Swetali

Page 1

Vol.4 Issue 1

International Engineering Journal For Research & Development

Impact factor : 3.35

E-ISSN NO:-2349-0721

A REVIEW PAPER ON: DESIGN AND MODELING GESTURE RECOGNITION OF HANDWRITTEN ALPHANUMERIC USING ACCELEROMETER BASED DIGITAL PEN Mr. Amit Fulsunge (Assistant Professor) Ms.Swetali D. Pawade Dept. of Electronics & Communication Engg. Dept.of Electronics & Communication Engg. Email: -Amitfulsunge@gmail.com Email:-swetalipawade26@gmail.com _________________________________________________________________________________________ air. The character recognition is done by an MEMS

ABSTRACT

accelerometer. This accelerometer gives response In this paper an MEMS accelerometer mostly based on gesture recognition algorithm and its application are presented. The hardware module

consists

of

a

triaxial

MEMS

accelerometer, microcontroller, and RF wireless transmission module for sensing and collecting accelerations of handwriting and hand gesture trajectories. Users will use this digital pen to write down digits, alphabets & some hand gestures. The accelerations of hand motions deliberate by the accelerometer are transmit wirelessly to a personal computer for trajectory recognition. The trajectory algorithm collected of information variety assortment, signal pre-processing for reconstruct the trajectory to satisfy the collective errors caused by drift of sensors. So, by altering the location of MEMS (micro electro mechanical systems) we can proficient to demonstrate the alphabetical characters and numerical on PC.

for every slight deflection or movement in the system. Accelerometer is developed by using MEMS technology. A significant advantage of accelerometer for general motion sensing is that they can be operated without any external reference and limitation in working conditions. However, gesture

recognition

is relatively complicated

because different users have different speeds and styles to generate various motion trajectories. Thus, many researchers have tried to increasing the accuracy of handwriting recognition systems. Recently, some researchers have working on reducing the error of handwriting trajectory reconstruction by using acceleration signals and angular velocities of inertial sensors. However, the reconstructed trajectories suffer from various intrinsic errors of inertial sensors. Hence, many researchers have focused on developing effective algorithms to reduce error of inertial sensors & to

KEYWORDS: MEMS accelerometer, handwritten

improve the recognition accuracy. (An efficient

gesture recognition, trajectory algorithm.

acceleration error compensation algorithm based on zero velocity compensation was developed to

INTRODUCTION Handwriting Recognition is mostly used for security & authentication purpose. There are two types of recognition offline recognition & online recognition. The constructed system is an online hand writing character recognition written in

www.iejrd.in

reduce acceleration errors for acquiring accurate reconstructed trajectory. The features of the preprocessed acceleration signals of each axis include ZCD and Range. Before classifying the hand

motion

trajectories,

we

perform

the

procedures of feature selection and extraction methods. The PNN classifier is used to get better

1


Vol.4 Issue 1

International Engineering Journal For Research & Development accuracy. If the orientation of the instrument was

equivalent digital algorithms as programmed. The

estimated precisely, the motion trajectories of the

complete computer can be controlled through hand

instrument were reconstructed accurately.

gestures. This will make our over all work easier and efficient. This paper deals with the controlling

BRIEF LITERATURE SURVEY:

all operations of mouse such as right click, left

Mr. Kunal J. Patil11, Mr. A. H. Karode2, Mr. S. R. Suralkar3 International Journal of Application or Innovation

in

(IJAIEM)

Web

Engineering

&

Management

Site:www.ijaiem.org

Email:

editor@ijaiem.orgVolume 3, Issue 4, April 2014

click and movement of cursor over the desktop, drag and drop, snapshot, Air writing and painting through hand gestures. 3) Prachi A Deshpande1, Prajakta A Patil2 International Journal of Innovative Research in Computer and Communication Engineering (An

ISSN 2319 – 4847

ISO 3297: 2007 Certified Organization) Vol. 3, This paper Describe Accelerometer based

Issue 4, April 2015.

gesture recognition method for Digit Recognition. Accelerometer based gesture recognition is one of the widely implemented method in the recognition scenario. We have implemented a 3D input digital pen which works on triaxial accelerometer to sense human gesture. This digital pen embedded with triaxial accelerometer, microcontroller, RF wireless transmitter module. The triaxial accelerometer measure acceleration signal along all the 3 axis. Accelerated signal process through microcontroller and serially transmitted through RF transmitter which can be received at remote place RF receiver. With the help of MATLAB tool feature vector are generated from received accelerated signal using zero crossing detector(ZCD) & range to recognize

In this paper an MEMS accelerometer mostly based on gesture recognition algorithm and its application are presented. The hardware module consists of a triaxial MEMS accelerometer, microcontroller, and RF wireless transmission module for sensing and collecting accelerations of handwriting and hand gesture trajectories. Users will use this digital pen to write down digits, alphabets& some hand gestures. The accelerations of hand motions deliberate by the accelerometer are transmit wirelessly to a personal computer for trajectory recognition. The trajectory algorithm collected of information variety assortment, signal pre-processing for reconstruct the trajectory to satisfy the collective errors caused by drift of

handwritten

sensors. So, by altering the location of MEMS 2) S. T. Gandhe, Nikita A. Pawar, Mayuri S.

