Feature matching in transformed images is critical to many fields of computer science, from autonomous robots to video analysis. However, most widely used feature matching algorithms vary in their ability to track features depending on whether rigid or non-rigid image transformations occur. This makes it critical, especially in real-time calculations, to be able to identify what kind of transformation is taking place quickly in order to deploy the best feature matching algorithm for that type of transformation. The proposed research uses a combined autoencoder and neural network classification model to classify rigid or non-rigid transformations in order to improve feature matching on the image pairs. This system is the first to perform this kind of analysis with representation learning and opens new ways to improving feature matching performance. We show that using this method improves the amount of feature matches found between correctly identified image pairs.