I need an idea for Optical Character Recognition for graduation project. I was thinking about enhancing algorithm used in OCR. In your idea, what algorithm can I enhance and focus with for better result of OCR softwares.

Frankly I would go get TESSERACT and learn how to use that. I recall it's open source if you wish to dive into this but for me I rarely encounter folk that will spend the years needed to work OCR at the source level or beat TESSERACT OCR.

Just in case your search foo is weak, it's over at https://github.com/tesseract-ocr

Open source, many languages and I've used it.

Be a part of the DaniWeb community

We're a friendly, industry-focused community of developers, IT pros, digital marketers, and technology enthusiasts meeting, networking, learning, and sharing knowledge.