Scribd
Upload
77 views12 pages

Optical Character Recognition: Shilpa Kale (46052) Kanchan Navgire (46122)

This document describes an optical character recognition system implemented using principal component analysis. The system was trained on a Hebrew alphabet database of 270 images with 10 variations of each letter. When tested, the system achieved a recognition rate of approximately 50% due to issues with letter location sensitivity and similarity between some letters. The accuracy could potentially be improved by implementing word-level recognition instead of single letters, centering each letter before recognition, and optimizing the selection of dimensions for the principal component analysis subspace.

Uploaded by

Kanchan navgire
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
77 views12 pages

Optical Character Recognition: Shilpa Kale (46052) Kanchan Navgire (46122)

This document describes an optical character recognition system implemented using principal component analysis. The system was trained on a Hebrew alphabet database of 270 images with 10 variations of each letter. When tested, the system achieved a recognition rate of approximately 50% due to issues with letter location sensitivity and similarity between some letters. The accuracy could potentially be improved by implementing word-level recognition instead of single letters, centering each letter before recognition, and optimizing the selection of dimensions for the principal component analysis subspace.

Uploaded by

Kanchan navgire
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 12

Shilpa kale (46052)

Kanchan navgire(46122)

Optical character recognition


Abstract
Optical character recognition usually abbreviated to OCR,
involves a computer system designed to translate images of typewritten text
(usually captured by a scanner) into machine editable text or to translate
pictures of characters into a standard encoding scheme representing them.
OCR began as a field of research in artificial intelligence and computational
vision.

In this project I decided to implement OCR using the


appearance based recognition technique. Formally, the problem can be stated
as follows: given a training dataset x, and an object o, find object xj, within
the dataset, most similar to o. PCA (defined below) is a popular technique in
apperance based recognition.
2. Pricipal Components Analysis
In statistics, principal components analysis (PCA) is a technique that can
be used to simplify a dataset., more formally it is a linear transformation that
chooses a new coordinate system for the data set such that the greatest
variance by any projection of the data set comes to lie on the first axis (then
called the first principal component), the second greatest variance on the
second axis, and so on. PCA can be used for reducing dimnesionalty in a
dataset while retaining those characteristics of the dataset that contribute
most to its varaince by eliminating the later principal components (by a more
or less heuristic decision). These characteristics may be the "most
important", but this is not necessarily the case, depending on the application.

PCA has the speciality of being the optimal linear transformation subspace
that has largest variance. However this comes at the price of greater
computational requirement. Unlike other linear transforms, the PCA does not
have a fixed set of basis vectors, Its basis vectors depend on the data set.

Assuming zero empirical mean (the empirical mean of the distribution has
been subtracted from the data set), the principal component wi of a dataset x
can be calculate by finding the eigenvalues and eigenvectors of the
covariance matrix of x, we find that the eigenvectors with the largest
eigenvalues correspond to the dimensions that have the strongest correaltion
in the dataset. The original measurements are finally projected onto the
reduced vector space.
3. Appearance Based Recognition Using PCA.
1. Obtian a trianing set of images of all objects of interset (in our case:
the ABC or the aleph-beth) under variable conditions (in our case:
different fonts, bold, italic, etc.).

2. Create a eigenspace from the training set using PCA.

3. Recognize the given image:

o Project both the image and the training set to the PCA subspace
(eigenspace).

o Compute the distances to the training set images in the eigenspace


(in our case: using L2 norm)

o Find object oj with minimal distance from the given image

o Return oj name.
4. The Algorithm
4.1 Creating PCA subspace (eigenspace).
o Organize the image database into colunm vectors. The vector size
eqauls the image height multiplied by the image width. All the
database images must be of the same size, 64 x 48 in our case
(equivalent to a 36 size font). The result is a vector_size x
database_size matrix, ColumnVectors.

o Find the empirical mean vector. Find the empirical mean along
each dimension. The result is a vector_size x 1 vector,
EmpiricalMean.

o Subtract the empirical mean vector EmpiricalMean from each column


of the data matrix ColumnVectors. Store the mean-subtracted data in a
vector_size x database_size matrix, MeanSubracted.

o Compute the eigenvectors and eigenvalues of the covariance


matrix of MeanSubracted. In this phase I deviated form the original
PCA algorithm. Finding the eigenvectors and eigenvalues of the
covariance matrix of MeanSubracted, which is a vector_size x vector
_size matrix, was more then Matlab could handle. When I tried to do
so, I got an “out of virtual memory” error. Therefore I used a method
(that I found on the web), of obtaining the covariance matrix of the
transposed matrix of MeanSubracted is a database_size x
database_size matrix, which is a smaller matrix but gives similar
eigenvalues and eigenvectors as the original matrix. In order to
convert these eigenvectors to the eigenvectors required I multiplied
the eigenvectors by the MeanSubracted matrix.

o Sort the eigenvectors by decreasing eigenvalue.

o Create a k dimensional subspace. Save the first k eigenvectors as a


matrix, SubSpace. Eigenvector with normalized eigenvalue close to
zero will not be saved even though it is in the k largest eigenvalues.
The end result is a k (or less) dimensional subspace.

