Gesture Vocalizer for Dumb People

Transcription

1 e-issn Volume 2 Issue 5, May 2016 pp Scientific Journal Impact Factor : Gesture Vocalizer for Dumb People Praveen Gurav 1, Ashwini Hunshyal 2, Akshata Lagamannavar 3, Akshata Somangoudar 4, Ambika Talawar 5 1 Asst. Professor, Dept. of ECE, KLE College of Engg & Technology, Chikodi, Karnataka, India, pgurav25@gmail.com 2,3,4,5 UG Students, Dept. of ECE, KLE College of Engg & Technology, Chikodi, Karnataka, India Abstract Communication plays an important role for human beings. Communication is treated as a life skill. Keeping these important words in mind we present our paper to help in improving the communication with the deaf and dumb people using flex sensor technology. This proposed system also checks pulse rate of the person hence it also provides health monitoring facility. Generally dumb people use sign language for communication but they find difficulty in communicating with others who don t understand sign language. This project aims to lower this barrier in communication. A brief description about various gestures and the implementation part is discussed in this paper. An electronic device is developed that can translate sign language into speech in order to make the communication take place between speech impaired and paralyzed patients with the general public possible. Gloves is used which is normal cloth driving gloves fitted with flex sensors along the length of each finger and the thumb and to perform hand gesture and it will be converted into speech so that normal people can understand their expression. A gesture in a sign language is a particular movement of the hands with a specific shape made out of them. A sign language usually provides sign for whole words, Flex Sensor plays a very important role in this. Flex sensors are those which change in resistance depending on the amount of bend on the sensor. Sensors in the glove pick up gestures and transmit the data with the help of analog to digital convertor to microcontroller. The microcontroller also receives pulse rate data through heartbeat sensor. Converted text data of both will be sent wirelessly through RF transmitter at the sending side. RF receiver at the receiving side converts this text data to speech by the recorder and displayed on the LCD. Keywords Flex sensor, ADC, AT89S52 microcontroller, LCD, APR33A3 Recorder module, RF Trans-receiver module, Speaker, Heart beat sensor. I. INTRODUCTION Generally dumb people use sign language for communication, this project aims to lower the communication barrier between dumb and normal people by developing an electronic device that can translate sign language into speech in order to make the communication effectively. In this project a wireless data gloves is used which is normal cloth fitted with flex sensors along the length of each finger and the thumb. Dumb people can use the gloves to perform hand gesture and it will be converted into speech and text so that normal people can understand their expression. In this system there are two sections, the transmitter part and the receiver part. The transmitter part receives inputs from flex sensor used to determine gesture and from heart beat sensor used to measure the pulse rate. The input received is recognized and transmitted wirelessly to the receiver section where the text relevant to the gesture is displayed on LCD and corresponding voice played through speaker. II. LITERATURE SURVEY A literature survey shows the various analysis and research made in this field and the results already published, taking into account the various parameters of the project and the extent of All rights Reserved 327

2 project. Deaf people have used sign languages throughout the history. One of the earliest written records of a sign language is from fifth century BC, in Plato's Cratylus. In 1620, Juan Pablo Bonet published Reduction of letters and art for teaching mute people to speak which is considered as the first modern treatise of sign language Phonetics. In order to overcome the gap of communication between dumb and normal person we have come up with this novel idea. Some papers present Sign Language Interpreter a recognition system for the vocally disabled. In the recent years, there has been tremendous research on the hand sign recognition. The technology of gesture recognition is divided into two categories- Vision-based and Glove-based, in comparison with these two, vision based system faces many problem it is not convenient for user to use whereas glove based is convenient and simple method. One more study proposes that the system must be capable of recognizing the gestures continuously without any manual indication. The system must recognize the gestures accurately between 80 to 90 percent. There is a need of designing of wireless transceiver system for Microcontroller and Sensors Based Speech Converter. There is a need of monitoring health of speech impaired and paralyzed patients too so heartbeat sensor is mounted in a hand gloves which is convenient and reliable to use, which measure pulse rate. The intension of the sign language translation system is to translate the normal sign language into speech and to make easy contact with the dumb and it is made portable. Proposed system avoids PC intervention for processing and all operations are controlled by microcontroller. Another study states that nowadays embedded system emerging as an important trend in all applications. More recently developed embedded applications are changing our lifestyle in a smart way. The development of speech converter by using RF trans-receiver to send data to recorder leads to an effective use of a device. III. METHODOLOGY Fig 3.1 Flow Chart Fig 3.1 shows the flow of algorithm used in the methodology of this paper. Our hardware requires 5V DC, hence using regulated power supply which comprises step down transformer, bridge rectifier, capacitor filter and a voltage regulator. Step down transformer converts 230V AC to All rights Reserved 328

