Optical character recognition (OCR) is a technology that converts images of typed, handwritten or printed text into machine-encoded text. The document describes the OCR process which includes image pre-processing, segmentation, feature extraction and recognition using a multi-layer perceptron neural network. It discusses advantages such as increased efficiency and ability to instantly search text. Disadvantages include issues with low quality documents. Applications include data entry for business documents and making printed documents searchable.

1. Raisoni College of Engineering
An Autonomous Institution under UGC Act 1965 |Accredited by NBA & NAAC ‘A’ Grade
DEPARTMENT OF ELECTRONICS AND TELECOMMUNICATION
ENGINEERING
Session:
2016-2017
Semester/Branch/Section: –VII / ETC – C
Name of Subject:
Optical Communication
TAE- 2
Report On
Optical Character Recognition
Submitted by:
Akash Shahu (Roll No. 26)
Ashish Pandey (Roll No. 30)
Submitted To:
Prof. K. Jajulwar
E&TC Department, G.H.R.C.E.

2. Introduction:
Optical character recognition (optical character reader, OCR) is
the mechanical or electronic conversion of images of typed, handwritten or
printed text into machine-encoded text, whether from a scanned document, a
photo of a document, a scene-photo (for example the text on signs and
billboards in a landscape photo) or from subtitle text superimposed on an image
(for example from a television broadcast). It is widely used as a form of data
entry from printed paper data records, whether passport documents, invoices,
bank statements, computerised receipts, business cards, mail, printouts of static-
data, or any suitable documentation. It is a common method of digitising printed
texts so that they can be electronically edited, searched, stored more compactly,
displayed on-line, and used in machine processes such as cognitive
computing, machine translation, (extracted) text-to-speech, key data and text
mining. OCR is a field of research in pattern recognition, artificial
intelligence and computer vision.
Early versions needed to be trained with images of each character, and worked
on one font at a time. Advanced systems capable of producing a high degree of
recognition accuracy for most fonts are now common, and with support for a
variety of digital image file format inputs.[2] Some systems are capable of
reproducing formatted output that closely approximates the original page
including images, columns, and other non-textual components.
Description:
Optical Character Recognition software does is optically recognize and
represent each character in a scanned document, or, in other words, it translates
an image of each character in a scanned document into an electronically
designated character.
Character recognition process is very complex and requires that the OCR
program matches each image letter to an electronic version that corresponds to
it. The program has to recognize the font that is used in order to be able to
recreate the document. In many cases the scanned copies of a document are of
low quality, blurred, with unrecognizable characters, especially if the original
paper copy was of poor quality, crumpled, faded, etc. In these cases it is really
difficult for the OCR software to perform accurately and that’s when errors
occur.
Until now they haven’t invented a completely error-free OCR software.
However, advancements are continually made in this direction. Today we have

3. many professional OCR tools on the market that can convert scanned
documents surprisingly well. One of them is the professional version
of Able2Extract that includes advanced OCR capabilities and gives its users an
opportunity to quickly overcome issues that come with image PDFs.
OCR is optical character recognition, a software tool that allows you to convert
scanned documents into text searchable files. It is now increasingly common for
documents to be scanned so that they can be conveniently viewed and shared
via electronic means. However a scan is merely an image capture of the original
document, so it cannot be edited or searched through in any way. This results in
a decrease in efficiency since employees now have to manually correct or
search through multiple pages. OCR solves this problem by making the
document text searchable.
Types of OCR:
 Optical character recognition (OCR) – targets typewritten text,
one glyph or character at a time.
 Optical word recognition – targets typewritten text, one word at a time (for
languages that use a spaceas a word divider). (Usually just called "OCR".)
 Intelligent character recognition (ICR) – also targets
handwritten printscript or cursive text one glyph or character at a time,
usually involving machine learning.
 Intelligent word recognition (IWR) – also targets
handwritten printscript or cursive text, one word at a time. This is especially
useful for languages where glyphs are not separated in cursive script.
OCR is generally an "offline" process, which analyses a static
document. Handwriting movement analysis can be used as input to handwriting
recognition. Instead of merely using the shapes of glyphs and words, this
technique is able to capture motions, such as the order in which segments are
drawn, the direction, and the pattern of putting the pen down and lifting it. This
additional information can make the end-to-end process more accurate. This
technology is also known as "on-line character recognition", "dynamic character
recognition", "real-time character recognition", and "intelligent character
recognition".

