A Smart Navguide System for Visually Impaired
Kiran Rakshana R1, Chitra C2
1Kiran Rakshana R, Department of Electronics and Communication Engineering, PSNA College Of Engineering And Technology, Anna university, Dindigul, India.
2Chitra C, Professor of Department of Electronics and Communication Engineering, PSNA College Of Engineering And Technology, Anna university, Dindigul, India.
Manuscript received on 05 April 2019 | Revised Manuscript received on 14 April 2019 | Manuscript Published on 24 May 2019 | PP: 182-184 | Volume-8 Issue-6S3 April 2019 | Retrieval Number: F10350486S319/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Nowadays, the Communication is generally takes place through speech and text. To access the information in a text, the vision plays the significant role. The visionless people can gather the information through their hearing ability. The proposed system is a novel implementation of smart guiding system for the visually challenged. The system is a novel and real-time cost beneficial technique. Instead of reading through them, the system allows the visually impaired to hear the contents of the text images. The Proposed system consists of Pi camera, audio microphone, ultrasonic sensor, Raspberry pi, headphone for voice and vibration motor. This system consists of three modules such as voice searching module, image processing module and voice-processing module. These modules are implemented by using the keyword operation search, which is in the form of voice, which is given by the user. After the keyword is received by the Raspberry pi, the pi camera will capture the image, according to the given keyword. This system integrates the Optical Character Recognition and Text to Speech Synthesizer concept. It comprises text extraction from image and translates the text into speech; this helps the user to read the text easier. In computer vision, the extraction of text is a difficult task from the color images. The image processing module stage includes binarization, de-noising, de-skewing, segmentation and feature extraction. It is also used to identify the bus name and bus number in the bus stop or bus stand for the visually impaired and it also achieve the obstacle avoidance by using the ultrasonic sensor and it is informed to the user by vibration sensing technique.
Keywords: Raspberry Pi, OCR, TTS, Pi Camera, Visually Impaired.
Scope of the Article: Communication