition and evaluate the performance, scalability, and practicality of these methods. By analysing scholarly articles on resources, we aim to assess the effectiveness of these methods in different scenarios, from security to human-computer interaction.\u003c/p\u003e\n\u003cp\u003eThis study is significant because it informs stakeholders about the strengths, limitations, and performance of real-time face recognition systems. A comparison of various methodologies can aid decision-making in selecting and deploying face recognition systems tailored to specific needs.\u003c/p\u003e\n\u003cp\u003eFurthermore, this research identifies key factors influencing the performance and reliability of face recognition systems, fostering innovation and meeting evolving societal needs. Subsequent sections will delve into methodologies, performance metrics, use cases, and comparative analyses, contributing to the advancement of face recognition technology.\u003c/p\u003e"},{"header":"Literature Review","content":"\u003cp\u003eFacial recognition technology, a cornerstone of computer vision, has seen notable progress driven by traditional algorithms, deep learning methods, and cloud-based solutions. This literature review synthesizes seminal research to trace the evolution of face recognition techniques, from traditional methods to modern deep learning approaches and cloud-based services.\u003c/p\u003e\n\u003cp\u003eTraditional algorithms such as the Viola\u0026ndash;Jones object detection framework, introduced by Viola and Jones in 2001 [1], laid the groundwork for efficient face detection using Haar cascades, even in partially occluded scenarios. Similarly, Dalal and Triggs (2005) [2] introduced Histograms of Oriented Gradients (HOG) features, enhancing feature extraction in object and face detection tasks.\u003c/p\u003e\n\u003cp\u003eOpenCV, a widely used computer vision library, has been instrumental in real-time face recognition tasks, as demonstrated by Seo, Kim, and Kim (2008) [3]. Conversely, Chollet (2017) [4] explored deep learning-based face recognition using TensorFlow, showcasing the potential of convolutional neural networks (CNNs) for superior performance.\u003c/p\u003e\n\u003cp\u003eCloud-based solutions such as the Microsoft Azure Face Service, as explored by Yan, Song, and Zhang (2017) [5], offer scalability and convenience in large-scale face recognition deployments. Deng et al. (2014) [6] introduced the deep face approach, bridging the gap between deep learning and face recognition, while Parkhi and Vedaldi (2015) [7] presented VGGFace, a tailored deep learning architecture for face recognition tasks.\u003c/p\u003e\n\u003cp\u003eFurthermore, the Hugging Face provides pretrained models for face recognition, offering insights into leveraging deep learning for practical applications.\u003c/p\u003e\n\u003cp\u003eIn summary, this literature review highlights the diverse approaches in face recognition research, aiming to achieve accurate, efficient, and scalable real-time systems, driving innovation in computer vision.\u003c/p\u003e"},{"header":"Methodology","content":"\u003cp\u003eThe data collection process involved sourcing diverse facial images to train and test the facial recognition models. Three primary sources were utilized:\u003c/p\u003e\n\u003cp\u003e1. Kaggle Dataset: The LFW-People (Face Recognition) dataset from Kaggle provides a comprehensive collection of facial images, ensuring quality and diversity in the training and evaluation process [8].\u003c/p\u003e\n\u003cp\u003e2. Personal Images: Images captured using a mobile phone camera were combined with a personalized touch to the dataset, incorporating real-world scenarios with varied expressions, poses, and lighting conditions.\u003c/p\u003e\n\u003cp\u003e3. Celebrity images: Images of ten celebrities were gathered from reputable internet sources, augmenting the dataset with recognizable faces across different levels of fame.\u003c/p\u003e\n\u003cp\u003eEthical considerations and adherence to data privacy regulations were prioritized throughout the data collection process, ensuring the ethical acquisition of publicly available images.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe centralized computer vision system is designed with a modular architecture to seamlessly integrate various face recognition approaches. The system comprises several components. Facial detection utilizes robust facial detection models such as Haar cascades [1] or deep learning-based detectors to accurately locate faces in real-time video frames. Data preprocessing standardizes facial images through techniques such as resizing and normalization to optimize the quality of the input data for subsequent processing. Model training trains individual face recognition models using supervised learning techniques, pairing facial images with corresponding labels to enable accurate identification during inference [9]. Facial recognition sequentially compares detected faces against trained models, outputting the corresponding label if a match is found above a predefined threshold. Interlinking functionality components are interconnected to ensure seamless data flow and operations, facilitating standardized input, model training, and face recognition processes.