Bone fractures are a common and frequently serious medical problem for which the precise diagnosis is essential to providing the best possible care. The suggested method makes use of deep learning (DL) to automate the fracture identification process from medical imaging data, including X-rays. A popular family of deep learning models for image analysis applications is called convolutional neural networks, or CNNs. Their effectiveness is in their ability to extract features and categorize them. Numerous architectures are employed for analysis, including pretrained models like GoogLeNet and MobileNet, as well as a manual fracture detection model called ManualNet are implemented. Preparing the data, designing the model architecture, training, and evaluating the process are the main processes in fracture detection. For both healthy and shattered bones, the best model's accuracy is 95%. Additionally, this system is able to be incorporated into hospital workflows to deliver quick and automated early fracture examinations, lessening the workload of radiologists and facilitating quicker patient care. Its real-time implementation could lead to better patient outcomes and lower medical expenses. This system advances the field of medical image analysis and demonstrates how deep learning may be used practically to diagnose bone fractures.