• Alok Marathe
• Girish Raskar
• Rohit Rathod
• Prathamesh Sangale
• Swati Shekapure

This research presents a novel approach to enhance user interaction with real-time object detection systems by integrating multilingual label translation. The project utilizes the YOLOv8 (You Only Look Once) model for efficient and accurate object detection in images or video streams. Upon detecting objects, the system labels them and provides users with an option to translate these labels into their preferred language. The core components of the system involve YOLOv8 for object detection, extracting bounding box coordinates and class labels. Subsequently, the detected objects are labeled for user comprehension. The integration of a translation option enables users to select their preferred language, facilitating a personalized experience. To achieve multilingual translation, the system interfaces with a translation API, exemplified by the Google Translate API in our implementation. This API is utilized to dynamically translate detected object labels into the user's language of choice. The translated labels are then presented alongside the original labels, providing a comprehensive understanding of the environment.

Object Detection, YOLOv8, Real-time, Computer Vision, Multilingual Translation

"REAL TIME MULTILINGUAL TRANSLATION OF OBJECT THROUGH CAMERA BASED VISUAL RECOGNITION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.n373-n376, April-2024, Available :http://www.jetir.org/papers/JETIR2404D45.pdf

"REAL TIME MULTILINGUAL TRANSLATION OF OBJECT THROUGH CAMERA BASED VISUAL RECOGNITION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppn373-n376, April-2024, Available at : http://www.jetir.org/papers/JETIR2404D45.pdf