Optical Character Recognition (OCR) is a technology that converts images of typed, handwritten, or printed text into machine-encoded text. This can be done with images from scanned documents, photos of documents, or text embedded in images such as signs or subtitles. OCR enables the digitization of printed text so it can be edited, searched, stored more compactly, displayed online, and used in automated processes like machine translation or text-to-speech. It works by analyzing the digital image to locate and recognize characters (letters, numbers, symbols), then converts these characters into editable and searchable text. Early OCR systems needed training on each font, but modern systems support many fonts and can even recreate complex document layouts including images and columns. OCR is widely used for data entry from paper records such as passports, invoices, bank statements, and more, significantly reducing manual typing efforts. It is also a field of research intersecting pattern recognition, artificial intelligence, and computer vision. In summary, OCR is the process and technology that transforms images of text into computer-readable text, enabling easier digital access and processing of printed or handwritten documents. This technology is essential for digitizing physical documents and automating data extraction tasks.