Professional Documents
Culture Documents
TECHNOLOGY
A.MADHAVI15P81A0573)
K.SAIKUMAR (15P81A0576)
K.MANISHA(15P81A0579)
INTRODUCTION
In the running world there is a growing demand for the users to convert the
printed documents in to electronic documents for maintaining the security of
their data. In this system the user can only read the text present in the file
but he cannot edit directly. If the user want to make any changes to the files
then he has to digitalize the text by typing manually.
DISADVANTAGES
• Processor - Pentium
• Speed - 200 GHZ
• RAM - 256MB(min)
• Hard Disk - 4 GB(min)
SOFTWARE REQUIREMENTS
• Image Acquisition
• Pre-processing
• Segmentation
• Feature Extraction
• Classification and Recognition
Image Acquisition
The raw data depending on the data acquisition type is subjected to a number
of preliminary processing steps to make it usable in the descriptive stages of
character analysis. The image resulting from scanning process may contain
certain amount of noise. Depending on the scanner resolution and the inherent
thresholding, the characters may be smeared or broken. Some of these defects
which may cause poor recognition rates and are eliminated through pre-
processor by smoothing digitized characters
Segmentation
The pre-processing stage yields a clean character image in the sense that a
sufficient amount of shape information, high compression, and low noise on a
normalized image is obtained. The next OCR component is segmentation.
Here the character image is segmented into its subcomponents
Feature Extraction
The classification stage is the decision making part of a recognition system and
it uses the features extracted in the previous stage. A feed forward back
propagation neural network having two hidden layers with architecture of is
used to perform the classification. The hidden layers use log sigmoid
activation function, and the output layer is a competitive layer, as one of the
characters is to be identified.
UML DIAGRAMS
1. Uploading Image When the user want to Image file is selected and Pass
open a file uploaded
2. To pre-process image Image will be taken for Conversion from RGB to Pass
pre-processing B/W image
• This research shows and explains the use of the K-Nearest Neighbor
algorithm in an Optical Character Recognition program. Through this
experiment, it can be seen that the K-Nearest Neighbor algorithm can be
used to classify images into alphabets in an OCR. It executes the job fairly
well too, achieving a precision of 76.9%.
Future Enhancement
• https://dl.acm.org/citation.cfm?id=553104
• https://www.slideshare.net/karanpanjwani752/optical-character-
recognition-ocr
• https://www.slideshare.net/nikbharat/project-report-of-ocr-
recognition?from_action=save
• Meilir Page-Jones: Fundamentals of Object Oriented Design in UML,
Pearson Education
THANK YOU
ANY QUERIES?