Access to Image-to-Text (OCR) Technology

New Feature Introduction

Through the efforts of Noor Center, access to Image-to-Text (OCR) technology has been provided with the aim of expanding research services.

Official Announcement

The manager of the Intelligent Processing Department of Noor Center announced this news in an interview with Noorsoft, stating:

"This intelligent processing capability has been developed at Noor Center with the goal of expanding research services for seminary students and university students. Several million OCR-processed pages have now become searchable."

Importance of OCR Technology

Engineer Hossein Jowzi added:

"Image-to-text conversion is one of the fundamental methods for making visual resources searchable, as using OCR-processed text in the search engine enables users to perform highlighted search within images."

Revolution in Resource Search

Previously, search was only possible in typed resources, which required significant annual time and cost investment in digitizing various print materials (books, journals, theses, etc.). Now, however, full-text search is available for researchers in journals that have been scanned at Noor and converted to text using optical character recognition.

Statistics and Future Plans

He continued:

"Image-to-text technology is currently being applied as a priority to journal articles in the Noormags database, with a volume of over nine million pages, and will subsequently be extended to resources in the Noorlib database."

Benefits

• Making visual resources searchable
• Saving time and cost in digitization
• Access to full text of scanned journals
• Enabling highlighted (colored) search within images