Optical Character Recognition

1
Optical Character Recognition

• Chuan-kai Yang

2
Outline

• OCR Systems
• Historical Perspective
• Commercial Applications

3
OCR Systems

• Image Scanner
• OCR software/hardware
• Output interface

4
Image Scanner

• Detector
• Illumination source
• Scan lens
• Document transport

5
OCR Software/Hardware

• Document Analysis
• Character Recognition
• Contextual Processing

6
Document Analysis

• Character segmentation/isolation
• Compensate poor scanning quality
• Image enhancement
• Underline removal
• Noise removal

7
Character Recognition

• Feature extractor
• Determine the descriptors or feature set
• Derived feature set is fed into the classifier
• Classifier
• Template matching (matrix matching)
• Structural classification
• Bayesian classifier
• Artificial neural networks

8
Template Matching 1/2

• One of the most common methods
• Individual image pixels are used as features
• Classification is performed by comparing an input
  character image with a set of templates(prototypes
  )
• Each comparison results in a similarity measure
  between the input character and the template, the
  comparison is pixel by pixel
• The character identity is assigned the identity
  of the most similar template

9
Template Matching 2/2

• Template matching is a trainable process because
  template characters may be changed
• In many commercial systems, PROMs (programmable
  read-only memory) store templates containing
  single fonts.
• If a suitable PROM exists for a font then
  template matching can be trained to recognize
  that font

10
Structural Classification 1/2

• It utilize structural features and decision rules
  to classify characters
• Features may be defined in terms of character
  strokes, character holes, or other character
  attributes such as concavities
• For instance, the letter P may be described as
  a vertical stroke with a hole attached on the
  upper right side

11
Structural Classification 2/2

• For a character image input, the structural
  features are extracted and a rule-based system is
  applied to classify the character
• Structural methods are also trainable
• The construction of good feature set and a good
  rule-base can be time-consuming

12
Other methods

• Discriminant function classifier use
  hypersurfaces to separate the feature description
  of characters
• Bayesian methods seek to minimize the loss
  function associated with misclassification
  through the use of probability theory
• ANNs, which are closer to human perception,
  employ mathematical minimization techniques
• These techniques are used in commercial OCR
  systems

13
Recognition Rate

• For machine-printed characters, the rate can
  reach over 99
• For hand-written characters, the rateis
  typically lower

14
Contextual Processing

• The number of word choices for a given field can
  be limited by the content of another field
• Knowing the zip code can help knowing address
• Post processing to correct recognition error
• Spelling checker
• Verified interactively by the user

15
Non-Roman Character Recognition
16
Output Interface

• The output interface allows character recognition
  results to be electronically transferred into the
  domain that uses the results
• Spread sheets
• Databases
• Word processors

17
Historical Perspective

• Born in 1951 GISMO by M. Sheppard a robot
  reader-writer
• 1954 J. Rainbow developed a prototyped machine
  that was able to read uppercase typewritten
  output at the fantastic speed of one character
  per minute
• Systems that cost one million dollars were not
  uncommon

18
Some ANSI Standard Fonts
machine
machine
handwritten
19
Todays OCR Systems

• It is not uncommon to find PC-based OCR systems
  for under 800 capable of recognizing several
  hundred characters per minute
• Some system advertise themselves as
  omnifont-able

20
Commercial Applications

• Task-Specific Readers
• Assigning ZIP codes to letter mail
• Reading data entered in forms, e.g. tax forms
• Automatic accounting procedures used in
  processing utilities bills
• Verification of account numbers and courtesy
  amounts on bank checks
• Automatic accounting of airline passenger tickets
• Automatic validation of passports

21
Address Readers
Up to 400 fonts, and up to 45000 mail pieces per
hour.
22
Form Readers

• Trained with a blank form
• Scan regions that should be filled with data
• Some system can process forms at a rate of 5800
  forms per hour

23
Check Readers

• Capture the check image
• Cross reference the amounts specified at both
  places
• An operator can correct misclassified characters
  by cross-validating the recognition results

24
Bill Processing Systems

• Focus on certain regions on a document where the
  expected information are located
• Account number
• Payment value

25
Airline Ticket Readers

• Scan/Match
• Reservation record
• Travel agent record
• Passenger ticket
• Some systems can scan tickets upt to 260000
  tickets per day (17 tickets per second)

26
Passport Readers

• Reads the travelers
• Name
• Date of birth
• Passport number
• Match against the database records containing
  information on fugitive felons and smugglers

27
General Purpose Page Readers

• High-end higher data throughput and more
  advanced capabilities
• Can adapt the recognition engine to customer data
  to improve accuracy
• Can even detect type face (bold face and italic)
• Low-End
• Mostly used in an office with desktop
  workstations
• Could handle a broad range of documents at a
  lower rate and accuracy