InkCapture is software that fundamentally changes the possibilities of digitizing historical handwritten documents. While printed documents (books, newspapers) are usually digitized, including textual information, and allow direct search of text in documents, for handwritten texts (chronicles, diaries, notes) there is no such possibility. There are no reliable tools for automatic handwriting recognition, so researchers rely on hours to view hundreds of pages of documents without supporting text search.
InkCapture aims to change this. By using modern methods of machine learning and computer vision, it will enable the automatic retrieval of texts from handwritten documents and will fundamentally increase the possibility of searching in historical documents.
Text recognition using neural networks
InkCapture uses machine learning methods and neural networks, which allow the system to recognize fonts written in different styles. The system has the ability to learn and its success is greatly influenced by the amount of data on which it can train letter and word recognition in advance. Therefore, he needs as many historical manuscript documents as possible in the learning phase. You can help with that too.
Digitization of manuscripts using artificial intelligence
Municipal chronicles, archival documents and documents, private historical documents, hand-kept records