3 AC. Bridge rectifier converts 12V AC to 12V pulsating DC. A capacitor filter removes riffles present in it and a voltage regulator of 7805 will convert it into 5V DC. A crystal oscillator with 12MHz is used which provides clock frequency to the microcontroller. Electrolytic and Ceramic capacitors are used which removes the ripples and cancels noise. The main electric board will contain a microcontroller that handles the program used to detect the analog voltage levels captured from the sensors, converts them to digital using the ADC of the microcontroller, makes the recognition of the letter signed. Microcontroller will compare the input voltage with predefined program voltage and accordingly it will display the output characters on the LCD screen. 3.1 Transmitter: At the transmitter side, flex sensors play a very important role as they are fitted on hand gloves so as to trace the correct movement of the fingers. For each flex sensor the required voltage will be supplied initially. According to the movement of the fingers there will be a voltage drop associated with it. The voltage thus obtained will be analogy in nature. This analog voltage is converted to digital using an analog to digital converter (ADC) and converted digital voltage is fed to microcontroller AT89s52. Microcontroller not only receives this but also receives pulse rate count input from heart beat sensor connected directly to it, received data is processed at this stage and corresponding values will be sent to receiver through RF transmitter. Fig 3.2 Block diagram of transmitter 3.2 Receiver: At the receiving side, transmitted values are received in microcontroller through RF receiver and compared with the predefined values in the microcontroller and produces the appropriate data to be displayed on the LCD and to be announced by the speaker. 3.3 Power Supply: In power supply circuit the DC pulsating is removed by electrolyte capacitor. Our hardware requires 5V DC and hence a voltage regulator of 7805 series is used. A crystal oscillator with 12MHz is used which provides the microcontroller with frequency clock pulse. The microcontroller process the data received and makes the recognition of the gesture signed. The microcontroller recognizes the predefined letter for a particular gesture and feds to the RF transmitter through serial data communication where RF antenna transmits the data wirelessly. At receiver section, the transmitted data is received by an RF receiver operating at the same frequency as that of the transmitter. The received data is fed as an input to the microcontroller Micro-controller All rights Reserved 329

4 compare the input data i.e. letter with predefined program data and accordingly it will display the output characters on the LCD screen and also simultaneously sends signal to the APR33a3 which plays prerecorded message using speaker. The device is portable and handy device. Fig 3.3 Block diagram of receiver 3.4 Data Glove Data glove is a normal hand glove to which 5 flex sensors are attached along the length of fingers. Sensors are attached to glove either by threading or by glue. Hand gestures are made such that the sensors attached to the glove bends properly and gives out proper voltage drop such that the controller can sense correctly. Fig 3.4 Data Glove Fig 3.5 Flex sensor 3.5 Flex Sensor Sensor refers to a transducer which converts physical energy into electrical energy. Flex sensor is a resistive sensor which changes its resistance as per the change in bend or curvature of All rights Reserved 330

5 into analog voltage. More the bent, more will be the resistance experienced. When the sensor is kept straight with no force acting on it, it has a flat resistance of around 10 kohms and experiences minimum 2 times greater than the flat resistance at 180 pinch bend. Inside the flex sensor are carbon resistive elements within a thin flexible substrate where more carbon means less resistance. The dimensions of the sensor are ¼ inch wide, 2-1/5 inches long and 0.19 inches thick.. The sensors connect to the device via three pin connectors (ground, live and output). Fig 3.6 Change in Resistance According to Bend Fig 3.7 Flex sensor as voltage divider The device incorporates within the device employing a potential divider network. The potential divider is employed to line the output voltage across 2 resistors connected non-parallel as shown in Figure 1.6. The electrical device and flex forms a potential divider that divides the input voltage by a quantitative relation determined by the variable and glued resistors. The change in resistance and corresponding voltage across can be given by the below formula, V OUT = (V IN x R 1 ) / (R 1 + R 2 )...(1.1) Where, V IN - input voltage 5v, R k and R 2 - flex sensor resistance Drawbacks: Strong logic levels are not obtained, have to use pull-up resistors in order to obtained strong logic levels. Analog output from flex sensor is in low range. Analog output from flex sensor is less accurate and unstable. Expensive. 3.6 Heartbeat Sensor: Heart beat sensor is designed to give digital output of heart beat when a finger is placed on it. When the heart beat detector is working, the beat LED flashes in unison with each heartbeat. This digital output can be connected to microcontroller directly to measure the Beats Per Minute (BPM) rate. It works on the principle of light modulation by blood flow through finger at each pulse. For further information please refer to its datasheet. Features 1. Microcontroller based SMD design 2. Heat beat indication by LED 3. Instant output digital signal for directly connecting to microcontroller 4. Compact size 5. Power supply voltage +5V All rights Reserved 331

