Offline Identification of the Author using Heterogeneous Data based on Deep Learning

Handwriting recognition has always been a challenge; therefore, it has attracted the attention of many researchers. The present study presents an offline system for the automatic detection of human handwriting under different experimental conditions. This system includes input data, image processing unit, and output unit. In this study, a right-to-left dataset is designed based on the standards of the American Society for Experiments and Materials (ASTM). An improved deep convolution neural network (DCNN) model based on a pre-trained network is designed to extract features hierarchically from raw handwritten data. A significant advantage in this study is the use of heterogeneous data. Another significant aspect of the present study is that the proposed DCNN model is independent of any particular language and can be used for different languages. The results show that the proposed DCNN model has a very good performance for identifying the author based on heterogeneous data.