IRJET- Finger Gesture Recognition using Laser Line Generator and Camera

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 06 Issue: 04 | Apr 2019 www.irjet.net p-ISSN: 2395-0072
© 2019, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 2802
Finger Gesture Recognition Using Laser Line Generator and Camera
Atharva Deshpande1, Chaitali Merinde2, Nikita Padwal3, Pragati Khedekar4,
Dnyanoba Chitre5
1,2,3,4B.E,COMPUTER ENGINEERING, TERNA ENGINEERING COLLEGE, NERUL NAVI MUMBAI
5PROFESSOR, COMPUTER ENGINEERING, TERNA ENGINEERING COLLEGE, NERUL, NAVI MUMBAI
----------------------------------------------------------------------***---------------------------------------------------------------------
Abstract –This paper presents theinformationaboutfinger
gesture recognition using laser line generator and camera.
Gesture recognition relates to perceiving important aspect of
movement by a human, including the hands, arms, face, head,
as well as body. It is of most extreme significance in designing
an insightful andefﬁcienthuman– computerinterface. Gesture
based interactions are becoming more and more popular in
today’s world. The project intends todevelopasystemthatcan
recognize gestures which can be used as an input commandto
interact with the PC/laptop which can be applied to certain
applications on that system. The method involves following
steps, namely-image acquisition, image pre- processing,
gesture detection, and gesture recognition.
Keywords -Gesture, Human-Machine interaction,Laserline,
Image acquisition, Feature extraction, Gesture matching.
1. INTRODUCTION
Today’s era technology is developing rapidly and new
innovations are done, the need for human and machines
interaction also increases. So to meet the need of interaction
between human and machines gesture recognition systems
are developed. Innovation of such system have eliminated
the use of mouse for interacting with computer.
Gesture is a form of nonverbal communication which
involves movement of a part of the body, especiallythe hand
usually to express an idea. While communicating with each
other, we make use of speech,gesturesandbodymovements
to convey information[2].Likewise while communicating
with computers we make use of input devicessuchasmouse
or keyboard. But this way of communication is not natural.
So in order to make the interaction natural gesture
recognition systems are developed. Driven by this subtle
objective of making hand one of the main modal for
interaction between human and computer huge amount of
activities have been giventohandgesturerecognition.So far,
the greater part of research work is highlighted on
recognition from images and videos due to popularity of
cameras .The ongoing advancementindepthsensorssuchas
Microsoft’s Kinect device has created another dimension of
energy in hand gesture recognition. In computer vision, the
hand gesture recognition can be treated as a combinationof
three sub parts hand. detection, tracking the hand and
gesture recognition[1]. For deaf and mute people hands are
important for communication, so hand gestures are vital for
communication in sign language. The existing real life
applications of gesture based human-machine interaction
are: in controlling robots, in gaming sector, translation of
body and sign language and in controlling machines.
The proposed systemhasbeen emphasizedondevelopingan
efficient scheme that can accomplish hand gesture
recognition without introducing any training related
overheads. This system will work as one of the futuristic of
Artificial intelligence and computer vision with user
interface. The main priority of the system is to be simple,
easy and user friendly withoutmakinganyspecial hardware.
All computation will occur on single PC or workstation. Only
special hardware will be used to digitize the image-Web
camera and Laser line.
2. RELATED WORK
There are many gesture recognition techniques developed
for recognizing various gestures performed by user.
Following works has been analyzed by us fordevelopingour
gesture recognition system.
In 2017, Athiya Marium et.al [1] presented a Hand Gesture
Recognition using Webcam which uses built in functions for
every gesture provided by thePyAutoGUImodule.Itiscoded
in Python and uses OpenCV library. The image pre-
processing techniques involved are color filtering,
smoothing, and thresholding. The algorithmimplemented in
this paper detects the gesture based on the number of
contours that are visibleandtherebyperformsthe necessary
operation related to gesture.
Ann Abraham Babu et al. [7] proposed another gesture
recognition technique using contour analysis In the first
phase, the input image is acquired with the help of a camera.
In the second phase, the skin color of hand regionisdetected
using HSV color space and morphological operationssuchas
erosion and dilationareperformedtoremove noisefollowed
by smoothing and thresholding of hand image. In Feature
extraction phase, contours of hand image are detected.
Finally, Gesture recognitionphaseincludesrecognizinghand
gestures using contour analysis by comparing Auto-
Correlation Function (ACF) amongst thecontoursandifthey
are close, then calculate Inter-Correlation Function (ICF) to
truly determine similarity. Each recognized gesture is
assigned with the corresponding action.

