International Journal of Computer Applications (0975 – 8887) Volume 64– No.13, February 2013 42 Voice Assisted Embedded Navigation System for the Visually Impaired V. Ramya Assistant Professor Department of Computer Science and Engineering, Annamalai University, Chidambaram,Tamilnadu Laxmi Raja Research Scholar Department of Computer Science and Engineering, Annamalai University, Chidambaram,Tamilnadu B Palaniappan Professor Department of Computer Science and Engineering, Annamalai University, Chidambaram,Tamilnadu ABSTRACT For visually impaired people, a cane is a close companion helping them to detect and avoid obstacles while walking. But while walking in a new or changed environment, it is hard for them to guess where they are. Also it will be a problem when they lose memory of locations and places. The standard method for taking notes by visually impaired is to emboss Braille dots on a paper, which can be read by feeling the dots by fingers [16]. It is difficult to imprint, copy, transfer or edit these writings. With the advancement in modern day electronic sensors, touch sensing and microcontroller technology, the proposed system aids the visually impaired in navigation via audible messages and haptic feedback, helping them localize where they are and to improve their mobility. This system supports the visually impaired to enter notes and control device operation via touch keypad. The device also provides user information in audio format, including navigation direction, ambient light and temperature condition. The aim of this project is to help visually impaired to improve their communication and provides independency during walking in even unknown areas. Keywords ARM, MEMS, Touch Keypad, and Voice assisted Navigation. 1. INTRODUCTION Worldwide, there are 314 million visually impaired and 45 million of them are blind. About 87% of the visually impaired live in the developing countries, over them 15 million people are from India [19]. Blind and Visual impaired people face several accessibility and mobility problems in day to day life. Some tasks or situations have physical constraints, sometimes impossible for them to overcome [16]. Those difficulties are related with a lack of autonomy or information that could help them to avoid obstacles. These problems can be overcome by improving the human ability for sensing and recognizing it [12]. In general, urban accidents are influenced by a lack of right signalization or by a chance, and some related causes like public phone booths, mailboxes, poles, dump-carts and twigs of trees. Moving through an unknown environment becomes a real challenge when we can’t rely on our own eyes [17]. Since dynamic obstacles usually produce noise while moving, blind people develop their sense of hearing to localize them [18]. However they are reduced to their sense of touch when the matter is to determine where an inanimate object exactly is. The common way for navigating of visionless person is using a walking cane. The walking cane is a simple and purely mechanical device dedicated to detect static obstacles on the ground, uneven surfaces, holes and steps via simple tactile- force feedback. This device is light, portable, but range limited to its own size and it is not usable for dynamic obstacles detection. Many commercial devices are available in the market for navigation for the blind. But lack of user-friendliness makes them less useful for the consumers. Thus our system is designed with ARM processor as it heart which can give the following applications; the system gives an audio output through microphone to the user about the direction in which the user is travelling. The system also provides a light source providing ambient light. The purpose of this light is to announce the presence of the user during low light times like night hours. Temperature of the environment can be sensed and output sent as voice. The device can take notes using a touch keypad when needed. It also has a MP3 player to play the user’s favorite music when needed and a SD card for storage. 2. RELATED WORK Katherine J. et.al [1] has developed HALO which gives visually impaired the freedom to travel independently in unknown environments, but they cannot warn the user of overhead hazards such as tree branches. HALO provides haptic cues to warn a visually impaired user of low-hanging obstacles during white cane navigation. The Haptic Alerts for Low-hanging Obstacles (HALO) system is a portable and affordable attachment to traditional white canes. By pairing distance data acquired from an ultrasonic range sensor with vibration feedback delivered by an eccentric mass motor, the device aims to alert users of low-hanging obstacles without interfering with the standard functionality of a white cane. Esteban Bayro Kaiser et.al [2] have developed “Wearable navigation system for the blind” that will map and track the position of the pedestrian during the exploration of the unknown environment. In order to build this system, the well known Simultaneous Localization and Mapping (SLAM) from mobile robotics will be implemented. Once a map is created the user can be guided efficiently by a route selecting method. The user will be equipped with a short range Laser, an inertial measurement unit (IMU), a wearable computer for data processing and an audio bone headphone. This system does not intent to replace the use of the white cane. However, the purpose is to gather contextual information to aid the user in navigating with the white cane. S.Kammouna et.al [3] have designed the NAVIG device which aims to complement conventional mobility aids (i.e.