h2 instructions about the directions to the blind

h2 { margin-top: 0.42cm; margin-bottom: 0.42cm; color: rgb(0, 0, 0); page-break-after: auto; }h2.western { font-family: “Liberation Serif”, serif; font-size: 12pt; }h2.cjk { font-size: 10pt; }h2.ctl { font-family: “FreeSans”; font-size: 12pt; font-weight: normal; }h1 { margin-bottom: 0.42cm; color: rgb(0, 0, 0); text-align: center; page-break-after: auto; }h1.western { font-family: “Liberation Serif”, serif; font-size: 14pt; }h1.cjk { font-size: 14pt; }h1.ctl { font-size: 14pt; }p { margin-bottom: 0.25cm; line-height: 120%; }

ABSTRACT

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

Application for detecting an object using the
mobile video camera and giving voice instructions about the current
location of the blind user by using GPS and to give the direction of
an object to the blind person. User will need to train the system
first regarding the object information. System extracts the features
to search objects in the camera view to know the direction of object,
where it is placed using angle extraction feature. This Android
application gives warning of the obstacles in the way to the user.
. Also the proposed system converts the text into
audio for giving the instructions about the directions to the blind
person and for such conversion the Speech synthesizer technique gets
used. The camera of the phone is enough for this purpose and no
special hardware is required, ensuring that it requires minimal
effort from the user to use the application during everyday life.
System gets used in social approach where the object in place or in
path everyday life and with the help of this system blind person
easily travel or visit common places such as school, college,
hospital, shopping mall and travel on roads.

INTRODUCTION

Object recognition

Blind
people face several problems in their life, one of these problems
that is the most important one is detection the obstacles when they
are walking. In this research, we suggested a system with two cameras
placed on blind person’s glasses that their duty is taking images
from different sides. By comparing these two images, we will be able
to find the obstacles. In this method, first we investigate the
probability of existence an object by use of special points that then
we will call them “Equivalent points”, then we utilize
binary method, standardize and normalized cross-correlation for
verifying this probability. This system was tested under three
different conditions and the estimated error is acceptable range.

Optical
character recognition

Machine
replication of human functions, like reading, is an ancient dream.
However, over the last five decades, machine reading has grown from a
dream to reality. Optical character recognition has become one of the
most successful applications of technology in the field of pattern
recognition and artificial intelligence. Many commercial systems for
performing OCR exist for a variety of applications, although the
machines are still not able to compete with human reading
capabilities.

2
LITERATURE REVIEW

In 2012, Nidhi describes Prototype system for color based object
detection is successfully implemented and tested. The test results
show that the detection method used in the paper can accurately
detect and trace any object in real time. This paper shows the
methods of Image processing and detecting an object in it based on
its specific color, by using Open cctv real time implementation is
possible. Thresholding of the generated image is necessary in order
to segment the image pixels and let them free from each other.

In 2012, Sanjivani Shantaiya presents an extensive survey of object
detection approaches and also gives a brief review of each approach.
Various object detection approaches are discussed as feature based,
template based, classifier based, motion based as per the reviewed
papers.

In 2013, Shalin A. Chopra tells about OCR system for offline
handwritten character recognition. The systems have the ability to
yield excellent results. Preprocessing techniques used in document
images as an initial step in character recognition systems were
presented. The feature extraction step of optical character
recognition is the most important.

In 2013, Khushboo Khurana describes In this paper, we have discussed
various object detection techniques. The template matching technique
requires large database of image templates for correct object
recognition. Hence it must be used only when limited objects are to
be detected. Global features and shape based method can give better
result and are efficient as compared to local features.

In 2014, Sukanya C.M describes In this survey paper all the main
terminology of object detection have been addressed. These include
object detection methods, feature selection and object
classification. Most commonly used and well recognized methods for
these phases have been explained in details. Different methods for
object detection are like frame difference, optical flow and
background subtraction.

In 2015, Chirag Patel describes Although Tesseract is command-based
tool but as it is open source and it is available in the form of
Dynamic Link Library, it can be easily made available in graphics
mode. The results obtained in above sections are obtained by
extracting vehicle number from vehicle number plate.

In 2015, Sean O’Brien After successfully creating our Hungarian
character and language models, we assessed the accuracy of the
OCRopus software. We compared the results of our models versus the
default English models on a Hungarian algebra textbook written in
1977 by László Fuchs.

In 2016, Mayuri B Gosavi In this system, we have proposed an
artificial neural network-based simple colour and size invariant
character recognition system to recognize English alphanumeric
characters. Our proposed system gives excellent result for the
character letters when they are trained and tested separately but
produce satisfactory result when they are processed together.

In 2016, Astha Gautam With the help of object recognition concept we
can simply identify the objects present in an image or a video
sequence. There are number of techniques and methods that can be
applied for having the desired result.

In 2016, Sukhpreet Singh This paper has presented a related work on
English OCR techniques. Various available techniques are studied to
find a best technique. But is found that the techniques which provide
better results are slow in nature while fast techniques mostly
provide inefficient results.

3
PROPOSED SYSTEM

The main objective of this project is to
develop an application for blind people to detect the objects in
various directions, detecting pits and manholes on the ground to make
free to walk Detecting objects using image processing can be used in
multiple industrial as well as social application. This project is
proposing to use object detection for blind people and give them
audio/ vocal information about it. We are detecting an object using
the mobile camera and giving voice instructions about the direction
of an object. User must have to train the system first about the
object information. We are then doing feature extraction to search
for objects in the camera view. We are taking help of angle where
object is placed to give direction about the object.

Figure
3.1:System
architecture of ODR

4
CONCLUSION

Optical character recognition technology
today can read and recognize an array of languages and convert files
into a number of formats. Even though it was developed decades ago,
it continues to be changed, edited and improved. The OCR application
is an apt tool for picture to text conversion and can be used by
different people in a variety of environments. It continues to be
supported by a wide range of products and systems, from
top-of-the-line machinery to compact easy-to-use solutions.

All through
the years, the methods of OCR systems have improved from primitive
schemes suitable only for reading stylized printed numerals to more
complex and sophisticated techniques for the recognition of a great
variety of typeset fonts and also hand printed characters.

REFERENCES

1. Arica, N., Vural, F. T.
Y., An Overview of Character Recognition focused on Offline
Handwriting, IEEE Transactions on Systems, Man and Cybernetics –
Part C: Applications and Reviews, 31(2), pp 216–233, 2001.

2. Bunke, H., Wang, P. S. P. (Editors), Handbook of Character
Recognition and Document Image Analysis, World Scientific, 1997.

3. Chaudhuri, A., Some Experiments on Optical Character Recognition
Systems anguages using Soft Computing Techniques, Technical Report,
Birla Institute of Technology Mesra, Patna Campus, India, 2010.

4. Cheriet, M., Kharma, N., Liu, C. L., Suen, C. Y., Character
Recognition Systems: A Guide for Students and Practitioners, John
Wiley and Sons, 2007.

5. Dsholakia, K., A Survey on Handwritten Character Recognition
Techniques for various Indian Languages, International Journal of
Computer Applications, 115(1), pp 17–21, 2015.

6. Mantas, J., An Overview of Character Recognition Methodologies,
Pattern Recognition, 19(6), pp 425–430, 1986.

7. Rice, S. V., Nagy, G., Nartker, T. A., Optical Character
Recognition: An Illustrated Guide to the Frontier, The Springer
International Series in Engineering and Computer Science, Springer
US, 1999.