(micro electro mechanical systems) we can

Hingmire, Kalpesh P. Mahajan, Devshri V.

proficient

PatilVolume 5, Issue 1, January 2015 ISSN: 2277

characters and numerical on PC.

to

demonstrate

the

alphabetical

128X International Journal of Advanced Research in Computer Science and Software Engineering. This paper describes the method for

PROBLEM FORMULATION As

the

world

is

modernized,

the

humans to interact with digital world and use the

computers have become smart, but they still use the

computer with just our hand movements. The paper

same keyboard and mouse.

is based on image processing. The camera detects gestures,

and

converts

those

gestures

into

The power to sense what we want to say to a computer using optical devices is the purpose

www.iejrd.in

2


Vol.4 Issue 1

International Engineering Journal For Research & Development of this paper. The paper uses simple Web Cam as a

The paper uses simple Web Cam as a sensing

sensing element to detect the gestures and hand

element

movements.

movements. The camera senses the color bands and

to

detect

the

gestures

and

hand

gestures which are then converted into digital form The camera senses the color bands and gestures which are then converted into digital form by using algorithms.

by

using

algorithms.

These

algorithms

are

implemented using MATLAB programming. In this paper, we mainly focus on Air writing

These algorithms are implemented using

(character recognition), mouse operations like its movement, left click and right click, drag and drop,

MATLAB programming.

snapshot. OBJECTIVES (a) Data-Glove based approaches: Data glove based The main objective of this paper is to have

interface are designed and researched for replacing

an intelligent computer, which can understand

static and fixed keyboard and mouse to have more

human gestures, and to introduce new technology,

natural way of communication as human being

by which humans can interact with computer. This

does by making gestures while communication.

paper deals with the controlling all operations of

But have this, the gesture must be recognized first

mouse such as right click, left click and movement

and thus data glove is used. It provides data based

of cursor over the desktop, drag and drop, snapshot,

on the angular measure of the bones in hand.

Air writing and painting through hand gesture.

Gestures are the first most interactive module for

This paper deals with the controlling all operations of mouse such as right click, left click and movement of cursor over the desktop, drag and drop, snapshot, Air writing and painting through hand gesture. MATLAB is a numerical computing environment,

developed

by

Math

Works.

MATLAB allows the generation, manipulation and processing of signals and images in the form of arrays and Matrices. It contains hundreds of builtin libraries (i.e. toolboxes) for Signal Processing, image processing, bio-matrix, data acquisition, etc.

game control, Wilmot. Komura and Lam have proposed a method to control a small robot walking motion using the data glove. They actually proposed a mapping system between finger motion and 3D characters location. In this proposed paper, we are mapping the finger motion with the 3D mouse pointer to sketch something useful on the computer screen. Basically the mapping is between the real world and the digital world, connecting each other. The data glove used for the experiment is an electronic device with motion

capture

sensors,

i.e.,

flex

sensors,

capturing the movements of each individual finger from physical world and converts them to digital signal using analog-to-digital convertor. This digital signal is then passed to the computer to further process and paints the digital or virtual world, as it is the mimic of physical or real world. (b) Vision

based

approaches:

In

vision

based

approach, Using cameras to recognize hand

www.iejrd.in

3


Vol.4 Issue 1

International Engineering Journal For Research & Development gestures started very early along with the

converter, and a wireless transceiver. The triaxial

development of the first wearable data gloves.

accelerometer measures the acceleration signals

There were many hurdles at that time in

generated

interpreting camera based gestures. Coupled with

microcontroller collects the analog acceleration

very low computing power available only on main

signals and converts the signals to digital ones via

frame computers, cameras offered very poor

the A/D converter. The wireless transceiver

resolution along with colour inconsistency. The

transmits the acceleration signals wirelessly to a

theoretical developments that lead to identifying

personal computer (PC). The output of any axis is

skin segmentation were in its infancy and were not

analog voltage which is directly proportional to the

widely recognized for its good performance that

acceleration in that axis. Acceleration values can be

we see today. Despite these hurdles, the first

positive, negative or zero. So, the output voltage

computer vision gesture recognition system was

has a zero bias output. The output given at this

reported in 1980s. (c) Coloured markers approach:

point means zero acceleration in that particularaxis.