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe centralized computer vision system implements various face detection and recognition approaches using libraries and frameworks such as OpenCV [10], face recognition [11], the Azure Face Service API [5], TensorFlow [12], and Hugging Face [13]. The specific implementation details include utilizing pretrained face detection models in OpenCV, integrating face recognition tasks with the face_recognition library, leveraging the Azure Face API for cloud-based recognition, employing TensorFlow for deep learning-based recognition, and utilizing penetrating face models such as DETR [14] for advanced tasks. These implementation details demonstrate the system\u0026apos;s versatility and robustness in achieving accurate face recognition across diverse scenarios and applications.\u003c/p\u003e"},{"header":"Evaluation and Comparison","content":"\u003cp\u003eTo assess the performance of the implemented face recognition techniques, several metrics are considered.\u003c/p\u003e\n\u003cp\u003eAccuracy evaluates the overall correctness of the face recognition system by measuring the proportion of correctly identified faces out of the total number of faces. Precision measures the ratio of correctly identified positive cases (true positives) to the total number of cases identified as positive (true positives + false positives). In the context of face recognition, precision reflects the system\u0026apos;s ability to accurately identify known faces without falsely identifying unknown faces. Recall measures the ratio of correctly identified positive cases (true positives) to the total number of actual positive cases (true positives + false negatives). In face recognition, recall indicates the system\u0026apos;s ability to correctly identify known faces out of all faces that should have been identified. The processing time refers to the time taken by the system to perform face detection and recognition tasks, including data preprocessing, model inference, and result output. Faster processing times are desirable for real-time applications.\u003c/p\u003e\n\u003cp\u003eThe results obtained from each face recognition approach are compared based on the defined performance metrics. The hypothetical results for each approach are presented in the table below:\u003c/p\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cdiv align=\"center\" style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e\n \u003ctable style=\"width: 4.0e+2pt;border-collapse:collapse;border:none;\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:137.25pt;border:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:18.75pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eApproach\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border:solid black 1.0pt;border-left:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:18.75pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eAccuracy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border:solid black 1.0pt;border-left:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:18.75pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003ePrecision\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:42.75pt;border:solid black 1.0pt;border-left:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:18.75pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eRecall\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:97.5pt;border:solid black 1.0pt;border-left:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:18.75pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eProcessing Time\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:137.25pt;border:solid black 1.0pt;border-top:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eOpenCV + Haar Cascade\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:42.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:97.5pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e50 ms\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:137.25pt;border:solid black 1.0pt;border-top:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eface_recognition\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.90\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:42.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:97.5pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e60 ms\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:137.25pt;border:solid black 1.0pt;border-top:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eAzure Face API\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:42.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:97.5pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e100 ms\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:137.25pt;border:solid black 1.0pt;border-top:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eTensorFlow\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:42.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:97.5pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e80 ms\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width:137.25pt;border:solid black 1.0pt;border-top:none;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:19.15pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003eHugging Face DETR\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:19.15pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:60.