Real Time Purpose Identification and Trace Using Deep-Learning and Computer Vision
OpenCV is a computer vision and image processing package that can be freely accessed and modified to suit the user’s requirements. It contains a complete set of tools and algorithms necessary for any imaging tasks such as ML applications, filtering, feature detection and image edge detection and so on. OpenCV enables to perform tasks such as denoising, edge finding, image morphing and feature finding which renders it indispensable in object detection and object classification systems [1], [2] This algorithm represent methodical object Identification while not unpleasant on the representation. Using these approach and algorithms situate on deep learning which is as well situated on machine learning involve clique of scientific and deep learning scheme insight by using reliance such as Open CV, we can discover each individual. object in reflection by the extent object in a emphasize oblong package and recognize each individual object and appropriate nit stage of the object. This additionally incorporates the exactness of every strategy for distinguishing objects. Realtime object identification has always been a broad, dynamic, and challenging domain within computervision. Image localization entails identifying a singular object within an image, while object identification involves the task of locating multiple objects within an image. This process involves recall various semantic entities of digital photography and videos. Realtime detection finds extensive application such as object tracking, video surveillance, pedestrian identification, people counting ,autonomous driving vehicles, facial Identification, sports ball tracking, an more.
Authors
- Shweta Chauhan (ORCID: https://orcid.org/0000-0002-6598-1992)
- Ritika Mehra (ORCID: https://orcid.org/0000-0002-2785-5856)
Institutions
- Doon University (IN)
Publication Details
- Published
- 2024-12-13
- DOI
- https://doi.org/10.1109/sustained63638.2024.11074164
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00