ABSTRACT-The major flow of this project is like it creates a robust AI which Scans the Hard Documents and analyse the pattern and then User can select what text to be extracted by selecting and mapping with the columns of the Excel File. For the first time of scan of particular model and performing actions by user counts in the training of the machine . For the next time if this type of pattern comes machine will automatically performs those actions.
This Project Deals with the digitalization of the hardcopies data which works on the FAST(Feature Acceleration) text extraction Method and Gaussian Algorithm , The former deals with the Corner detection of texts which works on the density of text and extract them and latter works in the smoothness of the Document to relax the extraction with no noise.
Keywords — Digitalization , Text Extraction , Machine Learning, FAST Algorithm , GAUSSIAN FILTER
|
DOI:
10.17148/IJARCCE.2022.11345
