Deep learning-based images classification using an efficient CNN model trained on handwritten dataset

Image processing and deep learning (DL) are two zones of excessive awareness to researchers and scientists worldwide. It is having multiple applications fields such as robotics, medicine, and security and surveillance. DL is about learning multiple representations and abstraction levels that help make sense of data such as images, sound, and text. The MNIST dataset has a massive number of handwritten text dataset, and it is frequently used for training, testing, and validation of the convolutional neural network (CNN) deep model. This article has created an efficient model with multiple convolutions, ReLU and pooling layers, which is tested on MNIST dataset with 98.47 % accuracy. Further, this model is tested on a similar kind of random image Dataset which gives significant results in terms of accurac