Published Paper Details:

Abstract: This project explores the use of the YOLOv11 deep learning model for advanced object detection to identify and classify custom visual elements within images. The main goal is to develop a model capable of accurately detecting specific objects under diverse and challenging image conditions. To this end, a custom dataset was created and carefully annotated to represent the objects of interest. The training was performed on Google Colab, taking advantage of GPU acceleration to speed up computation. Data Preprocessing techniques such as image augmentation and normalization were applied to improve the model's robustness and ability to generalize across different scenarios. YOLOv11 was selected for its well-known balance between real-time processing capabilities and high detection accuracy, making it suitable for deployment on a range of devices from PCs to edge platforms. The trained model showed strong performance in detecting objects in varied environments and image qualities, demonstrating its practical applicability. This project highlights the effectiveness of modern object detection architectures in customized image analysis tasks and sets a foundation for future work, including real-time deployment and integration with embedded or mobile systems. The results indicate significant potential for automating visual recognition in security, automation, and intelligent system applications.