Open Access Open Access  Restricted Access Subscription or Fee Access

Research Paper on Handwritten Character Recognition

Jasmanita *

Abstract


Handwriting recognition is the capacity of a machine to get and decipher penmanship contribution from numerous sources, for example, paper records, photos, touchscreen gadgets, and so on. Handwriting and automatic character recognition are an emerging area of research and find many applications in banks, offices and industries. The main objective of this project is to design an expert system capable of efficiently recognizing a format character of a particular type using the artificial neural network approach. Use neural signs in the field of literature. Reduced manpower to manually convert ancient literature to digital form. The proposed system served as a guide and work in the character recognition areas. Enrich the digital library with the English language. Neural computing is a relatively new field and therefore design components are less determined than those of different structures. Neural PCs carry out information parallelism. Neural PCs work in a totally extraordinary manner from ordinary PCs. Neural PCs are prepared (not modified) so that, given a specific beginning state (information passage); classify the input data into one of the classes or evolve the original data so as to optimize some desirable property.

Full Text:

PDF

References


G. Cohen, S. Afshar, J. Tapson, et al. Emnist: an extension of mnist to handwritten letters. Computer Vision and Pattern Recognition. 2017.

L. Eikvil. Citeseerx. Optical character recognition [Online]. Available from https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.4980&rank=2&q=Optical%20character%20recognition&osm=&ossid=

Singh, Sameer, Mark Hewitt. Cursive Digit And Character Recognition on Cedar Database. Proceedings 15th International Conference on Pattern Recognition. ICPR-2000. 3-7 Sept. 2000; Barcelona, Spain, New York: IEEE; 2002.

Anita Pal and Davashankar Singh. Handwritten English Character Recognition Using Neural Network. International Journal of Computer Science & Communication. 2010;1(2):141-144.

Manoj Sonkusare and Narendra Sahu. A SURVEY ON HANDWRITTEN CHARACTER RECOGNITION (HCR) TECHNIQUES FOR ENGLISH ALPHABETS. Advances in Vision Computing: An International Journal (AVC). 2016;3(1):1-12.

M. Kumar, S. R. Jindal, et al. Improved recognition results of medieval handwritten Gurmukhi manuscripts using boosting and bagging methodologies. Neural Process. Lett. Sep. 2019;50:43-56.

R. A. Khan, A. Meyer, et al. Saliency-based framework for facial expression recognition. Frontiers of Computer Science (electronic). 2019;13(4):183-198.

Kevin George Joe, Meghna Savit, et al. Offline character recognition on segmented handwritten kannada characters. Global Conference for Advancement in Technology (GCAT). 18-20 Oct. 2019; Bangalore, India, New York: IEEE; 2020.

A. Choudhury, H. S. Rana, et al. Handwritten Bengali numeral recognition using HOG based feature extraction algorithm. 5th International Conference on Signal Processing and Integrated Networks (SPIN). 22-23 Feb. 2018; Noida, India, New York: IEEE; 2018.

A. S. A. Rabby, S. Haque, et al. BornoNet: Bangla handwritten characters recognition using convolutional neural network. Procedia Computer Science. 2018;143:528-535.




DOI: https://doi.org/10.37628/ijippr.v7i1.716

Refbacks

  • There are currently no refbacks.