• Akana Sai Prameela
• Mr.Guddati Tatayyanaidu
• Mrs B S R D Lakshmi
• Mrs.A S R S Meghana

Object detection and recognition are essential components in various practical applications, such as smart surveillance, autonomous technologies, and tools designed to support visually impaired individuals. This project introduces a system that leverages deep learning, specifically the YOLO (You Only Look Once) algorithm, to identify and recognize objects in real time using video captured from a webcam. YOLO is recognized for its high-speed and accurate performance in object detection. Unlike conventional methods that scan an image multiple times, YOLO analyses the entire image in a single evaluation. This approach allows it to predict both object categories and their corresponding bounding boxes simultaneously. As a result, the system can quickly and efficiently detect multiple objects within a scene, making it ideal for fast-moving scenarios where immediate response is essential. The system is built using the Darknet framework—an open-source neural network framework written in C and CUDA. This framework boosts performance and facilitates deployment even on hardware with limited computational power. To improve the accessibility of the system—especially for visually impaired users—real-time voice feedback has been incorporated. This feature converts visual object recognition results into spoken audio outputs, enabling users to receive instantaneous verbal descriptions of their surroundings

Object Detection, YOLO, Darknet, Deep Learning, Real-Time Recognition, Assistive Technology, Computer Vision

"A NOVEL METHODOLOGY FOR OBJECT DETECTION AND RECOGNITION WITH DEEP LEARNING TECHNIQUE USING YOLO AND DARKNET ARCHITECTURE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.h968-h972, May-2025, Available :http://www.jetir.org/papers/JETIR2505900.pdf

"A NOVEL METHODOLOGY FOR OBJECT DETECTION AND RECOGNITION WITH DEEP LEARNING TECHNIQUE USING YOLO AND DARKNET ARCHITECTURE", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. pph968-h972, May-2025, Available at : http://www.jetir.org/papers/JETIR2505900.pdf