IRJET- Convenience Improvement for Graphical Interface using Gesture Detection
0 likes32 views
This document discusses a proposed system for improving graphical user interfaces using hand gesture detection. The system aims to allow users to access information from the internet without using input devices like a mouse or keyboard. It uses a webcam to capture images of hand gestures, which are then processed using techniques like skin color segmentation, principal component analysis, and template matching to recognize the gestures. The recognized gestures can then be linked to retrieving specific data from pre-defined URLs. An evaluation of the system found it had an accuracy rate of 90% in real-time testing for retrieving data from 10 different URLs using 10 unique hand gestures. The proposed system provides a more convenient interface compared to traditional mouse and keyboard methods.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 3248
Convenience Improvement for Graphical Interface
Using Gesture Detection
Dnyandev Sopan Musale1, Prof. Shaikh I.R.2
1Student ME, Department of Computer Engineering, SND College of Engineering and Research Center, Yeola.
2HOD, Department of Computer Engineering, SND College of Engineering and Research Center, Yeola.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - the way for getting data from web such as
weather condition, market condition, sports news, financial
information and other information from different newspaper,
Television and Internet. Now a day people interact with the
system through graphical user interface which uses input
devices like keyboard and mouse which is inconvenient and
time consuming. To overcome this issue we design convenient
GUI using hand gesture for getting data or information
without using input devices like mouse and keyboard. The
main aim of the proposed system reduce the disadvantages of
existing system for accessing data or information from World
Wide Web (internet) using hand gesture. In this we passes
trainee images data captured by web cam to the system for
processing then hand gesture get recognized by the system
and our system also tied with world wide web so we are able
to access required information or data from web and our
system cant required input mechanism
Key Words: Gesture Recognition, Hand Gesture, Hand
Segmentation, Image Acquisition, and PCA.
1. INTRODUCTION
Gesture recognition is nothing but Human computer
interaction (HCI) [7]. We can also define Gestures to convey
meaningful information by the body or physical action from
user and process of recognition of body or physical action
called Gesture recognition. Gesturesare dividedintwotypes
static and dynamic [8].Hand gesture is used in wide area by
computer vision and machine eye with development of
different tools and realization of virtual environment. inthis
paper we present human computer interaction through
convenience graphical interface using gesture detection.
When we study the hand gesture recognition it is changes
from person to person so result may be changed with
different as texture and skin tones changes. It is universally
accepted that every person has same hand and figure count
as normal consideration. The main aim of the proposed
system reduce the disadvantages of existing system for
accessing data or information from World Wide Web
(internet) using hand gesture. In this we passes trainee
images data captured by web cam to the system for
processing then hand gesture get recognized by the system
and our system also tied with world wide web so weareable
to access required information or data from web and our
system without keyboard and mouse.
2. LITERATURE SURVEY
In early days Gesture Recognition becomes very prevail
process. For determining hand gesture different gesture
recognition technique are used. And every technique has its
own positive and negative consequences. The oldtechnology
is wired technology in which user get connected with
computer system through wire. But this technology has
several limitation ofthelengthofwire that’swhyusercannot
freelymovein room. The data glovesor instrumentedgloves
also called electronics gloves is the example of wire
technology [1][2]. Sensors are required for creating
electronics gloves for tracking Finger position orientation
and hand location. These instrumented gloves provide best
result but because of expensive cannot use in common
application. So we get replace electronics gloves by optical
markers this is one way to overcome expensiveness. Optical
markers produce infra-red light and this light reflect on
screen to getting information about tips of finger or hand
location.Optical marker also providesgoodresultbutagainit
hassome prosand cons i.e. complex configuration. After that
advanced technique get introduce called image based
technique in which image features like color, texture get
processed. We workwiththese featuresoftheimageforhand
gesture recognition. ForStudy Hand gesture andrecognition
system can be divided into different parts hand detection,
hand recognition and data retrieval from web.
2.1. Hand Detection
In Hand detection phase input is taken in the form of images
or video stream captured by webcam after that theseimages
are passed to the system for image processing and then with
take precaution of time consuming. For hand detection
multiple methods or approaches are used. The easy way is
taking image as input and finding skin color region, butitisa
difficult task as it has background color detection and
another body parts as image skin color is detected by using
skin color detection algorithm.
2.2. Hand Recognition
Hand gesture recognition deals with features detection and
Second parameter estimation model calculation. In features
detection extract featuresfrom imageswhichareusefulafter
that from this features calculate parameter by parameter
estimation model. In Hand gesture recognitionsegmentation
is done as there are unwanted background objects. Forhand
locating segmentation based skin color method is applied.](https://image.slidesharecdn.com/irjet-v5i3766-190204040126/85/IRJET-Convenience-Improvement-for-Graphical-Interface-using-Gesture-Detection-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 3250
ACKNOWLEDGEMENT
I have great pleasure in expressing my sincere thanks to Dr
H. N. Kudal Principal, S. N. D. College of Engineering, Yeola
for providing all the necessary facilities. I wish toexpressmy
great thanksto my guide Prof. I. R. Shaikh Head of Computer
Engg.Department, encourage me throughout the project. I
wish to express my sincere thanks to Co-ordinator, post
graduate progrmme Prof. V.N. Dhakane Computer
Engg.Department for his valuable suggestions andguidance.
I am grateful to the staff members of the Department of
Computer Engg. for their stretching hands of the successful
completion of this paper work. At the last but not least, I am
thankful to my parent whohad encouragedinspiredmewith
their blessings.
REFERENCES
[1] [1] Yue Zhao, Yunda Liu, Min Dong(*), Sheng Bi”Multi-
Feature Gesture Recognition Based on Kinect”.The
6th Annual IEEE International Conference on Cyber
Technology in Automation, Control and Intelligent
systems June 19-22, 2016, Chengdu, China
[2] [2] Mandeep Kaur Ahuja ”Hand Gesture Recognition
Using PCA” IJCSET(www.ijcset.net) — July 2015 — Vol
5, Issue 7,267-271
[3] [3] Panwar, M. ”Hand gesture recognition based on
shape parameters.” International Conference on
Computing, Communication and Applications IEEE,
2012:1-6.
[4] [4] Sushma Laxman Wakchaure, Ganesh Dnyandev
Ghuge, Dnyandev Sopan Musale ”A Frequently used
Hand Gesture Recognition System for Daily Information
Retrieval from Internet International Journal of
Scientific Engineering Research, Volume 6, Issue 3,
March-2015 ISSN 2229 -5518
[5] [5] Haitham Hasan, Sameem Abdul-Kareem, Human
computer interaction using vision-based hand gesture
recognition systems: a survey,, Neural Comput
Application,2013.](https://image.slidesharecdn.com/irjet-v5i3766-190204040126/85/IRJET-Convenience-Improvement-for-Graphical-Interface-using-Gesture-Detection-3-320.jpg)
IRJET- Convenience Improvement for Graphical Interface using Gesture Detection
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 3248 Convenience Improvement for Graphical Interface Using Gesture Detection Dnyandev Sopan Musale1, Prof. Shaikh I.R.2 1Student ME, Department of Computer Engineering, SND College of Engineering and Research Center, Yeola. 2HOD, Department of Computer Engineering, SND College of Engineering and Research Center, Yeola. ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - the way for getting data from web such as weather condition, market condition, sports news, financial information and other information from different newspaper, Television and Internet. Now a day people interact with the system through graphical user interface which uses input devices like keyboard and mouse which is inconvenient and time consuming. To overcome this issue we design convenient GUI using hand gesture for getting data or information without using input devices like mouse and keyboard. The main aim of the proposed system reduce the disadvantages of existing system for accessing data or information from World Wide Web (internet) using hand gesture. In this we passes trainee images data captured by web cam to the system for processing then hand gesture get recognized by the system and our system also tied with world wide web so we are able to access required information or data from web and our system cant required input mechanism Key Words: Gesture Recognition, Hand Gesture, Hand Segmentation, Image Acquisition, and PCA. 1. INTRODUCTION Gesture recognition is nothing but Human computer interaction (HCI) [7]. We can also define Gestures to convey meaningful information by the body or physical action from user and process of recognition of body or physical action called Gesture recognition. Gesturesare dividedintwotypes static and dynamic [8].Hand gesture is used in wide area by computer vision and machine eye with development of different tools and realization of virtual environment. inthis paper we present human computer interaction through convenience graphical interface using gesture detection. When we study the hand gesture recognition it is changes from person to person so result may be changed with different as texture and skin tones changes. It is universally accepted that every person has same hand and figure count as normal consideration. The main aim of the proposed system reduce the disadvantages of existing system for accessing data or information from World Wide Web (internet) using hand gesture. In this we passes trainee images data captured by web cam to the system for processing then hand gesture get recognized by the system and our system also tied with world wide web so weareable to access required information or data from web and our system without keyboard and mouse. 2. LITERATURE SURVEY In early days Gesture Recognition becomes very prevail process. For determining hand gesture different gesture recognition technique are used. And every technique has its own positive and negative consequences. The oldtechnology is wired technology in which user get connected with computer system through wire. But this technology has several limitation ofthelengthofwire that’swhyusercannot freelymovein room. The data glovesor instrumentedgloves also called electronics gloves is the example of wire technology [1][2]. Sensors are required for creating electronics gloves for tracking Finger position orientation and hand location. These instrumented gloves provide best result but because of expensive cannot use in common application. So we get replace electronics gloves by optical markers this is one way to overcome expensiveness. Optical markers produce infra-red light and this light reflect on screen to getting information about tips of finger or hand location.Optical marker also providesgoodresultbutagainit hassome prosand cons i.e. complex configuration. After that advanced technique get introduce called image based technique in which image features like color, texture get processed. We workwiththese featuresoftheimageforhand gesture recognition. ForStudy Hand gesture andrecognition system can be divided into different parts hand detection, hand recognition and data retrieval from web. 2.1. Hand Detection In Hand detection phase input is taken in the form of images or video stream captured by webcam after that theseimages are passed to the system for image processing and then with take precaution of time consuming. For hand detection multiple methods or approaches are used. The easy way is taking image as input and finding skin color region, butitisa difficult task as it has background color detection and another body parts as image skin color is detected by using skin color detection algorithm. 2.2. Hand Recognition Hand gesture recognition deals with features detection and Second parameter estimation model calculation. In features detection extract featuresfrom imageswhichareusefulafter that from this features calculate parameter by parameter estimation model. In Hand gesture recognitionsegmentation is done as there are unwanted background objects. Forhand locating segmentation based skin color method is applied.