In this approach, the human hand used to wear

So, the zero point voltage is greater than output

marked gloves or coloured markers with some

voltage, it indicates the negative acceleration. The

colours to direct the process of tracking the hand

accelerometer works with three modes, they are

and locating the palm and fingers. It provides the

Standby mode, auto sleep mode and Low power

ability to extract geometric features necessary to

mode. The microcontroller integrates a high-

form hand shape .There might be different colours

performance

of colour glove, where three different colours are

microcontroller unit (MCU) on a signal chip. The

used to represent the fingers and palms, where a

output signals of the accelerometer are sampled at

wool glove was used. The MIT-LED glove was

100 Hz by the 10-bit A/D converter. Then, all the

developed at the MIT Media Laboratory in the

data sensed by MEMS are transmitted to PC

early 1980s as part of a camera-based LED system

wirelessly by an RF transceiver, at 2.4- GHz

to track body and limb position for real-time

transmission band with 1-Mb/s transmission rate.

computer graphics animation. A camera sitting in

The overall power consumption of the digital pen

front of the user could capture number of LEDs as

circuit is 30 mA at 3.7 V.

by

a

user’s

10-bit

A/D

hand

motions.

converter

and

The

8-b

they were studded on the glove. The different illumination patterns for different gestures that could be interpreted by a computer. However, the performance was poor due to occlusions and the variations of any gesture performed by different users. One of the first instances of gesture recognition using a glove with finger tip markers was reported by Davies et al.

PROPOSED SYSTEM

Figure1: Block diagram of proposed system

The portable device consists of a triaxial accelerometer microcontroller with a 10-b A/D

www.iejrd.in

4


International Engineering Journal For Research & Development

Vol.4 Issue 1

This system we are using triaxial-accelerometer, a

reality,” IEEE Trans. Ind. Electron., vol. 54, no. 4,

microcontroller (with A/D converter), and a

pp. 2174–2189, Aug. 2007.

wireless

transceiver

(RF).

The

triaxial

accelerometer measures the acceleration signals generated

by

a

user’s

hand

motions.

The

microcontroller collects the analog acceleration Signals and converts the signals to digital ones via the A/D converter. The wireless transceiver

[6] E. Sato, T. Yamaguchi, and F. Harashima, “Natural interface using pointing behavior for human–robot gestural interaction,” IEEE Trans. Ind. Electron., vol. 54, no. 2, pp. 1105–1112, Apr. 2007.

transmits the acceleration signals wirelessly to a

[7] Y. S. Kim, B. S. Soh, and S.-G. Lee, “A new

personal computer (PC).The acceleration signals

wearable input device: SCURRY,” IEEE Trans.

measured from the triaxial accelerometer are

Ind. Electron., vol. 52, no. 6, pp. 1490–1499, Dec.

transmitted to computer via the wireless module.

2005.

Bibliography:

[8] Miss Leenamahajan ,Prof G,.A.Kulkarni ,”

[1] Jeen-Shing Wang and Fang-Chen Chuang, “An Accelerometer-Based

Digital

Pen

With

a

Trajectory Recognition Algorithm for Handwritten

Digital Pen for Handwritten Digit and Gesture Recognition

Using

Trajectory

Recognition

Algorithm Based On Triaxial Accelerometer.

Digit and Gesture Recognition,” IEEE Sens. J., vol. 59, no. 07, pp. 1543–1551, July. 2012. [2] Z. Dong, U. C. Wejinya, and W. J. Li, “An optical-tracking calibration method for MEMSbased digital writing instrument,” IEEE Sens. J., vol. 10, no. 10, pp. 1543–1551, Oct. 2010. [3] J. S.Wang, Y. L. Hsu, and J. N. Liu, “An inertial-measurement-unit-based trajectory

reconstruction

pen

algorithm

with

a

and

its

applications,” IEEE Trans. Ind. Electron., vol. 57, no. 10, pp. 3508–3521, Oct. 2010. [4] S.-H. P. Won, W. W. Melek, and F. Golnaraghi, “A Kalman/particle

filter-based position and

orientation estimation method using a position sensor/inertial measurement unit hybrid system,” IEEE Trans. Ind. Electron., vol. 57, no. 5, pp. 1787–1798, May 2010. [5] A. D. Cheok, Y. Qiu, K. Xu, and K. G. Kumar, “Combined

wireless

hardware

and

real-time

computer vision interface for tangible mixed

www.iejrd.in

5


Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.