• Tarang Gujar
• Prof. Abdul Gaffar H

Nowadays everything is becoming computerized .All the time consuming processes like issuing of passport, license, banking process is now done online. All these processes involve huge amount of documentation. This sometimes can create problems like the scanned copies of handwritten documents can be difficult to understand by a computer. The way of writing anything changes from person to person and because of this, the humans also face difficulty in the recognition of different writing styles and variations, may be the patterns shifted, scaled, distorted, with some skewed and even overwritten and therefore it is hard for computers to recognize the writing of a person.So to solve this problem handwriting recognition systems are being developed. Also there is no system designed for blind people which will enable them to interpret handwritten text with precision apart from braille. And it is not feasible to provide braille in all places. Thus such a system or model was important for such people which will read handwritten text and convert into voice. Here introducing four phase: preprocessing, segmentation, feature extraction, classification. CNN Technique will be used for classification and recognition of handwritten text through training and testing.

CNN, handwriting, classification, segmentation, feature, preprocessing

"Handwritten text recognition and conversion into speech Using Deep Learning and Machine Learning techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.289-294, June 2019, Available :http://www.jetir.org/papers/JETIR1907E43.pdf

"Handwritten text recognition and conversion into speech Using Deep Learning and Machine Learning techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp289-294, June 2019, Available at : http://www.jetir.org/papers/JETIR1907E43.pdf