SlideShare a Scribd company logo
Invention Journal of Research Technology in Engineering & Management (IJRTEM)
ISSN: 2455-3689
www.ijrtem.com Volume 1 Issue 4 ǁ June. 2016 ǁ PP 01-04
| Volume 1| Issue 4 | www.ijrtem.com | June 2016| 1
FPGA-Based Contact Lenses Try-On System
Chen-Chien Hsu, Hsiang-Yu Huang, Man-Wei Huang, Wei-Yen Wang, and Chiang-Heng Chien
(Department of Electrical Engineering, National Taiwan Normal University, Taiwan, R.O.C.)
ABSTRACT : A hardware/software (HW/SW) co-design approach developing a contact lenses try-on system via the use of the Field
Programmable Gate Array (FPGA) [1] is proposed in this paper. To achieve an interactive user-friendly environment, the menu of
contact lenses and the result that shows howit looks when wearing the contact lens are displayed on the LCD touch panel directly. After
capturing the user’s image via CMOS sensors, image processing is employed to determine user’s irises from the image. A particle filter
algorithm is then introduced to track the irises so that the contact lenses chosen by the user can be overlapped on the image to provide
a natural examination of the effect of the contact lenses try-on system. Experimental results show good performances of the proposed
system.
Keywords: FPGA, Eye Tracking, Particle Filter, Nios II, Image Processing
1. Introduction
Contact lenses, a thin lens placed directly on the surface of the eyes, are regarded as a medical device to enhance visual
abilities. Many people wear color cosmetic contact lenses for aesthetic reasons nowadays. To meet the consumer’s demand, more and
more contact lenses manufactures produce color cosmetic contact lenses. However, it is difficult to decide preferable contact lenses since
consumers are often not allowed to try it on. This is because the costs of color cosmetic contact lenses are relatively high, and only a few
manufactures provide samples for consumers. To solve this problem, this research develops a system that allows consumers to virtually
try on color cosmetic contact lenses without physically wearing it so that consumers can easily choose their preferable ones. To allow a
natural presentation of the contact lenses, eye tracking is one of the key points in the proposed contact lenses try-on system. The white
part of the eye is sclera, which interferes less during the course of tracking. The black part is iris, which is the main object to be tracked.
There are different light sources for use in eye tracking, such as infrared light and natural light. If infrared light is used, little effort is
required for image processing. However, there is a safety concern in which infrared light might potentially damage human’s eyes.
Therefore, the desired natural light source is used, where a particle filter [2][3] algorithm is developed to track the exact position of the
iris after the image has been captured. HSV color space is used to remove the shadow caused by natural light while a 5x5 median filter
is used to remove impulsive noise. Binarization is also very important to identify the object of interest in the image. Finally, dilation and
erosion are used to reconstruct and decompose the image. The development platform of the contact lenses try-on system is based on
Altera’s DE2 development board, which provides high speed SSRAM, SDRAM with large data storage, uClinux operating system, the
Cyclone II, and SoPC Builder’s logical module. Altera also provides devices such as COMS sensor to capture images and LCD touch
panel to display the menu and the results.
2. Proposed Contact Lenses Try-On System
1.1 Design Architecture
Figure 1 Hardware Design of the proposed contact lenses try-on system
FPGA-Based Contact Lenses Try-On System
| Volume 1| Issue 4 | www.ijrtem.com | June 2016| 2
Fig. 1 shows the hardware design of the proposed contact lenses try-on system. After the CMOS sensor receives data from the
image capturing user’s face, the image is gone through image processing for eye tracking. The menu of the contact lenses is then shown
on the LCD touch panel under the control of CMOS Master Controller, NIOS II processor, and LTM Master Controller. Finally,
Quatrus II software by Altera [4] is used to integrate the system.
1.2 Overall Flow Chart
Fig. 2 (a) shows the flowchart of this system. First, the menu of contact lenses try-on system is displayed on the LCD touch
panel. Then, the user touches the panel to choose what kind of contact lenses they would like to try on. As the user had chosen their
preferable contact lenses, D5M will capture the user’s image. After that, image processing is used to distinguish the facial part from the
background for eye tracking. The location of the iris is tracked via particle filter as a consequence. Finally, the image of the contact
lenses chosen by the user is overlapped on the image and the result is presented on the LCD board.
(a) (b)
