ICSES Transactions on Image Processing and Pattern Recognition
Vol. 5, No. 3, Sep. 2019
Segmentation-based Cognitive Solution for Handwritten Character Recognition
a Wipro Technologies, Bengaluru, India
Highlights and Novelties
1- Language identification and interpretation of handwritten characters is one of the challenges faced in various industries.
2- There is need for greater accuracy in offline handwriting recognition of such handwritten text. Also, displaying the confidence of recognition helps the user to decide if this can be taken as acceptable threshold or improvise with further noise reduction or manual correction process.
3- In a Handwritten character recognition system, the major challenge is in mimicking a neural network system into an artificial system to enable the system to think and decide based on the analysis it has done which is a simulation of human brain using segment of character sets.
4- Performance of single-algorithm systems drops precipitously as the quality of input decreases. In such situations, a human subject can continue to perform accurate recognition, showing only a gradual decrease in reliability.
Soft computing is the area in the field of computer science where hard and complex tasks are accomplished with low cost or high benefit (in time and investment) with one or more in-exact solution techniques. It is not a single area of research or a process of study whereas it is commonly accepted and included with numerous computational and research area including Neural Networks, Fuzzy system, Evolutionary computing like Genetic Algorithms, Swarm Intelligence, Cognitive Reading and Chaos theory. The trend of researches in Cognitive Reading has become so popular in programming area in the field of Computer science from late 1990s when scientists and researchers show more interests on computational approaches are complex in nature to derive from a known algorithm of solution. This article explains some of the methods in Cognitive reading in image processing for character recognition and briefly discusses the steps involved in the process of Character recognition in image processing.
Cognitive reading Neural network Segmentation Stroke-based recognition Image processing Character recognition
Copyright and Licence
Copyright © by the authors. Licensee International Computer Science and Engineering Society (ICSES). This article is an open-access article distributed under the terms and conditions of the Creative Commons Attribution Non Commercial 4.0 International (CC BY-NC 4.0) license, supported by creativecommons.orgcall_made
Cite this manuscript as
Magesh Kasthuri, "Segmentation-based Cognitive Solution for Handwritten Character Recognition," ICSES Transactions on Image Processing and Pattern Recognition, vol. 5, no. 3, pp. 1-8, Sep. 2019.
For External Scientific Databeses