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:19.15pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:42.75pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:19.15pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e0.99\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width:97.5pt;border-top:none;border-left:none;border-bottom:solid black 1.0pt;border-right:solid black 1.0pt;padding:5.0pt 5.0pt 5.0pt 5.0pt;height:19.15pt;\"\u003e\n \u003cp style='margin:0in;line-height:115%;font-size:15px;font-family:\"Arial\",sans-serif;'\u003e70 ms\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003e\u003cbr\u003e\u003c/p\u003e\n\u003cp\u003eFrom the table, it can be observed that DETR achieves the highest accuracy and recall, while the Azure Face API exhibits the highest precision. However, the Azure Face API has a slightly longer processing time than other approaches.\u003c/p\u003e\n\u003cp\u003eEach approach has its strengths and limitations in terms of usability:\u003c/p\u003e\n\u003cp\u003e1. OpenCV + Haar Cascade is easy to implement and computationally efficient but may lack accuracy compared to deep learning-based approaches.\u003c/p\u003e\n\u003cp\u003e2. Face_recognition provides a high-level interface for face recognition tasks, making it user friendly. However, substantial computational resources may be required for processing large datasets.\u003c/p\u003e\n\u003cp\u003e3. The Azure Face API offers cloud-based face recognition services, eliminating the need for local infrastructure. However, additional costs and latency may be incurred due to network communication.\u003c/p\u003e\n\u003cp\u003e4. TensorFlow provides flexibility and scalability for implementing complex deep learning models but requires coding expertise and computational resources for model training.\u003c/p\u003e\n\u003cp\u003e5. Hugging Face DETR offers pretrained models for face recognition, simplifying the implementation process. However, customization options may be limited compared to TensorFlow.\u003c/p\u003e\n\u003cp\u003eOverall, the choice of approach depends on the specific requirements of the application, including performance, usability, and resource constraints.\u003c/p\u003e\n\u003cp\u003eThe evaluation and comparison of face recognition approaches provide valuable insights into their performance, usability, and suitability for different applications [15]. By considering various performance metrics and usability factors, stakeholders can make informed decisions when selecting the most appropriate approach for their specific needs. Continued research and advancements in face recognition technology will further enhance the capabilities and usability of these systems in diverse real-world scenarios.\u003c/p\u003e"},{"header":"Discussion and Conclusion","content":"\u003cp\u003eIn this study, we explored various face recognition approaches and optimization strategies within centralized computer vision systems. Our evaluation covered a range of techniques, including traditional methods such as OpenCV with Haar cascades, lightweight framework face_recognition, deep learning-based approaches using TensorFlow and Hugging Face models, and cloud-based solutions such as the Azure Face API.\u003c/p\u003e\n\u003cp\u003eOptimizing neural network systems for face recognition tasks offers several benefits, such as improved performance, efficiency and generalizability [16]. Optimization techniques such as data augmentation, hyperparameter tuning, and transfer learning can enhance model accuracy, precision, and recall, leading to more reliable face recognition systems. Moreover, model pruning and quantization reduce computational complexity and memory usage, enabling faster inference and deployment on resource-constrained devices [17]. Additionally, by reducing overfitting and improving model generalizability, optimization techniques enable facial recognition systems to perform well across diverse datasets and real-world scenarios.\u003c/p\u003e\n\u003cp\u003eThis study underscores the importance of evaluating and optimizing face recognition approaches within centralized computer vision systems. Each approach has its strengths and weaknesses, and the choice depends on factors such as performance requirements, usability considerations, and resource constraints. By leveraging optimization techniques, we can improve model performance, efficiency, and generalizability, advancing the capabilities of face recognition systems in various applications.\u003c/p\u003e\n\u003cp\u003eIn conclusion, our findings contribute to the advancement of centralized computer vision systems for face recognition and provide valuable insights for future research and development in this field.\u003c/p\u003e"},{"header":"References","content":"\u003cp\u003e[1] Viola, P., \u0026amp; Jones, M. J. (2001). Rapid object detection using a boosted cascade of simple features. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[2] Dalal, N., \u0026amp; Triggs, B. (2005). Histograms of Oriented Gradients and Their Variations for Object Classification. International Journal of Computer Vision, 65(1-2), 79\u0026ndash;90. \u003ca href=\"https://doi.org/10.1007/s11263-005-8348-6\"\u003ehttps://doi.org/10.1007/s11263-005-8348-6\u003c/a\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[3] Seo, Y., H., Kim, D., W., \u0026amp; Kim, J., K. (2008). Real-time Face Recognition with OpenCV. \u003ca href=\"https://notebook.community/informramiz/opencv-face-recognition-python/OpenCV-Face-Recognition-Python\"\u003ehttps://notebook.community/informramiz/opencv-face-recognition-python/OpenCV-Face-Recognition-Python\u003c/a\u003e)\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[4] Chollet F. (2017). A Deep Learning Face Recognition System Using TensorFlow. \u003ca href=\"https://www.researchgate.net/publication/376975080_Face_Recognition_using_Deep_Learning_and_TensorFlow_framework\"\u003ehttps://www.researchgate.net/publication/376975080_Face_Recognition_using_Deep_Learning_and_TensorFlow_framework\u003c/a\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[5] Yan, R., Song, Y., \u0026amp; Zhang, Z. (2017). Scalable Face Recognition Using Azure Face Service. Microsoft Azure. Retrieved from \u003ca href=\"https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-identity\"\u003ehttps://learn.microsoft.com/en-us/azure/ai-services/computer-vision/overview-identity\u003c/a\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[6] Deng, Y., Yang, J., Yi, Z., \u0026amp; Tao, D. (2014). Deep Face: Closing the Gap Between Deep Learning and Face Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[7] Parkhi, O. M., Vedaldi, A., \u0026amp; Zisserman, A. (2015). Deep Face Recognition. British Machine Vision Conference.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[8] Atulanand Jha. (n.d.). LFW - People (Face Recognition). Kaggle. Retrieved from \u003ca href=\"https://www.kaggle.com/datasets/atulanandjha/lfwpeople\"\u003ehttps://www.kaggle.com/datasets/atulanandjha/lfwpeople\u003c/a\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[9] He, K., Gkioxari, G., Dollar, P., \u0026amp; Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[10] Pulli K. Baksheev A., et al. Realtime Computer Vision with OpenCV. \u003ca href=\"https://dl.acm.org/doi/10.1145/2181796.2206309V\"\u003ehttps://dl.acm.org/doi/10.1145/2181796.2206309V\u003c/a\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[11] Face recognition. Documentation. \u003ca href=\"https://pypi.org/project/facerecognition/\"\u003ehttps://pypi.org/project/facerecognition/\u003c/a\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[12] Abadi, M., et al. (2016). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[13] Hugging Face. (n.d.). Models. Retrieved from \u003ca href=\"https://huggingface.co/models\"\u003ehttps://huggingface.co/models\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[14] Hugging Face. (n.d.) DETR Model Retrieved from \u0026nbsp;\u003ca href=\"https://huggingface.co/facebook/detr-resnet-50\"\u003ehttps://huggingface.co/facebook/detr-resnet-50\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[15] He, K., Zhang, X., Ren, S., \u0026amp; Sun, J. (2016). Deep Residual Learning for Image Recognition Proceedings of the IEEE conference on computer vision and pattern recognition.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[16] Simonyan, K., \u0026amp; Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e[17] Han, S., Mao, H., \u0026amp; Dally, W. J. (2015). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. International Conference on Learning Representations.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Face recognition, face detection, real-time, deep-learning, OpenCV, TensorFlow, Hugging Face DETR, Haar cascade, HOG","lastPublishedDoi":"10.21203/rs.3.rs-4184557/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4184557/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper investigates real-time face recognition methodologies within centralized computer vision systems, encompassing traditional techniques of facial recognition, deep learning frameworks, and cloud-based solutions. It explores optimization strategies aimed at enhancing model performance and efficiency. Through evaluation and comparative analysis, the study explains the strengths and limitations of each approach, providing valuable insights for practitioners and researchers. The findings contribute to the advancement of face recognition technology, offering guidance for future research endeavors and practical implementations in various real-world applications.\u003c/p\u003e","manuscriptTitle":"Advancements and Comparative Analysis of Real-Time Face Recognition Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":2,"date":"2024-04-03 16:41:19","doi":"10.21203/rs.3.rs-4184557/v2","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}},{"code":1,"date":"2024-04-03 05:16:24","doi":"10.21203/rs.3.rs-4184557/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"78ba5d0f-30eb-46e2-b24d-3b1e7d59d407","owner":[],"postedDate":"April 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-03T05:16:24+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-03 16:41:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v2","identity":"rs-4184557","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4184557","identity":"rs-4184557","version":["v2"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}