Figure 2 (a) Flow chart of the proposed contact lenses try-on system. (b) Flow chart of the particle filter algorithm for tracking.
1.3 Median Filter
Since an image could contain a lot of noises that could thereby affect the performance of the system. Therefore, median filer [5]
is introduced to remove the noise of the image. According to the experimental results, a size of 5x5 mask is suitably used for the median
filter in the proposed system.
1.4 Morphology
After the image is processed through color space conversion and median filter, binarization can make the object more
obvious. However, the result might be incomplete due to the light or the noise. Therefore, morphology [6] is required to track the
location of the center of the object. Morphology[6] includes dilation, erosion, opening, and closing. Dilation and erosion are used in this
paper, where dilation refills the losing part of the iris while erosion removes the noise around eyes. Morphology completes the shape of
the iris.
1.5 Particle Filter
Fig. 2 (b) shows the flowchart of particle filter algorithm for tracking. First, weight assignment deals with calculations of
weights valuing each particle. The larger the value is, the higher the possibilityfor this particle to be the location of the iris. Tournament
selection [7] is employed so that particles with the top five highest weights are chosen to estimate the location of the iris. Then, a
resampling procedure is used to eliminate particles with lower weights and replicate the particles with higher weights. After that, since
the object might move and slightly change by the time goes, prediction is required to estimate the location of each particle at the next
time. Fig. 3 shows the process of eye tracking by particle filter, where the yellow dots are particles generated by particle filter. Through
iterations, an optimal location in the estimation of the iris is obtained thereafter. It is marked in red in the figure.
FPGA-Based Contact Lenses Try-On System
| Volume 1| Issue 4 | www.ijrtem.com | June 2016| 3
Figure 3 The process of eye tracking by using particle filter algorithm.
3. Experimental Results
The proposed contact lenses try-on system is implemented on a Altera’s DE2-70 development board as shown in Fig. 4. Users
can choose the contact lenses they would like to try on from the menu shown in Fig. 5 (a). In order to achieve a more natural result, we
adjust the display by comparing the color of the iris and the background illumination in that environment shown in Fig. 5 (b).
Figure 4 The Altera’s DE2-70 development board.
(a) (b)
Figure 5 (a) Contact lenses menu for users to choose. (b) The result of the proposed contact lenses try-on system.
4. Conclusion
The proposed contact lenses try-on system is a low cost, simple operation, and user-friendly platform, which replaces the high
cost contact lenses sample and provides a more efficient way for consumers to try on their preferable color contact lenses. Because
contact lenses images are stored in SD card provided by the DE2, new styles of contact lenses can be added anytime when they are
available for consumers. Therefore, the proposed system has high flexibilities for both the sellers and consumers aspects.
FPGA-Based Contact Lenses Try-On System
| Volume 1| Issue 4 | www.ijrtem.com | June 2016| 4
5. Acknowledgements
This research is partially supported by the “Aim for the Top University Project” and “Center of Learning Technology for
Chinese” of National Taiwan Normal University (NTNU), sponsored by the Ministry of Education, Taiwan, R.O.C. and the
“International Research-Intensive Center of Excellence Program” of NTNU and Ministry of Science and Technology, Taiwan, under
Grants no. MOST 104-2911-I-003-301 and MOST 103-2221-E-003-027.
REFERENCES
[1]. Oetken, S. Wildermann, and J. Teich, A Bus-based SoC Architecture for Flexible Module Placement on Reconfigurable FPGAs: Int. Conf. on
[2]. Field Programmable Logic and Applications (FPL), Milano, 2010, 234-239.
[3]. S. Fazli, H. Moradi, and P. Hamed Bouzari, Particle Filter based Object Tracking with Sift and Color Feature: 2nd Int. Conf. on Machine
Vision, Dubai, 2009, 89-93.
[4]. D. Xu, L. Huang, and C. Liu, Object Tracking using Particle Filter based on Color Correlogram:2nd Int. Symposium on Intelligent Information
Technology Application, Shanghai, 2008, 608-612.
[5]. Altera Corporation, Quarts II Handbook (Altera Corporation, 2004).
[6]. T. Huang, G. Yang, and G. Tang, A fast two-dimensional median filtering algorithm, IEEE Trans. on Acoust., Speech, and Signal Processing,
27(1), 1979, 13–18.
[7]. O. Dgforges, and N. Normand, A generic systolic processor for real time grayscale morphology: Int. Conf. on Acoustics, Speech, and Signal
Processing, Istanbul, 2006, 3331-3334.
[8]. Z. Michalewicz, Genetic Algorithm + Data Structure = Evolution Programs, Third Ed., Springer, 1996.

