Front End Data Cleaning And Transformation In Standard Printed Form Using Neural Models [article]

Raju Dara, Dr.Ch. Satyanarayana, Dr.A.Govardhan
2014 arXiv   pre-print
Front end of data collection and loading into database manually may cause potential errors in data sets and a very time consuming process. Scanning of a data document in the form of an image and recognition of corresponding information in that image can be considered as a possible solution of this challenge. This paper presents an automated solution for the problem of data cleansing and recognition of user written data to transform into standard printed format with the help of artificial neural
more » ... networks. Three different neural models namely direct, correlation based and hierarchical have been developed to handle this issue. In a very hostile input environment, the solution is developed to justify the proposed logic.
arXiv:1401.2911v1 fatcat:o4k7toghvrcvtmk3edci7i2h7e