Restoration of Historical Document Images Using Convolutional Neural Networks
Poulami Raha, Bhabatosh Chanda · 2019 IEEE Region 10 Symposium (TENSYMP) · 2019
Historical documents are priceless, irreplaceable and an integral part of national and world history. Handwritten documents can be a letter, notes, journal, memoir etc. or any formally written manuscript implicating a historical event or cultural heritage. These types of documents are often fragile and degraded. They have limited timespan because of materials used, and need to be digitized, restored and preserved in digital format to ensure their longevity. In this research work, we have proposed a novel methodology using a single convolutional neural network to denoise and restore old handwritten documents. The proposed model demonstrates excellent performance in restoration and preservation of severely degraded old handwritten document images of around 70 years old.