4.2 Recognizing a given image


o Transform the image into a colunm vector. Resize the image to
the database images size and set it as a colunm vector,
ImageColumVec.

o Find the distance from the image colunm vector to each of the
database colunm vectors in the subspace. Project both the image
vector and the training set (database) vector to the PCA subspace,
multiply SubSpaceT by ImageColumVec and by ColumnVectors
and compute the distance using the L2 norm method.

o Return the name (label) of the colunm vector with the minimal
distance.
5. The Program
The program consists of 9 files and 2 main functions, written in Matlab.

Main functions:

1. CreateDB(): loads the database, trains it and saves the data for the
OCR use.

2. OCR (image_file_name): loads the image and recognizes it.

Files:

1. database.zip – an archive of the database images. Unzip it before


database creation and training.

2. imread2.m – this function loads an image and creates its negative.

3. getImages.m – a script used for loading the database images. This file
is the one needed to be changed in order to update/add images to the
database.

4. pca.m – this function trains the dataset with the images loaded by the
script, using the PCA algorithm described above.

5. CreateDB.m – holds the CreateBD() function.

6. PCAdateBase.mat – if created, holds the PCA saved data.

7. im_resize.m – resizes the image to the desired size


8. getCharId.m - this function preforms the recognizing algorithm
described above.

9. OCR.m - holds the OCR (image_file_name) function.


6. Results

I ran the program using a full hebrew Aleph Beth database, 270 images (10
different images per letter).

After running a few tests, the recognition success rate was about 50% due to
two main reasons: location sensitivity and similar letters with small
differences between them.

Location sensitivity: character recognition via apperance based recognition


is location sensitive because charatcers come in different sizes (using the
same font size) and can not always by at center of the image. In addition, in
different fonts, the same letter can by placed in different locations within the
“letter box”. When a given letter is located in a different location then the
correct dataset images the recognition algorithm will return a long distance
under the L2 norm method and a shorter distance can be found to an
incorrect letter.

For example: the following image was recognized correctly as

but the same image (letter) moved aside within the “letter box” was

incorrectly recognized as .
Similar letters: among the hebrew Aleph Beth one can find very similar
letters with very small differences between them. For example VAV “‫ ”ו‬and
NUN SOFIT “‫”ן‬, can be called a “similar couple”. This kind of similarity
can cause mistakes when writing with a specific font in which the letter
resembles its “similar couple partner”.

For example: this Kaph Sofit was incorrectly recognized as Resh

.
7. Discussion

The goal of my project was to create a reliable OCR using the PCA method.
After testing this method and ending up with a poor recognition rate as
described above, one may think that I failed reaching that goal, but with a
few enhancements (maybe a project for next year) one can correct the
problems described above.

 Creating a whole word OCR (instand of one letter at a time) would


minimize the similar letters mistake. This can be done by loading a
whole word image, dividing it into letters using some clustering
or/and a edge detecting techniques and sending the letter to my OCR
with a flag indicating the letter location in the word (last letter or not).
Because most of the “similar couples”, described above, contains one
final (Sofit) letter, ignoring the final letters when checking a letter
form the beginning or the middle of the word would minimize those
mistakes.

 Centering the letters. By centering the letters within the “image box”
(both the dataset and the given character) the location sensitivity
problem would be solved, because all the letters will be in the same
location within the “image box”. This can be done again by using
clustering or/and a edge detecting techniques in order to find the
location of the letter within the “image box” and moving it to the
center.

 Choosing k. k is the dimension of subspace. k represents the trade-off


between the recognition accuracy and the amount of compution
required. A large k requires more compution time but results in better
accuracy. In this case k was choosen arbitrarily to be 32. Obviously, a
higher k would have resulted in more accurate results. Exhaming the
eigenvalues can proved a method for a better choise of k.

8. References
1. Wikipedia web encyclopedia:

http://en.wikipedia.org/wiki/Main_Page

2. Matt's Matlab Tutorial Source Code Page:

http://joplin.ucsd.edu/Tutorial/matlab.html

3. Lecture Notes form “Introduction to Computational and


Biological Vision” course:

Object Identification and Recognition III - Apearance Based Recognition

You might also like