4. PowerPoint Presentation on
Optical Character Recognition
What is Optical Character
Recognition?
 OCR allow to convert mechanical or electronic image base text into the
machine encodes able text through an optical mechanism.
 The ultimate objective of OCR is to simulate the human reading
capabilities so the computer can read, understand, edit and do similar
activities it does with the text.
 Representing the architecture of Optical Character Recognition(OCR) that
is designed using artificial computational model same as biological neuron
network.
OCR Model
Optical Character Recognizer Model.

5. Image Preprocessing
 Image processing is a signal processing that convert either an image or a
set of characteristics or parameters related to the image.
 It is achieve correction of distortion, noise reduction, normalization,
filtering the image and so on.
 RGB to Gray scale Conversion: The RGB color space contains red, green,
blue that are added together in a variety of ways to reproduce a array of
color.
 Gray scale to Binary Image Conversion: A binary image has only two
possible color value for each pixel is that black and white. This color depth
is 1-bit monochrome.
Image Segmentation
 By the Image segmentation simplify and/or change the representation of
an image into something that is more meaningful and easier to analyze.
 Image segmentation is used for object recognition of an image; detect the
boundary estimation, image editing or image database look-up.
 Determining Character Line: Enumeration of character lines in a character
image is essential in delimiting the bounds within which the detection can
precede.
 Detecting Individual Character: Detection of individual symbols involves
scanning character lines for orthogonally separable images composed of
black pixels.
Boundary detection of character line.
Boundary detection of a character.

6. Feature Extraction
 Feature extraction extract set of feature to produce the relevant
information from the original input set data that can be represent in a
lower dimensionality space.
 To implement the feature extraction process we have used Image to
matrix mapping process.
 By the matrix mapping process the character image is converted
corresponding two dimensional binary matrixes.
 Image to Matrix Mapping: By the matrix mapping process the character
image is converted corresponding two dimensional binary matrixes.
Image to
Matrix
Mapping
Binary
Represe
ntation
17-Aug-16 7
Multi-Layer Perception
Neural Network
Multi-Layer Perception Neural network has
an input layer, hidden layer and output layer.
Input layer feed the input data set that is
came from feature extraction and output
layer produced the set of output vector.
•Appling the learning process
algorithm within the multilayer
network architecture, the
synaptic weights and threshold
are update in a way that the
classification/recognition task can
be performing efficiently.
•Presenting 600-602-6 three Layer
Neural network architecture to
perform the Optical Character
Recognition Learning process.
Training

7. Recognition
• Feature data is feed to the network input layer and produced
an output vector and calculating the error function.
8
An approach to empirical OCR paradigm using Multi-Layer Preceptor Neural Network
Advantages
1. It increases the efficiency and effectiveness of office work.
2. The ability to instantly search through content is immensely
useful, especially in an office setting that has to deal with
high volume scanning or high document inflow.
3. You can now use the copy and paste tools on the document
as well, instead of rewriting everything to correct it.
4. OCR is quick and accurate, ensuring the document's content
remains intact while saving time as well.
5. When combined with other technologies such as scanning
and file compression, the advantages of OCR truly shine.
6. Workflow is increased since employees no longer have to
waste time on manual labour and can work quicker and
more efficiently.

8. Disadvantages
1. Optical scanners can also have trouble with documents
that lack significant contrast between characters and the
background.
2. Dirty pages, or those printed on coloured stock, may
confuse a scanner and result in large blocks of unread text.
3. The extra steps necessary to render poor-quality originals
suitable for OCR scanning may end up completely
offsetting the potential time savings the technology offers.
4. Handwritten documents require even, clear spacing
between letters to ensure proper scanning.
5. Each separate box can then be scanned individually,
preventing the computer from misreading letters that have
run together.
Application
1. Data entry for business documents, e.g. check,
passport, invoice, bank statement and receipt
2. Automatic number plate recognition
3. More quickly make textual versions of printed
documents, e.g. book scanning for Project
Gutenberg.
4. Make electronic images of printed documents
searchable, e.g. Google Books
5. Assistive technology for blind and visually impaired
users