6 Fig. 3.8 Heartbeat Sensor Applications 1. Digital Heart Rate monitor 2. Patient Monitoring System 3. Bio-Feedback control of robotics and applications 3.7 Microcontroller AT89S52 The AT89S52 is a low-power, high-performance CMOS 8-bit microcontroller with 8K bytes in-system programmable Flash memory. The device is manufactured using Atmel s high-density non-volatile memory technology and is compatible with the industry-standard 80C51 instruction set and pin out. The on-chip Flash allows the program memory to be reprogrammed in-system or by a conventional non-volatile memory programmer. By combining a versatile 8-bit CPU with in-system programmable Flash on a monolithic chip, the Atmel AT89S52 is a powerful microcontroller which provides a highly-flexible and cost-effective solution to many embedded control applications. Salient Features are: 8K bytes of Flash 256 bytes of RAM 32 I/O lines Watchdog timer Two data pointers Three 16-bit timer/counters A six-vector two-level interrupt architecture A full duplex serial port On-chip oscillator and Clock circuitry In addition, the AT89S52 is designed with static logic for operation down to zero frequency and supports two software selectable power saving modes. 3.8 Analog to Digital Convertor (ADC) ADC is an electronic circuit that converts a continuous physical quantity like voltage or temperature to a digital number that represents the quantity s amplitude so that the microcontroller can read the data. The ADC0808 data acquisition component is a monolithic CMOS device with an 8- bit analogy-to-digital converter, 8- channel multiplexer and microprocessor compatible control logic. The 8-bit A/D converter uses successive approximation as the conversion technique. The converter features a high impedance chopper stabilized comparator, a 256R voltage divider with analogy switch tree and a successive approximation register. The 8-channel multiplexer can directly access any of 8- single-ended analogy signals. The design of the ADC0808 has been optimized by incorporating the most desirable aspects of several A/D conversion All rights Reserved 332

7 3.9 LCD Fig LCD Display. LCD (Liquid Crystal Display) screen is an electronic display module and find a wide range of applications. A 16x2 LCD display is very basic module and is very commonly used in various devices and circuits. These modules are preferred over seven segments and other multi segment. LEDs The reasons being: LCDs are economical; easily programmable; have no limitation of displaying special & even custom character (unlike in seven segments) animations and so on. A 16x2 LCD means it can display 16 characters per line and there are 2 such lines. In this LCD each character is displayed in 5x7 pixel matrix. This LCD has two registers, namely, Command and Data. The command register stores the command instructions given to the LCD. A command is an instruction given to LCD to do a predefined task like initializing it, clearing its screen, setting the cursor position, controlling display etc. The data register stores the data to be displayed on the LCD. The data is the ASCII value of the character to be displayed on the LCD RF Transceiver CC2500 The CC2500 is a low-cost 2.4 GHz transceiver designed for very low-power wireless applications. The circuit is intended for the MHz ISM (Industrial, Scientific and Medical) and SRD (Short Range Device) frequency band. The RF transceiver is integrated with a highly configurable baseband modem. The modem supports various modulation formats and has a configurable data rate up to 500 k Baud.CC2500 provides extensive hardware support for packet handling, data buffering, burst transmissions, clear channel assessment, link quality indication, and wake-on-radio. The main operating parameters and the 64-byte transmit/receive FIFOs of CC2500 can be controlled via an SPI interface. In a typical system, the CC2500 will be used together with a microcontroller and a few additional passive components. This module works in half-duplex mode. Means it can either transmit or receive but not both at same time. After each transmission module will be switched to receive mode automatically. The LED for TX and RX indicates whether IC is currently receiving or transmitting.the data sent is checked for CRC error if any. The RX LED is directly on TX OUT pin to indicate that actual data is received and is sent to output pin APR33A3 Recorder The APR33A series are powerful audio processor along with high performance audio analogto-digital converters (ADCs) and digital-to-analog converters (DACs). The APR33A series are a fully integrated solution offering high performance and unparalleled integration with analog input, digital processing and analog output functionality. The APR33A series incorporates all the functionality required to perform demanding audio/voice applications. High quality audio/voice systems with lower bill-of-material costs can be implemented with the APR33A series because of All rights Reserved 333

8 integrated analog data converters and full suite of quality-enhancing features such as sample-rate convertor. Fig 3.10 CC2500 Trans-receiver module Fig 3.11 APR33A3 Recorder module The APR33A series C2.0 is specially designed for simple key trigger, user can record and playback the message averagely for 1, 2, 4 or 8 voice message(s) by switch. It is suitable in simple interface or need to limit the length of single message, e.g. toys, leave messages system, answering machine etc. Meanwhile, this mode provides the power-management system. Users can let the chip enter power-down mode when unused. It can effectively reduce electric current consuming to15ua and increase the using time in any projects powered by batteries. IV. RESULTS The proposed method translates sign language to speech automatically and satisfy dumb people by conveying their thoughts.the system overcomes the real time difficulties of dumb people and improve their lifestyle. System efficiency is improved with the help of microcontroller and APR33A, also integrated with RF wireless transmission for long distance communication. By implementing this system speaking dream of dumb people becomes true. Compared with existing system it is possible to carry this to any place with ease. The main advantage of this approach is less computational time and fast response in real time applications. Wireless data transmission to the LCD and recorder, makes the user to handle it freely. It can be used in any public place very conveniently. Fig 4.1 shows some hand gestures that are converted and displayed in text form on LCD. Fig 4.1 Hardware All rights Reserved 334

