Recent Trends in OCR Systems: A Review
Aditi Moudgil, Saravjeet Singh, Vinay Gautam · 2022
Optical character recognition (OCR) is one of the most emergent applications of pattern recognition. It is a fully grown, advancing, energizing, and helpful field and is going about as an establishment stone for emerging advanced applications. Applications for OCR are the medical field, speech recognition, biometric recognition, etc. OCR is a technique that is used to convert scanned images, such as handwritten text or PDF files, into an editable format. In a nation like India, a plenitude of data and invaluable information is available as original copies, old writings, books, manuscripts, family data, etc. that are customarily accessible either in printed or handwritten formats. Such literature becomes inefficient when information must be searched among thousands of pages. Today&s;s era is an advanced era that accepts documents and available information in a digitized form, and it should be the very first step, and accessible, by machines. Thus, the process of digitizing such literature came to the rescue. The conversion of digitized information into a textual form becomes a challenging but mandatory task to make the information readable by any machine processing a million pages per second. When it comes to analyzing manuscripts that might not even be in readable form, and the text in those manuscripts has deteriorated, it becomes even more challenging to get that precious text and to make it available.