{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T20:06:26Z","timestamp":1792094786746,"version":"4.4.0"},"reference-count":71,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T00:00:00Z","timestamp":1784505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Adverse drug events (ADEs) remain a major cause of preventable healthcare complications due to incorrect pill identification, dosage errors, and confusion between visually identical pills, particularly among older adults, visually impaired individuals, and people with limited health literacy. Recent advances in artificial intelligence and computer vision have enabled automated pill recognition systems. However, many existing methods address detection, classification, and imprint recognition as isolated tasks without providing a lightweight unified framework suitable for real-time healthcare deployment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study presents a lightweight hybrid framework for multi-pill and multi-attribute recognition to support pharmacovigilance and artificial intelligence-driven clinical decision support. The proposed framework integrates pill detection using YOLOv26n, MobileNetV4-ConvSmall-based classification, EasyOCR-based imprint recognition, and metadata retrieval into a unified prediction pipeline. A customized benchmark dataset containing 400 pill classes, each with 50 images, for a total of 20,000 images, was used for classification. Each image has two pills, comprising 40,000 manually labeled pill instances used for detection. Comparative experiments, functional comparisons with existing pill recognition systems, and cross-device qualitative evaluations were conducted to assess framework performance, robustness, and deployment feasibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>YOLOv26n achieved a precision of 0.963, a recall of 0.982, mAP@50 of 0.989, and mAP@50-95 of 0.981, while MobileNetV4-ConvSmall achieved a class accuracy of 99.60% with higher performance in pill shape and color accuracy. Comparative optical character recognition (OCR) analysis shows that EasyOCR achieved more reliable imprint recognition performance than TesseractOCR and TrOCR. Comparative framework evaluation demonstrated that the YOLOv26n with MobileNetV4-ConvSmall combination achieved the high overall recognition performance, obtaining a Top-1 accuracy of 89.83% and a Top-5 accuracy of 99.49%. Cross-device qualitative evaluation using smartphone cameras and direct laptop uploads demonstrated robust performance under varying image noise conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed framework demonstrates the potential of lightweight deep learning architectures for scalable medication identification and AI-assisted pharmacovigilance applications. By integrating detection, classification, imprint recognition, and metadata retrieval into a unified framework, the proposed system has the potential to support medication identification and improve assistive healthcare workflows. The final clinical judgment and medication verification should remain under the supervision of a healthcare professional.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1890296","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T05:34:11Z","timestamp":1784525651000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A lightweight hybrid deep learning framework for multi-pill detection, multi-attribute recognition, OCR-based imprint analysis, and metadata retrieval"],"prefix":"10.3389","volume":"9","author":[{"given":"A.","family":"Sai Sachin","sequence":"first","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.","family":"Karthikeyan","sequence":"additional","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/IoT-NC.2013.6694053","article-title":"\u201cThe smartphone as a medical device: assessing enablers, benefits and challenges,\u201d","author":"Agu","year":"2013","journal-title":"2013 IEEE international workshop of internet-of-things networking and control (IoT-NC)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e28281","DOI":"10.1016\/j.heliyon.2024.e41137","article-title":"Deep learning-based object detection algorithms in medical imaging: systematic review","volume":"11","author":"Albuquerque","year":"2025","journal-title":"Heliyon"},{"key":"B3","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3390\/surgeries6040087","article-title":"Data-leakage-aware preoperative prediction of postoperative complications from structured data and preoperative clinical notes","volume":"6","author":"Amanatidis","year":"2025","journal-title":"Surgeries"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1821686","DOI":"10.3389\/fdsfr.2026.1821686","article-title":"Global pharmacovigilance reporting: comparative analysis of adverse event obligations across five major regulatory authorities","volume":"6","author":"Bernaus","year":"2026","journal-title":"Front. Drug