A. Kurakin et al.[8] proposed a system which is evaluated on
a challenging dataset of twelve dynamic American Sign
Language(ASL) gestures.Inthisa methodcalledactiongraph
is used for back-end classifier.
3. METHODOLOGY
The following figure mentions a basic idea of the system we
have proposed.
Figure 1: Block diagram of proposed system.
Our gesture recognition system includesthefollowingsteps:
1) Image acquisition: This step involves capturing
images frame by frame using a webcam.
2) Image pre-processing: In this the images which are
captured by webcam go through some image pre-
processing process which involves color filtering,
smoothing and thresholding.
3) Gesture detection: This step involvesmethod which
extracts the feature from the image. A laser line is
used
4) on which finger gesture is performed and the
irregularities in the laser line are detected. Using
the irregularities features are extracted.
5) Gesture recognition: This step involves recognition
of the finger gesture with the help of extracted
features. After recognition related operation which
is assigned to the action is performed.
4. TECHNIQUES
Step 1: Read and write bitmap images.
In this step, we have developedanalgorithm whichreadsthe
bitmap images along with their header and also writes the
data to another file to create the exact copy of the bitmap
image. This will be useful for capturing the gestures
provided by the user and then doingimagepreprocessing on
that image and then returning the output to the user.
Step 2: Implement a routine which detects the presence of
fingers based on color.
In this task, we have developed an algorithm to detect
whether a finger is present or not in an image. This will help
us to identify if the hand is present and if present it will
perform the further functions.
1) Implement algorithm to covert rgbimageintograyscale
image.
Conversion formula used is
gray[i][j]=(pixel[i][j].b*0.3)+(pixel[i][j].g*0.59)+(pixel[i][j].r
r*0.11);
Figure 2: input-output
2) Implement a routine which removes unwanted objects
from the image.
Here we used technique similar to Grassfire transform to
remove the noise and to keep only that data which we want
for recognition purpose. The algorithm checks the
neighbouring 8 pixel of a pixel which we have implemented
using recursion. If the number of pixels are less than a
threshold count we consider it as noise and then convert it
value to white. The lines which are hidden i.e observable
from down are considered.
3) The discontinuity in the lines in output image indicates
the finger.

Step 3: Implement a routine which detects the presence of
laser line and finds it’s orientation.
Inthis, wehavedevelopedan algorithmtodetectthepresence
of laser line and it’s orientation in the image. The algorithm
first converts the RGB image into grayscale and then checks
for pixels with value 0.Then that pixels are saved which
indicates the presence of laser line.
Figure 5: Laser Line
Task 4: Interface a webcam and perform the fingerdetection
only along the laser line.
In this , we have developed an algorithm in which alignment
of finger along the laser line will be detected. If the finger is
not aligned properly then the gesture recognition will not
begin.
Task 5: Based on the Lookup Table (LUT) react to the user’s
gesture.
After this, an algorithm to react to the extracted gesture is
developed. Related operation will be performed.
5. EXAMPLE
Figure 6: Input gesture
If this is the gesture done by user then the opera browser
will be opened on your laptop/desktop.
Figure7: Output
6. CONCLUSION
The proposed system will control the computer application
with the help of finger gestures. The method proposed here
will successfully create a finger gesture recognition system
using laser line generator and camera, which will be able to
recognize gestureperformed byuserandaccuratelyperform
the respective function. Our system will eliminate the use of
mouse and make the human-machine interaction simpler
through gestures.
7. HARDWARE
Figure 8: Laser line generator
Figure 9: Webcamera
8. REFERENCES
[1] Athiya Marium,Deepthi Rao, Divina Riya Crasta, Kavya
Acharya, Rio D’Souza, “Hand Gesture Recognition using
Webcam”, American Journal of Intelligent Systems
2017,7(3): 90-94.
[2] Dhanashree Pannase, “To Analyse Hand Gesture
Recognition For Electronic Device Control: Review”,

International Journal of Advance Research in Computer
Science and Management Studies.
[3] Anchit P.Narwadkar, Mhalsakant.M.Sardeshmukh,
“Human Computer Interaction by Gesture Recognition”,
IOSR Journal of Electronics and Communication
Engineering, e-ISSN: 2278-2834, p- ISSN:2278-8735.
[4] Vinod Kumar Kurmi, Lakshmi Shraya Kopulla, Nandini
Kumari Roma, Siddharth J.Singh, Dr. K.S.Venkatesh,
“2D and 3D Vision of Robotics”.
[5] Stephane Perrin, Alvaro Cassinelli and Masatoshi
Ishikawa, “Gesture Recognition Using Laser-Based
Tracking System”, University of Tokyo,Ishikawa
Hashimoto Laboratory.
[6] Kenji Oka, Yoichi Sato, Hideki Koike, “Real-Time
Fingertip Tracking and GestureRecognition”,University
of Tokyo.
[7] Ann Abraham Babu, Satishkumar Varma, Rupali
Nikhare, “Hand Gesture Recognition System for Human
Computer Interaction using Contour Analysis”,IJRET,e-
ISSN: 2319-1163, p-ISSN: 2321-7308.
[8] A.Kurakin, Z. Zhang, Z. Liu, “A Real Time System For
Dynamic Hand Gesture Recognition With a Depth
Sensor”, 20th European Signal Processing
Conference(EUSIPCO 2012), Bucharest, Romania,
August 27 -31, 2012.

IRJET- Finger Gesture Recognition using Laser Line Generator and Camera

More Related Content

What's hot (20)

Similar to IRJET- Finger Gesture Recognition using Laser Line Generator and Camera (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Finger Gesture Recognition using Laser Line Generator and Camera