Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
In this paper a comparison of three algorithms – Logistic Regression, Shallow Neural Network and Deep Learning are used in this study to create an offline handwritten character recognition system. Recognition of similar shaped character is difficult problem and in character recognition system most errors occur due to similar shaped characters. In this article we propose a generic comparison between three algorithms which works well and the accuracy of this can be increased if the processor of computer is probably high. Our first comparison algorithm that is Logistic Regression which detects many similar characters thus giving us the less efficient success ratio. Next algorithm is Shallow Neural Networks this method is based on observation that there exists a relationship between heights and widths of alphabets written by individual which is unique and specific to him. Our last comparison algorithm is Deep learning Algorithm, we have used Convolutional Neural Network Algorithm to detect the handwritten characters. In today world it has become easier to train deep neural network due to availability of huge amount of data and various Algorithmic Innovations. Now-a-days the amount of computational power needed to train a neural network has increased due to the availability of GPU’s and other cloud-based services like Google Cloud platform and Amazon Web Services which provide resources to train a Neural network on the cloud. We have designed a image segmentation based Handwritten character recognition system. We have developed this comparison algorithm system using python programming language.
Keywords:
Matplotlib Cv2 python-mnist EMNIST DATASET
Cite Article:
"in air character recognition", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.7, Issue 6, page no.2168 - 2172, June-2022, Available :http://www.ijrti.org/papers/IJRTI2206327.pdf
Downloads:
000205259
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator