Abstract

In this paper, we present a neural network models like artificial neural network (ANN), back propagation neural network (BPNN), feed forward neural network (FFNN) and Long Short Term Memory (LSTM) named Recurrent Neural Network (RNN) to classify the input images using a series of frameworks. The architecture involves data collection, pre-processing, feature extraction and classification of images. A 10-fold cross validation is conducted on the collected input image samples and the results are evaluated against these four models over different performance metrics. The results show that the RNN attains improved classification accuracy and reduced error rate than other methods.