Saf. Regul"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2601.12882","article-title":"Yolo26: An analysis of nms-free end-to-end framework for real-time object detection","author":"Chakrabarty","year":"2026","journal-title":"arXiv [Preprint"},{"key":"B6","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/ICSPC63060.2024.10862882","article-title":"\u201cTransfer learning for few-shot pill image recognition,\u201d","author":"Chee","year":"2024","journal-title":"2024 IEEE 12th conference on systems, process and control (ICSPC)"},{"key":"B7","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1109\/MICCIS66057.2025.00047","article-title":"\u201cResearch on pill detection based on improved yolo11,\u201d","author":"Chen","year":"2025","journal-title":"2025 3rd international conference on mobile internet, cloud computing and information security (MICCIS)"},{"key":"B8","doi-asserted-by":"publisher","first-page":"e30486","DOI":"10.1016\/j.heliyon.2024.e30486","article-title":"Automated medication verification system (amvs): system based on edge detection and cnn classification drug on embedded systems","volume":"10","author":"Chiu","year":"2024","journal-title":"Heliyon"},{"key":"B9","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1108\/17410380610678792","article-title":"The applicability of a multi-attribute classification framework in the healthcare industry","volume":"17","author":"Danas","year":"2006","journal-title":"J. Manuf. Technol. Manag"},{"key":"B10","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1109\/CISCE62493.2024.10653353","article-title":"\u201cReal-time pill identification for the visually impaired using deep learning,\u201d","author":"Dang","year":"2024","journal-title":"2024 6th international conference on communications, information system and computer engineering (CISCE)"},{"key":"B11","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/978-3-032-08359-3_28","article-title":"\u201cComparison of neural network training time using cpu and gpu with nvidia cuda technology,\u201d","author":"Dymora","year":"2025","journal-title":"Conference on automation"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e57728","DOI":"10.7759\/cureus.57728","article-title":"Ai-driven clinical decision support systems: an ongoing pursuit of potential","volume":"16","author":"Elhaddad","year":"2024","journal-title":"Cureus"},{"key":"B13","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1186\/s12859-020-03724-x","article-title":"Dpddi: a deep predictor for drug-drug interactions","volume":"21","author":"Feng","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1186\/s12877-024-05595-w","article-title":"Exploring the reasons for self-administration medication errors among illiterate and low-literate community-dwelling older adults with polypharmacy: a qualitative study","volume":"24","author":"Ghassab-Abdollahi","year":"2024","journal-title":"BMC Geriatr"},{"key":"B15","doi-asserted-by":"publisher","first-page":"86","DOI":"10.5281\/zenodo.15024999","article-title":"An intelligent web application for drug information retrieval using optical character recognition and deep learning","volume":"152","author":"Ghazaryan","year":"2025","journal-title":"Nor. J. Dev. Int. Sci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"185","DOI":"10.22329\/jtl.v20i1.9970","article-title":"Deep learning methods towards a pedagogical framework and implementation strategy: a study of information technology education curriculum development in indonesia","volume":"20","author":"Halomoan","year":"2026","journal-title":"J. Teach. Learn"},{"key":"B17","doi-asserted-by":"publisher","first-page":"290","DOI":"10.4082\/kjfm.21.0193","article-title":"Pharmacovigilance and its importance for primary health care professionals","volume":"43","author":"Hamid","year":"2022","journal-title":"Korean J. Fam. Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e3710","DOI":"10.1002\/ett.3710","article-title":"Edge computing in smart health care systems: review, challenges, and research directions","volume":"33","author":"Hartmann","year":"2022","journal-title":"Trans. Emerg. Telecommun. Technol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1038\/s41746-022-00665-y","article-title":"Smartphone camera oximetry in an induced hypoxemia study","volume":"5","author":"Hoffman","year":"2022","journal-title":"NPJ Dig. Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"40902","DOI":"10.1117\/1.JBO.26.4.040902","article-title":"Smartphone-based imaging systems for medical applications: a critical review","volume":"26","author":"Hunt","year":"2021","journal-title":"J. Biomed. Opt"},{"key":"B21","doi-asserted-by":"publisher","first-page":"2666","DOI":"10.47738\/jads.v6i4.936","article-title":"Yolov12 model optimization for monitoring occupational health and safety in hospital archive rooms","volume":"6","author":"Jepisah","year":"2025","journal-title":"J. Appl. Data Sci"},{"key":"B22","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3126\/prod.v3i1.78454","article-title":"Easypill: Ai-powered pill identification for enhancing medication safety and reducing errors by using mobilenet cnns","volume":"3","author":"Jha","year":"2025","journal-title":"J. Prod. Discourse"},{"key":"B23","doi-asserted-by":"publisher","first-page":"356","DOI":"10.3390\/math14020356","article-title":"Go-pill: a geometry-aware ocr pipeline for reliable recognition of debossed and curved pill imprints","volume":"14","author":"Jo","year":"2026","journal-title":"Mathematics"},{"key":"B24","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1007\/s12239-025-00336-3","article-title":"Development of yolo-based object detection model with bounding box separation techniques","volume":"27","author":"Kang","year":"2026","journal-title":"Int. J. Automot. Technol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1101\/2025.11.14.25340278","article-title":"Development and clinical validation of lightweight, multimodal machine learning models for smartphone-based cataract detection and classification","author":"Kannan","year":"2025","journal-title":"medRxiv [Preprint"},{"key":"B26","doi-asserted-by":"publisher","first-page":"103164","DOI":"10.1016\/j.jnca.2021.103164","article-title":"A systematic review of iot in healthcare: applications, techniques, and trends","volume":"192","author":"Kashani","year":"2021","journal-title":"J. Netw. Comput. Applic"},{"key":"B27","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1007\/s44291-025-00122-6","article-title":"Real-time pill identification and classification using deep learning framework for medicine inspection systems","volume":"2","author":"Kavitha","year":"2025","journal-title":"Discover Electr"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.29103\/jacka.v3i1.24732","article-title":"The role of deep learning in advancing computer vision applications: a comprehensive systematic review","volume":"3","author":"Khadem","year":"2026","journal-title":"J. Adv. Comput. Knowl. Algorithms"},{"key":"B29","doi-asserted-by":"publisher","first-page":"5644","DOI":"10.3390\/app15105644","article-title":"Advanced pharmaceutical recognition system based on deep learning for mobile medication identification","volume":"15","author":"Kim","year":"2025","journal-title":"Appl. Sci"},{"key":"B30","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3390\/chemosensors10010004","article-title":"Pill detection model for medicine inspection based on deep learning","volume":"10","author":"Kwon","year":"2021","journal-title":"Chemosensors"},{"key":"B31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1177\/2042098615615472","article-title":"Predicting risk of adverse drug reactions in older adults","volume":"7","author":"Lavan","year":"2016","journal-title":"Ther. Adv. Drug Saf"},{"key":"B32","doi-asserted-by":"publisher","first-page":"60859","DOI":"10.1109\/ACCESS.2025.3557569","article-title":"Enhanced multi-pill detection and recognition using vfi augmentation and auto-labeling for limited single-pill data","volume":"13","author":"Lee","year":"2025","journal-title":"IEEE Access"},{"key":"B33","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1515\/auto-2022-0107","article-title":"A concept for providing and utilizing metadata in data analytics applications","volume":"71","author":"Li","year":"2023","journal-title":"At-Automatisierungstechnik"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3139","DOI":"10.1109\/TPAMI.2022.3180392","article-title":"Generalized focal loss: Towards efficient representation learning for dense object detection","volume":"45","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1007\/s10489-025-06956-7","article-title":"Recognizing unknowns: a survey on visual open-set recognition","volume":"55","author":"Li","year":"2025","journal-title":"Appl. Intell"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IITCEE67948.2026.11394638","article-title":"\u201cComparative evaluation of yolov12 and sahi for medication identification in hospital pharmacies,\u201d","author":"Malepati","year":"2026","journal-title":"2026 international conference on intelligent and innovative technologies in computing, electrical and electronics (IITCEE)"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40801-017-0125-6","article-title":"Adverse drug events and medication errors in african hospitals: a systematic review","volume":"5","author":"Mekonnen","year":"2018","journal-title":"Drugs Real World Outcomes"},{"key":"B38","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.medcli.2019.08.007","article-title":"Reacciones adversas a medicamentos","volume":"154","author":"Montan\u00e9","year":"2020","journal-title":"Med. Clin"},{"key":"B39","doi-asserted-by":"publisher","first-page":"20420986251361435","DOI":"10.1177\/20420986251361435","article-title":"Artificial intelligence in pharmacovigilance: advancing drug safety monitoring and