Scribd
Upload
27 views1 page

Dsaa Project Initial Proposal GROUP-11 Members: Vaishnavi NV, Syed Jahangir Peeran, V Tejkiran, V Sai Rathan, Srilekha N

The document proposes extracting text from images using optical character recognition and machine learning, then converting the text to speech. It would allow applications like reading bedtime stories aloud or speaking street names to blind users. Challenges include recognizing broken text and improving accuracy through machine learning and grammar/spelling checks. The input is a photo with text, which would undergo text detection, character segmentation/classification, word merging, correctness checking, and final text-to-speech output.

Uploaded by

Harshitha Reddy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
27 views1 page

Dsaa Project Initial Proposal GROUP-11 Members: Vaishnavi NV, Syed Jahangir Peeran, V Tejkiran, V Sai Rathan, Srilekha N

The document proposes extracting text from images using optical character recognition and machine learning, then converting the text to speech. It would allow applications like reading bedtime stories aloud or speaking street names to blind users. Challenges include recognizing broken text and improving accuracy through machine learning and grammar/spelling checks. The input is a photo with text, which would undergo text detection, character segmentation/classification, word merging, correctness checking, and final text-to-speech output.

Uploaded by

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

DSAA PROJECT

INITIAL PROPOSAL
GROUP-11
Members: Vaishnavi NV, Syed Jahangir Peeran, V Tejkiran, V Sai Rathan, Srilekha N.

Aim
Extracting meaningful text from a given image using Optical Character recognition
(OCR) along with machine learning and then converting the extracted text into speech.

Applications
(i) A software which reads out bedtime stories or as a textbook reader for students.
(ii) An OCR based app with access to camera and speech which communicates the
street name/door number to a blind person (through speech).

Challenges
(i) We will try to recognise even broken text in an image.
(ii) With the addition of using machine learning algorithm, the accuracy of OCR will
be lifted up.
(iii) For better accuracy, we will run the converted text through grammar/spelling
checker to predict the word/sentence better.

Input
A photo with text written on it, will be sent as the input for processing.

Processing
(i) Detect text regions alone from the image using sliding windows technique.
(ii) Segmenting characters.
(iii) Classifying characters.
(iv) Combining the letters and merging words to form sentences.
(v) Checking its correctness.
(vi) Converting the obtained text to speech.

Output
A voice signal speaking out the text which was processed in the above step.

References
(i) Chen, Huizhong, et al. "Robust Text Detection in Natural Images with Edge-
Enhanced Maximally Stable Extremal Regions." Image Processing (ICIP), 2011 18th
IEEE International Conference on. IEEE, 2011.
(ii) https://www.coursera.org/learn/machine-learning

You might also like