Validation of Random Dataset Using an Efficient CNN Model Trained on MNIST Handwritten Dataset

Abstract

Image processing and Deep learning are two zones of excessive awareness to researchers and scientists around the world. It is having multiple applications fields such as robotics, medicine, and security and surveillance. Deep Learning is about learning multiple levels of representation and abstraction that help to make sense of data such as images, sound, and text. MNIST data set is having a huge number of handwritten text data set and it is frequently used for training, testing, and validation of CNN deep model. In this article, we have created an efficient model with multiple convolutions, relu and pooling layers. Which is tested on MNIST data set with 98.45% accuracy? Further, this model is tested on similar kind of random image data set which gives significant results in terms of accuracy.