naxtlab

NEWS

NEXTLab Successfully Developed Newspaper Text Digitization Automation Technology

2022.11.14


NEXTLab has succeeded in developing newspaper text digitization automation technology, and patented it. This self-developed technology uses AI to automatically recognize newspaper original text from pdf files and lets the users read them easily on their mobile devices. Recently, it passed KOLAS test certificate, and received patent so that the government would acknowledge it.

Thanks to all the talented developers at NEXTLab, we were more than happy to introduce the solution to PlantyM with new OCR technology. Let’s give a big round of applause to them! 



Last December, NEXTLab successfully concluded a POC project targeting newspapers affiliated with Korea Press Foundation, and in 2022, the project was selected as an AI voucher support project from National IT Industry Promotion Agency. Its technology and business feasibility were verified, and it took approximately 6 months of development period to pass the KOLAS test certificate. NEXTLab also signed an MOU with PlantyM for future technology advancement and business cooperation. 

AI-based newspaper text digitization automation technology analyzes pdf files collected from newspapers, and then basically provides features such as AI-based layout analysis, OCR process, natural language processing, and inspection processing. Through this process, users can enjoy the same level of experience as reading published articles online.

NEXTLab independently developed the latest deep learning-based layout parser, news clustering, and news categorization technology to include in the solution, and linked it with the newspaper viewer app “WINE” developed by PlantyM.


<Picture of newspaper text digitization automation solution concept> 


Since the solution’s completion, NEXTLab is preparing to introduce it to major newspapers, online media, libraries, and even airlines. With the growing demand of users checking news conveniently in their hands, the solution can help provide old articles to read as well as new ones.

 

Gwang-woo Lee, CEO of PlantyM, stated, “We are pleased that many major newspapers can utilize this technology to automate their text digitization process and increase their work efficiency in it, so that the amount of work which required about a hundred people to do previously can be effectively reduced and managed with much fewer people. It has been a great opportunity to cooperate with NEXTLab and use their excellent technology, and we look forward to providing high-quality online newspaper service, while guaranteeing high customer satisfaction.”

Chang-geun Lee, CEO of NEXTLab, announced, “NEXTLab has focused on the consistent theme of AI Vision and OCR technology since its foundation, and as a result developed and introduced many solutions in the telecommunications and broadcast industry, smart work, and traffic compliance field. With our accumulated experience and development capabilities, we could provide highly credible and stable solutions that are in demand, and we were delighted to work together with a brilliant partner such as PlantyM along the way.”