Writer identification can be used to find fakes and help with forensic science. Handwritten text is the only way to identify the author offline. Recently, convolutional neural networks (CNNs) have become the best way to classify images on a large scale. The recurrent neural network (RNN) models the spatial relationship between the fragment sequences in order to improve the local fragment feature's capacity for discrimination. To get the best of both models, combine CNN and RNN to create a Convolution Recurrent Neural Network (CRNN). Therefore, the CRNN model for offline writer identification is suggested in this paper. The proposed method achieved 96% accuracy in classifying 690 writers using CRNN. The suggested method can make efficient and strong writer identification based on different sizes, different orientations, or both. The efficiency of the proposed system has been demonstrated. Finally, an accuracy comparison of CRNN with CNN and RNN has been conducted

Writer identification, Offline analysis, Convolution Neural Networks, Deep learning, Recurrent Neural Network, Convolutional Recurrent Neural Network, Long short-term memory