A Review on Optical Character Recognition and Text to Speech Conversion

The application depending on image and voice with a parallel functioning is suitable to assist physically challenged people. So that dependability of a challenged person is decreased to a improved level. Image acquisition based text reader can help visually challenged people to manage the handheld objects in day to day life. Initially steps involves capturing of image, distinguishing image with text portion and residual regions, image pre-processing on region of interest, after the extraction of characters and words, conversion of text to speech is done. To splinter text from a document it is obligatory to discover all the possible manuscript text regions. Text detection, line detection, character identification, feature extraction, training of extracted features are the steps in sequence that are executed.