• Mahesh Chaudhari
• Vinayak Yeul
• Nikhil Kale

Even though computers and smartphones are more common than ever, many individuals still enjoy the classic writing experience of ink on paper. However, the conventional method of writing text has some drawbacks. The capacity to translate legible handwritten input into digital form from sources like paper documents is known as handwriting recognition. A handwriting recognition system manages formatting, completes accurate character segmentation, and identifies the most likely words. Thus, converting handwritten characters to digital representation is becoming more and more common. It has become crucial to save any handwritten documents in digital format. In this paper, we are creating a HCR model, which will be used to overcome the disadvantages of conventional method. After receiving the handwritten document as input in the form of an image, the programme segments and recognises each character in the image. Additionally, it recognises the letters before going on to find the words in the image. This is accomplished using CNN algorithm with better accuracy as well as machine learning methods. The specified input image will be provided in word document format as the intended output. Large data sets of images, such as those from IAM and MNIST, that display the various writing styles and forms can be used to train the system. This can also be applied to businesses and organisations who only keep critical records in writing form.

Convolutional Neural Network, Handwritten Character Recognition, Pre-processing, Segmentation, Image gathering

"Conversion of Handwritten Text into Digital Form using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.527-530, May-2023, Available :http://www.jetir.org/papers/JETIRFX06091.pdf

"Conversion of Handwritten Text into Digital Form using CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. pp527-530, May-2023, Available at : http://www.jetir.org/papers/JETIRFX06091.pdf