regulatory integration","volume":"16","author":"Nagar","year":"2025","journal-title":"Ther. Adv. Drug Saf"},{"key":"B40","unstructured":"Pillbox Archived Drug and Pill Image Dataset Retired on January 28, 2021\n          \n          2021"},{"key":"B41","doi-asserted-by":"publisher","first-page":"e0291865","DOI":"10.1371\/journal.pone.0291865","article-title":"High accurate and explainable multi-pill detection framework with graph neural network-assisted multimodal data fusion","volume":"18","author":"Nguyen","year":"2023","journal-title":"PLoS ONE"},{"key":"B42","doi-asserted-by":"publisher","first-page":"3693","DOI":"10.32604\/cmc.2025.060793","article-title":"A comprehensive review of pill image recognition","volume":"82","author":"Nguyen","year":"2025","journal-title":"Comput. Mater. Contin"},{"key":"B43","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/s11554-025-01831-7","article-title":"Real-time pill image recognition on edge devices with adaptive lightweight attention","volume":"23","author":"Nguyen","year":"2026","journal-title":"J. Real-Time Image Process"},{"key":"B44","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s12911-025-03316-w","article-title":"Modeling anesthetic-drug label detection for low-resource operating rooms","volume":"26","author":"Nsumba","year":"2026","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"B45","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/ICCAE56788.2023.10111387","article-title":"\u201cMedicine classification using yolov4 and tesseract ocr,\u201d","author":"Paglinawan","year":"2023","journal-title":"2023 15th international conference on computer and automation engineering (ICCAE)"},{"key":"B46","doi-asserted-by":"publisher","first-page":"300","DOI":"10.3390\/bdcc9120300","article-title":"Unordered stacked pillbox detection algorithm based on improved yolov8","volume":"9","author":"Pan","year":"2025","journal-title":"Big Data Cogn. Comput"},{"key":"B47","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1007\/978-3-031-97119-8_33","article-title":"\u201cEnhancing medication adherence with computer vision: object detection models for pill detection,\u201d","author":"Pinto","year":"2025","journal-title":"World conference on information systems and technologies"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1007\/s44163-026-01405-x","article-title":"A hybrid framework for pill identification using convolutional neural networks and optical character recognition","author":"Pujari","year":"2026","journal-title":"Discover Artif. Intell"},{"key":"B49","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-031-73661-2_5","article-title":"\u201cMobilenetv4: universal models for the mobile ecosystem,\u201d","author":"Qin","year":"2024","journal-title":"European conference on computer vision"},{"key":"B50","doi-asserted-by":"publisher","first-page":"28","DOI":"10.55299\/ijphe.v5i2.1724","article-title":"Automatic pill counting using yolov8 to improve medication distribution accuracy","volume":"5","author":"Qomariah","year":"2026","journal-title":"Int. J. Public Health Excell"},{"key":"B51","doi-asserted-by":"publisher","first-page":"88","DOI":"10.15282\/mekatronika.v6i2.11020","article-title":"Pill recognition via deep learning approaches","volume":"6","author":"Ramlee","year":"2024","journal-title":"Mekatronika"},{"key":"B52","doi-asserted-by":"publisher","first-page":"17905","DOI":"10.1109\/ACCESS.2026.3654582","article-title":"A hybrid-based deep learning framework for pill detection, multi-attribute classification, and prediction with metadata retrieval","volume":"14","author":"Sachin","year":"2026","journal-title":"IEEE Access"},{"key":"B53","doi-asserted-by":"publisher","first-page":"012001","DOI":"10.1088\/1742-6596\/2641\/1\/012001","article-title":"Analysis of optical character recognition using easyocr under image degradation","volume":"2641","author":"Salehudin","year":"2023","journal-title":"J. Phys.: Conf. Ser"},{"key":"B54","doi-asserted-by":"publisher","first-page":"3057","DOI":"10.1109\/IGARSS.2015.7326461","article-title":"\u201cProper comparison among methods using a confusion matrix,\u201d","author":"Salmon","year":"2015","journal-title":"2015 IEEE international geoscience and remote sensing symposium (IGARSS)"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.09653","article-title":"Ultralytics yolo evolution: An overview of yolo26, yolo11, yolov8 and yolov5 object detectors for computer vision and pattern recognition","author":"Sapkota","year":"2025","journal-title":"arXiv [Preprint"},{"key":"B56","doi-asserted-by":"publisher","first-page":"84486","DOI":"10.1109\/ACCESS.2022.3197671","article-title":"Explainable ai for healthcare 5.0: opportunities and challenges","volume":"10","author":"Saraswat","year":"2022","journal-title":"IEEE Access"},{"key":"B57","doi-asserted-by":"publisher","first-page":"4890","DOI":"10.1109\/TMI.2025.3583974","article-title":"Improving robustness