Acquisition of Textual Data
Acquisition of Textual Data
Pages of a Book
Different Styles
Enhance readability
TEXT
• Printed or typed Handwritten
• Pure Text Pure text with labels PTWL and Picture's Printed text
with labels, pictures and handwritten corrections
• Input data by manual by a keyboard
• Using scanners
• An opto-electronic device used to optically scan
a page of text and convert into 0s and 1s and
stored in the computer
Types
• Flat bed
• Sheet fed
• V shaped book
• Hand held
Flat bed Scanner
• Light beam – lens - mirror
• Array of solid states - electronic eyes - CCD ( Charge coupled
Devices)
• Converts the electrical o/p into set of bits which stores in the memory
of computer
• 300 x 900 pixels
• Save as bit map
Optical Character Recognizer
• Conversion of bitmap form into ascii form