• NALLA AJAY KUMAR
• MAMIDI RANJITH REDDY

OFFLINE handwritten text recognition is one of the most active fields of computer science study, and it is intrinsically challenging due to the wide range of writing styles. Character recognition and isolated word recognition reach great recognition rates, but we are still a long way from developing high-performance recognition algorithms for unconstrained offline handwritten manuscripts. Automatic handwriting recognition systems often contain multiple pre-processing processes to decrease variance in handwritten texts as much as feasible while yet preserving information that is crucial for recognition. There is no universal approach for preparing offline handwritten text lines, although it often depends on slope and slant correction as well as letter size normalisation. Using Artificial Neural Networks, this research proposes novel strategies for removing the slope and slant from handwritten text lines and normalising the size of the text pictures (ANNs). The slope and horizontal alignment are properly estimated using local extreme from a text picture recognised as belonging to the lower baseline by a Multilayer Perceptron (MLP). ANNs are also used to eliminate slant in a non-uniform manner. Finally, another MLP calculates the slope and slant adjusted text's reference lines in order to normalise its size.

Automatic handwriting recognition using Artificial Neural Network

"Automatic handwriting recognition using Artificial Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.136-141, February-2019, Available :http://www.jetir.org/papers/JETIRFE06025.pdf

"Automatic handwriting recognition using Artificial Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp136-141, February-2019, Available at : http://www.jetir.org/papers/JETIRFE06025.pdf