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 3249 In this accuracy can be maintained because of gesture parameter features are properly selected by recognition process. After selection of hand gesture system isable to get data from web or internet from respective gesture. 2.3. Data Retrieval In information or data retrieval phase the data can be retrieved from internet according to provide gesture. User fixes URL for per gesture in a database and when gestures are recognized according that gesture users call that URL from database. In this way informationcanbeaccessedusing gestures from web. 3. Proposed System Fig -1: System architecture 3.1. Image Acquisition Images are acquired using the 13 megapixel real-aperture camera in controlled background as well as by varying the lightning conditions. 3.2. Hand Segmentation The main and basic step in hand gesture recognition is to segment the hand from the whole image so that it can be utilized for recognition. In our proposed color skin color segmentation is applied to segment the hand.Asskincolorof different person can vary and background image can also contain the skin pixels so after skin color model Otsu Thresholding is applied to remove the background. Conversion from RGB to YCbCr: The proposed skin color segmentation in applied to YCbCr color space. 3.2. Gesture Recognition One of the important technique of recognition is template matching in which a template to recognize is available andis compared with already stored template. In our approach PCA method for feature extraction and matching is used. Principal Component Analysis: PCA is used to reduce the dimensionality of the image while preserving much of the information. It is the powerful tool for analyzing the data by identifying patterns in the dataset and reduces the dimensions of the dataset such that maximum variance in the original details visible in reduced data. PCA wasinvented by Karl Pearson in 1901. It works by converting set of correlated variables to linearly uncorrelated variable called principal components. Principal components are calculated by computing Eigen vectors of covariance matrix obtained from the group of hand images. The highest M eigenvectors contains the maximum variance in the original data. These principal components are orthogonal to each other and the first component is in the direction of greatest variance. 4. SYSTEM ANALYSIS We required laptop with dual core having 2GB RAM with webcam. Using webcam images are capturedwithresolution 640 x 480.We tested proposed system with 10 URLs with10 different hand gestures. We determine 10 gestures, 10 images taken for each gesture means we have 100 images with eliminating background disturbance and tested the accuracy rate in real time environment as shown in following tables Table -1: Hand Reorganization Result for data retrieval Hand Reorganization Result Gesture Input images Successf ul cases Recognition Rate % 1 10 8 80 2 10 9 90 3 10 9 90 4 10 10 100 5 10 8 80 6 10 10 10 7 10 9 90 8 10 9 90 9 10 10 90 10 10 9 90 ALL 100 90 90% 3. CONCLUSION The proposed system implemented convenience graphical interface using hand gesture detection which is used to getting data from web. It is cheaper ascompare to touchpad. We are getting data from web successfully by this system.As we tested the accuracy rate in real time environment is also good i.e. 90%and good fluency of controlling thesystem.For future work we can increase the hand gesture recognition accuracy rate.
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 3250 ACKNOWLEDGEMENT I have great pleasure in expressing my sincere thanks to Dr H. N. Kudal Principal, S. N. D. College of Engineering, Yeola for providing all the necessary facilities. I wish toexpressmy great thanksto my guide Prof. I. R. Shaikh Head of Computer Engg.Department, encourage me throughout the project. I wish to express my sincere thanks to Co-ordinator, post graduate progrmme Prof. V.N. Dhakane Computer Engg.Department for his valuable suggestions andguidance. I am grateful to the staff members of the Department of Computer Engg. for their stretching hands of the successful completion of this paper work. At the last but not least, I am thankful to my parent whohad encouragedinspiredmewith their blessings. REFERENCES [1] [1] Yue Zhao, Yunda Liu, Min Dong(*), Sheng Bi”Multi- Feature Gesture Recognition Based on Kinect”.The 6th Annual IEEE International Conference on Cyber Technology in Automation, Control and Intelligent systems June 19-22, 2016, Chengdu, China [2] [2] Mandeep Kaur Ahuja ”Hand Gesture Recognition Using PCA” IJCSET(www.ijcset.net) — July 2015 — Vol 5, Issue 7,267-271 [3] [3] Panwar, M. ”Hand gesture recognition based on shape parameters.” International Conference on Computing, Communication and Applications IEEE, 2012:1-6. [4] [4] Sushma Laxman Wakchaure, Ganesh Dnyandev Ghuge, Dnyandev Sopan Musale ”A Frequently used Hand Gesture Recognition System for Daily Information Retrieval from Internet International Journal of Scientific Engineering Research, Volume 6, Issue 3, March-2015 ISSN 2229 -5518 [5] [5] Haitham Hasan, Sameem Abdul-Kareem, Human computer interaction using vision-based hand gesture recognition systems: a survey,, Neural Comput Application,2013.