9 Fig 4.2 Hand gestures V. CONCLUSION The proposed method translates sign language to speech automatically and satisfy dumb by conveying thoughts on their own. The system overcomes the real time difficulties of dumb people and improves their lifestyle. System efficiency is improved with the help of microcontroller and APR33A3, also integrated with RF wireless transmission is help in long distance communication. By implementing this system speaking dream of dumb people becomes true. Compared with existing system it is possible to carry this system to any places. The main advantage of this approach is less computational time and fast response in real time applications has been achieved. Due to the wireless data transmission to the LCD and recorder, makes the user to handle it freely. It can be used in public places very conveniently. In future,the system can be made more compact such that both transmitter and receiver parts mounted on same glove.the presented system may not give 100% accurate output due to high sensitivity of sensors thus still more development is needed for flex sensors. System is trained on a limited database should be made capable to handle more gesture. Other developments needed are like 1. Designing of a whole system, which would be capable of vocalizing the gestures and movements of animals. 2. Virtual reality application e.g., replacing the conventional input devices like joy sticks in video games with the data glove. 3. The Robot control system to regulate machine activity at remote sensitive sites. Thus the future enhancement of this system not only leads to an effective communication between dumb and normal but also to smart All rights Reserved 335

10 REFERENCES [1] Nimitha N, Ranjitha R, Santhosh Kumar V, Steffin Franklin, Implementation of Real Time Health Monitoring System Using Zigbee For Military Soldiers, International Journal for Research in Applied Science & Engineering Technology (IJRASET), Volume 3, Issue IV, ISSN: April [2] Kiran R, Department of Electronics and Communication Engineering, College of Engineering Trivandrum, India Digital Vocalizer System for Speech and Hearing Impaired International Journal of Advanced Research in Computer and Communication Engineering, Vol. 4, Issue 5, May [3] Sachin Bhat, Amruthesh M, Ashik, Chidanand Das, Sujith, Translating Indian Sign Language to text and voice messages using flex sensors, International Journal of Advanced Research in Computer and Communication Engineering,Vol. 4, Issue 5, May [4] Rajalakshmi, N.Vasudevan, Dr.Rajinigrinath, S. Praveen Kumar, Electronic Hand Glove Gesture to Voice Reorganization Using Physically Challenged Persons, International Journal of Innovative Research in Computer and Communication Engineering, An ISO 3297: 2007 Certified Organization Vol.3, Special Issue 8, October [5] Priyanka Lokhande,Riya Prajapati,Sandeep Pansare, Data Gloves for Sign Language Recognition System International Journal of Computer Applications ( ) National Conference on Emerging Trends in Advanced Communication Technologies (NCETACT-2015). [6] Arulselvi and Tamarai, Sign Language Recognition System Using Fingern Spelling, Middle-East Journal of Scientific Research 20 (8): , 2014,ISSN , IDOSI Publications, [7] Naveen Kumar Toshawar, Chandni Jain, Intelligent Control System using Gesture Sensing, National Conference on Synergetic Trends in engineering and Technology: Impact of Industry & Society (STET-2014) International Journal of Engineering and Technical Research (IJETR) ISSN: , Special Issue. [8] Vajjarapulavanya, Akulapravin, M.S., Madhanmohan, Hand Gesture Recognition And Voice Conversion System Using Sign Language Transcription System IJECT Vol. 5, Issue 4, Oct - Dec [9] R.Manikandan Sastra University, Sign Language to Speech Translation System Using PIC Microcontroller, APRIL [10] Ajinkyaraut, Vineeta Singh, Vikrant Rajput, ruchikamahale HAND SIGN INTERPRETER The International Journal of Engineering And Science (IJES), Volume 1, Issue 2, Pages 19-25, 2012, ISSN: [11] Bhavina Patel, Vandana Shah, Ravindrakshirsagar, Microcontroller Based Gesture Recognition System for the Handicap People, Journal of Engineering Research and Studies, Vol. II, Issue IV, October-December, 2011/ [12] Muhammad Ali Mazidi, Janice Gillispie Mazidi, Rolin D Mckinenlay, The 8051 Microcontroller and Embedded systems published by Pearson Education, Second Edition, All rights Reserved 336