A Tool for Extracting Text from Scanned Documents and Convert it into Editable Format

摘要: With the advent of Social media, now-a-days most data are stored in images. These if processed correctly can provide large information. Hence there is a need to convert these into A novel technique which available image an editable format proposed where be acquired either by camera, smart phone or directly from any source. The segmented characters using Connected Components (CC) and edge recombination stroke width. This then converted Optical Character Recognition (OCR) technology Maximally Stable Extremal Region (MSER) for segmentation. system also extract object images, done Artificial Neural Networks (ANN). complete solution developed MATLAB output variable. extracted word document required it edited. performance measured two parameters namely precision rate recall has about 88% 97% higher than earlier methods.