<< Chapter < Page Chapter >> Page >

Preparation

All files referenced and other helpful information is posted on this site at the GitHub link. The GitHub link also has 3 Python files, which is our completed OCR software. This tutorial serves as a walkthrough of the code under recognitionScript.py, where more in-depth explanations are discussed in the provided .py files.

This tutorial uses Python 2.7, Numpy, and OpenCV for the software development portions. The instructions for downloading OpenCV for Linux can be found at this link. For windows, go to to opencv.org For Numpy, visit numpy.org For Python, visit python.org

We assume the reader will have been exposed to Python before. If not, a general understanding of Python IO and the ability to look up Python documentation is preferable.

Preprocessing

For our tutorial, we will make a few assumptions for our input images. First off, the image will only have printed text. We also assume the image will be a png. For example, we will have pictures similar to the figure below. Sample image Because this is an introduction, there will not be information on transforming and translating, as this involves verbose algorithms beyond the scope of our knowledge.

Second, images may contain the full range of colors.

The first step is to read in the image we will be performing OCR on. OpenCV has the ability to do this with imread() function. We have made a wrapper function that does this and returns a copy, which will be necessary for some OpenCV functions

Reading in image

Right now, im is an image, which can be represented as a matrix with pixels. Each pixel is some object with 3 values, red, blue, green(rgb). In order to make this compatible with future functions, we will convert the image to grayscale. This involves a function provided by OpenCV, which process the rgb values and replace the pixel with some intensity value. The next step is to convert the image into grayscale. Open Cv has a color converting function called Cv2.cvtColor(image, code ) which can map one type of color to another based on the input code. For the purposes of converting our image into grayscale we use the parameter Cv2.COLOR_BGR2GRAY and call our the helper function color2gray, which returns the grayscaled image.

Convering color to gray

Greyscale Above is our grayscaled image.

Filtering

Next, we will need to apply a filter onto the image. Depending on the task, we could use many different filters to achieve a certain goal. We want to filter our image to increase our ability to detect edges; this allows us to identify characters in the image. Therefore, we will be covering the Gaussian, Laplacian, and Sobel filters.

Gaussian filter

Using the following formula, we will create some n by n matrix to build the Gaussian filter.

gaussss

The Gaussian filter is effective towards noisy signals, because of its characteristic as also being a low pass filter. By blurring the image to a small degree, we allow any sensitive edge detection algorithms to not mistake noise to be something of significance.

Laplace

In cases where we know that noise is not an issue, we can use the Laplacian filer. Rather than worry about reducing noise, the Laplace filter's purpose is to enhance edges by sharpening the image. The formula to describe the filter is

Questions & Answers

Is there any normative that regulates the use of silver nanoparticles?
Damian Reply
what king of growth are you checking .?
Renato
What fields keep nano created devices from performing or assimulating ? Magnetic fields ? Are do they assimilate ?
Stoney Reply
why we need to study biomolecules, molecular biology in nanotechnology?
Adin Reply
?
Kyle
yes I'm doing my masters in nanotechnology, we are being studying all these domains as well..
Adin
why?
Adin
what school?
Kyle
biomolecules are e building blocks of every organics and inorganic materials.
Joe
anyone know any internet site where one can find nanotechnology papers?
Damian Reply
research.net
kanaga
sciencedirect big data base
Ernesto
Introduction about quantum dots in nanotechnology
Praveena Reply
what does nano mean?
Anassong Reply
nano basically means 10^(-9). nanometer is a unit to measure length.
Bharti
do you think it's worthwhile in the long term to study the effects and possibilities of nanotechnology on viral treatment?
Damian Reply
absolutely yes
Daniel
how to know photocatalytic properties of tio2 nanoparticles...what to do now
Akash Reply
it is a goid question and i want to know the answer as well
Maciej
characteristics of micro business
Abigail
for teaching engĺish at school how nano technology help us
Anassong
Do somebody tell me a best nano engineering book for beginners?
s. Reply
there is no specific books for beginners but there is book called principle of nanotechnology
NANO
what is fullerene does it is used to make bukky balls
Devang Reply
are you nano engineer ?
s.
fullerene is a bucky ball aka Carbon 60 molecule. It was name by the architect Fuller. He design the geodesic dome. it resembles a soccer ball.
Tarell
what is the actual application of fullerenes nowadays?
Damian
That is a great question Damian. best way to answer that question is to Google it. there are hundreds of applications for buck minister fullerenes, from medical to aerospace. you can also find plenty of research papers that will give you great detail on the potential applications of fullerenes.
Tarell
what is the Synthesis, properties,and applications of carbon nano chemistry
Abhijith Reply
Mostly, they use nano carbon for electronics and for materials to be strengthened.
Virgil
is Bucky paper clear?
CYNTHIA
carbon nanotubes has various application in fuel cells membrane, current research on cancer drug,and in electronics MEMS and NEMS etc
NANO
so some one know about replacing silicon atom with phosphorous in semiconductors device?
s. Reply
Yeah, it is a pain to say the least. You basically have to heat the substarte up to around 1000 degrees celcius then pass phosphene gas over top of it, which is explosive and toxic by the way, under very low pressure.
Harper
Do you know which machine is used to that process?
s.
how to fabricate graphene ink ?
SUYASH Reply
for screen printed electrodes ?
SUYASH
What is lattice structure?
s. Reply
of graphene you mean?
Ebrahim
or in general
Ebrahim
in general
s.
Graphene has a hexagonal structure
tahir
On having this app for quite a bit time, Haven't realised there's a chat room in it.
Cied
what is biological synthesis of nanoparticles
Sanket Reply
Got questions? Join the online conversation and get instant answers!
Jobilize.com Reply

Get the best Algebra and trigonometry course in your pocket!





Source:  OpenStax, Introduction to optical character recognition. OpenStax CNX. Dec 17, 2014 Download for free at http://legacy.cnx.org/content/col11728/1.1
Google Play and the Google Play logo are trademarks of Google Inc.

Notification Switch

Would you like to follow the 'Introduction to optical character recognition' conversation and receive update notifications?

Ask