The goal of the project is to train artificial intelligence to recognize thousands of handwritten documents, such as applications, certificates, and journals, which still exist in government institutions and hinder the digitalization process.
The goal of the project is to train artificial intelligence to recognize thousands of handwritten documents, such as applications, certificates, and journals, which still exist in government institutions and hinder the digitalization process.
The creation of the dataset was announced by Deputy Minister of Economy, Environment and Agriculture of Ukraine Oleksandr Tsybort on his Facebook page.
According to him, handwritten documents are currently a «blind spot» for existing AI solutions. The RUKOPYS dataset was created specifically for the Handwritten to Data hackathon so that participants could work with real data.
«Thousands of handwritten documents still live within the state: applications, journals, certificates, signatures, seals. They are the ones that slow down digitalization no less than complex procedures or regulations,» said Tsybort.
He emphasized that the best technological solutions developed during the hackathon will be implemented in the ePermit system and other government services at the production level.
The project is being implemented through the efforts of the Ministry of Economy, Environment and Agriculture and the Ministry of Digital Affairs in partnership with AI HOUSE and the Ukrainian Catholic University (UCU).
The ePermit system is an electronic platform that simplifies the process of obtaining permits for businesses and citizens. The implementation of AI solutions for handwriting recognition will significantly speed up document processing and reduce the bureaucratic burden.
Earlier, Dmytro Voytech, Advisor on Artificial Intelligence at the Ministry of Economy, said in the AI&I podcast that the initiative will significantly accelerate the digitalization of public services and open the way to the global digitization of historical archives.
