DESCRIPTION
The patent disclosure oovers System and Method for Automated Speech Synthesis for Instant Notifications to
Visually Challenged People.
In the proposed patent, the application, available on the Play Store, enables users to oonvert any text appearing in
notifications into audio speech, featuring optical character reoognition, auto-start functionality, multi-language
support, and hand gesture features all in one comprehensive application.
Fig 1 Shows the screen shot of reading text
Detailed Description of the Project
1. Document Reader In document reader page, import the PyPDF2 and pyttsx3 modules, open the PDF file using
PdfFileReader() to read the PDF by providing the path of the PDF as the argum~nt. Use the getPage() method to
select the page to be read, then extract the text from the page using extractText(). Finally, instantiate a pyttsx3
object.
2. Optical Character Recognition In optical character recognition page, need to load the image using OpenCV,
which is installed under the name cv2. The image then needs to be converted to a binary image if it is not already
one, consisting only of black and white pixels. In the case of it being a binary image, you can skip the two lines of
code that store the result in the gray variable. The binary image is obtained by first converting it to grayscale and
then applying an arithmetic operation, which, in this case, is the bitwise-not operation. Gray scaling involves taking
the three RGB values of an image and transforming them using the following formula: Y = 0.299 • R + 0.587 • G +
0.114' B.
3. Screeri Reader In screen reader page, identify elements that could be read aloud. Select the appropriate element.
Specify how to read that element to the user.
REFERENCES
1. Nishank M- Voice Assistant for visually challenged people-International Research Journal of Engineering and
Technology (IRJET)-6-9
2. Kiran.Rakshana R, Chitra C-A Smart Navguide System for visually challenged-International Journal of Innovative
Technology and Exploring Engineering (IJITEE)-8-6
3. ElisaAnderson-visually challenged Reader: An Object Identification Mobilebased Application for the visually
challenged using Augmented Reality Detection-International Conference on Cybernetics and Intelligent System
(ICARUS)-6-5
4. Md. Amana! Khan Shishir-EYE ASSISTANT-{ICASERT 2019)-2454-915-NGEPET(special issue)
5. Schantz, Herbert F. (1982). The history of OCR, optical character recognition. [Manchester Center, Vt.j: Recognition
Technologies Users. Association. ISBN 9780943072012.
6. Dhaval, Sunita Vikrant, Advanced Image-Based Spam Detection and Filtering Techniques. Hershey, PA: IGI Global.
p. 91.1SBN 9781683180142. Retrieved September 27,2019.
7. Tappert, C. C.; Suen, C. Y.; Whakaari, T. "The state of the art in online handwriting recognition" .IEEE Transactions
on Pattern Analysis and Machine Intelligence.
Tappert
CLAIMS
1/We Claim,
1. The patent disclosure covers System and Method for Auto Configuration and Booting set using RPA
as described above in Fig 1.
2. A screen reader is an essential piece of software for a visually challenged person.
3. A screen reader transmits whatever text is displayed on the computer screen into a form that a
visually challenged user can process (usually tactile, audible or a combination of both).
4. The system can eventually upgraded to a level where a non-visually challenged people to use with
smooth interface in increasing their productivity and connectivity