A SMART IMAGE PROCESSING ALGORITHM FOR TEXT RECOGNITION, INFORMATION EXTRACTION AND VOCALIZATION FOR THE VISUALLY CHALLENGED

This paper proposes a smart algorithm for image processing by means of recognition of text, extraction of information and vocalization for the visually challenged. The system uses LattePanda Alpha system on board that processes the scanned images. The image is categorized into its equivalent alphanumeric characters following pre-processing, segmentation, extraction of features and post-processing of the scanned or image based information. Further, a text to speech synthesizer is used for vocalization processed content. In converting handwritten scripts, the system offers an accuracy of 97% in conversion. This also depends on the legibility of the data. The time delay for the entire conversion process is also analysed and the efficiency of the system is estimated.

[1]  Laura Fernández-Robles,et al.  Application of Extractive Text Summarization Algorithms to Speech-to-Text Media , 2019, HAIS.

[2]  Chandra Shekhar Yadav,et al.  Optical Character Recognition (OCR) for Printed Devnagari Script Using Artificial Neural Network , 2010 .

[3]  Ricardo Oliveira,et al.  Text Vocalizing Desktop Scanner for Visually Impaired People , 2018, HCI.

[4]  A. V. Joshi Kumar,et al.  Automated Electronic Pen Aiding Visually Impaired in Reading, Visualizing and Understanding Textual Contents , 2012 .

[5]  Pravin A. Dhulekar,et al.  Automatic voice generation system after street board identification for visually impaired , 2016, 2016 International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC).

[6]  Gérard Chollet,et al.  Data Driven Approaches to Speech and Language Processing , 2004, Summer School on Neural Networks.

[7]  Jiss Kuruvilla,et al.  A review on image processing and image segmentation , 2016, 2016 International Conference on Data Mining and Advanced Computing (SAPIENCE).

[8]  Larry S. Davis,et al.  A video based interface to textual information for the visually impaired , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.

[9]  Mrunmayee Patil,et al.  An Automatic Approach for Translating Simple Images into Text Descriptions and Speech for Visually Impaired People , 2015 .

[10]  Neha Joshi.  Text Image Extraction and Summarization , 2019 .

[11]  Frédéric Bimbot,et al.  Variable-length sequence matching for phonetic transcription using joint multigrams , 1995, EUROSPEECH.

[12]  B. Vanathi,et al.  Hardcopy Text Recognition and Vocalization for Visually Impaired and Illiterates in Bilingual Language , 2019 .

[13]  Nachum Dershowitz,et al.  OCR Error Correction Using Character Correction and Feature-Based Word Classification , 2016, 2016 12th IAPR Workshop on Document Analysis Systems (DAS).

[14]  K. Ragavi,et al.  Portable Text to Speech Converter for the Visually Impaired , 2016 .

[15]  Prabhat Verma,et al.  A Framework for the Next Generation Screen Readers for Visually Impaired , 2012 .

[16]  V. Anjalipriya,et al.  REAL TIME IMPLEMENTATION OF IMAGE RECOGNITION AND TEXT TO SPEECH CONVERSION , 2014 .

[17]  Frédéric Bimbot,et al.  Inference of variable-length linguistic and acoustic units by multigrams , 1997, Speech Commun..

[18]  Prabhat Verma,et al.  An enhanced speech-based Internet browsing system for visually challenged , 2010, 2010 International Conference on Computer and Communication Technology (ICCCT).

[19]  M. ARUN,et al.  Design and Implementation of Text To Speech Conversion for Visually Impaired Using ‘ i ’ Novel Algorithm , 2014 .

[20]  Chien-Hsing Chou,et al.  Chinese FingerReader: a wearable device to explore Chinese printed text , 2017, SIGGRAPH Posters.

[21]  Ajay Roy,et al.  Text recognition and face detection aid for visually impaired person using Raspberry PI , 2017, 2017 International Conference on Circuit ,Power and Computing Technologies (ICCPCT).