Recognizing Handwritten Digits Using Multi-Dimensional Recurrent Neural Networks Intelligent Character Recognition (ICR) with Improved F-Score Measures

The goal of this study is to create a model that can recognize digits using Novel Recurrent Neural Networks (RNN) with LSTM cells and provide an F score comparison for optical character recognition versus Support Vector Machines (SVM) Linear Kernel on the MNIST dataset. sample estimation done GPower statistical software pre-power test 80%. type-I error rate (alpha rate) 0.05 considered. dataset has 70K samples handwritten digits, which 60K are used as training remaining 10,000 testing samples. In research work, classified RNN linear SVM algorithms. attains accuracy 99% significance value 0.171 (p 0.05), whereas 87.75%. results proved performed much better than SVM.