Fighter Aircraft Detection using CNN and Transfer Learning

In this work, Deep learning techniques such as Convolutional Neural networks (CNN) and Transfer Learning are used to detect identify Fighter aircraft or jets. A dataset consisting of 21 different with 20000 images is being processed using the above algorithms. CNN works on principle "pooling," which progressively reduces spatial size model decrease number parameters computations in network. CNN's widely for image detection domains, including defense, agriculture, business, face recognition technology, etc. a machine method where created task reused initial point second task. related issues multi-task concept drift not only an area study deep learning. The uses python libraries pandas, seaborn, sci-kit- learn, etc., find any pre-trained patterns insights. Data separated into train test datasets 80-20 percent total data, respectively. built TensorFlow library CNN. metric "accuracy." transfer also compare accuracy results adopt best-fitting one