WebAnnoCV: A Lightweight OpenCV-Based Annotation Tool for Interactive Web Applications

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings (2025), p. 1-5
Yazar: Mathivanan, N
Diğer Yazarlar: Aswath, S, Adithya, S, Ranjith, Kumar N
Baskı/Yayın Bilgisi:
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Konular:
Online Erişim:Citation/Abstract
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

MARC

LEADER 00000nab a2200000uu 4500
001 3247062611
003 UK-CbPIL
024 7 |a 10.1109/ICETEA64585.2025.11099761  |2 doi 
035 |a 3247062611 
045 2 |b d20250101  |b d20251231 
084 |a 228229  |2 nlm 
100 1 |a Mathivanan, N  |u Karpagam Academy of Higher Education,Department of Artificial Intelligence and Data Science,Coimbatore,India 
245 1 |a WebAnnoCV: A Lightweight OpenCV-Based Annotation Tool for Interactive Web Applications 
260 |b The Institute of Electrical and Electronics Engineers, Inc. (IEEE)  |c 2025 
513 |a Conference Proceedings 
520 3 |a Conference Title: 2025 International Conference on Emerging Technologies in Engineering Applications (ICETEA)Conference Start Date: 2025 June 5Conference End Date: 2025 June 6Conference Location: Puducherry, IndiaImage annotation is a crucial process in building computer vision models for various tasks such as object detection, segmentation and classification. Current annotation solutions are rarely cloud-based or require local software installations, which can lead to issues in latencies, privacy, and dedicated hardware. WebAnnoCV is a very thin annotation tool based on OpenCV that runs in the browser. js (ML-based Object Detection JavaScript Library), HTML (Hypertext Markup Language), JavaScript. This enables speedy image labeling in real time in your web browser with no extra installations or server processing required. The platform supports bounding boxes, polygon segmentation, key points and a slew of other annotation modes. AI-assisted capabilities like edge identification, contour recognition, and object tracking make the application reduce the manual workload significantly and lead a rapid image labeling. The web-based application was designed as a tool where all the processes would be available on the client-side, ensuring the protection of data privacy and eliminating the need for external servers, thereby making it suitable for sensitive domains such as healthcare, finance and education. Annotations are created in standard formats like JSON (JavaScript Object Notation), COCO (Common Objects in Context) and Pascal VOC (Visual Object Classes), so that it erupts directly into popular machine learning frameworks as TensorFlow, PyTorch and OpenCV. WebAnnoCV reduces the time for annotation by up to 30%, with similar accuracy to other forms of annotation. With a user-friendly interface, it is easy to use on PC, tablets, and mobile, making up for its comprehensive functions that are easy for both rookies and professionals to handle. WebAnnoCV offers a secure, scalable and efficient approach for performing annotation tasks in realtime across these diverse application domains, such as autonomous driving, medical imaging and environmental monitoring. 
653 |a Applications programs 
653 |a Environmental monitoring 
653 |a Cloud computing 
653 |a Medical imaging 
653 |a Privacy 
653 |a Image annotation 
653 |a Labeling 
653 |a Computer vision 
653 |a Object recognition 
653 |a Machine learning 
653 |a Annotations 
653 |a Real time 
653 |a Hypertext 
653 |a HyperText Markup Language 
653 |a JavaScript 
653 |a Economic 
700 1 |a Aswath, S  |u Karpagam Academy of Higher Education,Department of Artificial Intelligence and Data Science,Coimbatore,India 
700 1 |a Adithya, S  |u Karpagam Academy of Higher Education,Department of Artificial Intelligence and Data Science,Coimbatore,India 
700 1 |a Ranjith, Kumar N  |u Karpagam Academy of Higher Education,Department of Artificial Intelligence and Data Science,Coimbatore,India 
773 0 |t The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Conference Proceedings  |g (2025), p. 1-5 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3247062611/abstract/embedded/ZKJTFFSVAI7CB62C?source=fedsrch