and reliability in medical image classification with latent-guided diffusion and nested-ensembles","volume":"44","author":"Shen","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B58","doi-asserted-by":"publisher","first-page":"4953","DOI":"10.3390\/electronics13244953","article-title":"Lightweight detection counting method for pill boxes based on improved yolov8n","volume":"13","author":"Sun","year":"2024","journal-title":"Electronics"},{"key":"B59","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1109\/KST.2017.7886081","article-title":"\u201cAutomatic text imprint analysis from pill images,\u201d","author":"Suntronsuk","year":"2017","journal-title":"2017 9th international conference on knowledge and smart technology (KST)"},{"key":"B60","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1186\/s12911-021-01691-8","article-title":"Comparison of retinanet, ssd, and yolo v3 for real-time pill identification","volume":"21","author":"Tan","year":"2021","journal-title":"BMC Med. Inform. Decis. Mak"},{"key":"B61","doi-asserted-by":"publisher","first-page":"220","DOI":"10.22270\/jddt.v14i5.6565","article-title":"A comprehensive review of medication errors in modern healthcare","volume":"14","author":"Unnissa","year":"2024","journal-title":"J. Drug Deliv. Ther"},{"key":"B62","doi-asserted-by":"publisher","first-page":"3971","DOI":"10.1109\/CVPRW50498.2020.00463","article-title":"\u201cepillid dataset: a low-shot fine-grained benchmark for pill identification,\u201d","author":"Usuyama","year":"2020","journal-title":"2020 IEEE\/CVF conference on computer vision and pattern recognition workshops (CVPRW)"},{"key":"B63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/RAIT65068.2025.11088891","article-title":"\u201cAi-powered tablet identification and information extraction system using image recognition and optical character recognition,\u201d","author":"Vignesh","year":"2025","journal-title":"2025 6th international conference on recent advances in information technology (RAIT)"},{"key":"B64","doi-asserted-by":"publisher","first-page":"1629238","DOI":"10.3389\/fphys.2025.1629238","article-title":"A yolov11-based ai system for keypoint detection of auricular acupuncture points in traditional chinese medicine","volume":"16","author":"Wang","year":"2025","journal-title":"Front. Physiol"},{"key":"B65","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JPHOT.2024.3426929","article-title":"Mcir-yolo: white medication pill classification using multi-band infrared images","volume":"16","author":"Wang","year":"2024","journal-title":"IEEE Photonics J"},{"key":"B66","doi-asserted-by":"publisher","first-page":"20552076251411631","DOI":"10.1177\/20552076251411631","article-title":"Artificial intelligence in primary health care: a bibliometric analysis of publications from 2015 to 2024","volume":"12","author":"Wang","year":"","journal-title":"Dig. Health"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2026.3664411","article-title":"Pill-msvae: a multi-scale variational autoencoder based on the internet of things for accurate automatic drug identification and monitoring","author":"Wang","year":"","journal-title":"IEEE Internet Things J"},{"key":"B68","doi-asserted-by":"publisher","first-page":"4350","DOI":"10.3390\/s21134350","article-title":"Confidence score: the forgotten dimension of object detection performance evaluation","volume":"21","author":"Wenkel","year":"2021","journal-title":"Sensors"},{"key":"B69","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1016\/j.aej.2025.05.037","article-title":"A dual-engine fusion optical character recognition method for fast identification and key information extraction of drug labels","volume":"128","author":"Wu","year":"2025","journal-title":"Alex Eng. J"},{"key":"B70","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/CEII65291.2024.00020","article-title":"\u201cRecognizing medicine names from bangladeshi handwritten prescription images using trocr,\u201d","author":"Zaman","year":"2024","journal-title":"2024 7th Asia conference on cognitive engineering and intelligent interaction (CEII)"},{"key":"B71","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/3081333.3081336","article-title":"\u201cMobiledeeppill: a small-footprint mobile deep learning system for recognizing unconstrained pill images,\u201d","author":"Zeng","year":"2017","journal-title":"Proceedings of the 15th annual international conference on mobile systems, applications, and services"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1890296\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T05:34:12Z","timestamp":1784525652000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1890296\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":71,"alternative-id":["10.3389\/frai.2026.1890296"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1890296","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,20]]},"article-number":"1890296"}}