More Related Content

What's hot

Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network  Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network
ijcga
 
Construction of sine and cosine hologram of brain tumor image
Construction of sine and cosine hologram of brain tumor imageConstruction of sine and cosine hologram of brain tumor image
Construction of sine and cosine hologram of brain tumor image
eSAT Journals
 
Interactive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkInteractive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor network
ijcga
 
ESPI - Project Report
ESPI - Project Report ESPI - Project Report
ESPI - Project Report
Akash Marakani
 
Proposed Multi-object Tracking Algorithm Using Sobel Edge Detection operator
Proposed Multi-object Tracking Algorithm Using Sobel Edge Detection operatorProposed Multi-object Tracking Algorithm Using Sobel Edge Detection operator
Proposed Multi-object Tracking Algorithm Using Sobel Edge Detection operator
QUESTJOURNAL
 
Program for 2015 ieee international conference on consumer electronics taiw...
Program for 2015 ieee international conference on consumer electronics   taiw...Program for 2015 ieee international conference on consumer electronics   taiw...
Program for 2015 ieee international conference on consumer electronics taiw...
supra_uny
 

What's hot (20)

L010427275
L010427275L010427275
L010427275
 
Aiding visually challenged individual for object detection and navigation usi...
Aiding visually challenged individual for object detection and navigation usi...Aiding visually challenged individual for object detection and navigation usi...
Aiding visually challenged individual for object detection and navigation usi...
 
Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network  Interactive Full-Body Motion Capture Using Infrared Sensor Network
Interactive Full-Body Motion Capture Using Infrared Sensor Network
 
D017511825
D017511825D017511825
D017511825
 
Construction of sine and cosine hologram of brain tumor image
Construction of sine and cosine hologram of brain tumor imageConstruction of sine and cosine hologram of brain tumor image
Construction of sine and cosine hologram of brain tumor image
 
Construction of sine and cosine hologram of brain tumor image
Construction of sine and cosine hologram of brain tumor imageConstruction of sine and cosine hologram of brain tumor image
Construction of sine and cosine hologram of brain tumor image
 
Interactive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor networkInteractive full body motion capture using infrared sensor network
Interactive full body motion capture using infrared sensor network
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point Clouds
 
AN OPTIMAL SOLUTION FOR IMAGE EDGE DETECTION PROBLEM USING SIMPLIFIED GABOR W...
AN OPTIMAL SOLUTION FOR IMAGE EDGE DETECTION PROBLEM USING SIMPLIFIED GABOR W...AN OPTIMAL SOLUTION FOR IMAGE EDGE DETECTION PROBLEM USING SIMPLIFIED GABOR W...
AN OPTIMAL SOLUTION FOR IMAGE EDGE DETECTION PROBLEM USING SIMPLIFIED GABOR W...
 
IRJET- Real Time Implementation of Air Writing
IRJET- Real Time Implementation of  Air WritingIRJET- Real Time Implementation of  Air Writing
IRJET- Real Time Implementation of Air Writing
 
DIGITAL RESTORATION OF TORN FILMS USING FILTERING T ECHNIQUES
DIGITAL RESTORATION OF TORN FILMS USING FILTERING T ECHNIQUESDIGITAL RESTORATION OF TORN FILMS USING FILTERING T ECHNIQUES
DIGITAL RESTORATION OF TORN FILMS USING FILTERING T ECHNIQUES
 
FPGA Implementation of Glaucoma Detection using Neural Networks
FPGA Implementation of Glaucoma Detection using Neural NetworksFPGA Implementation of Glaucoma Detection using Neural Networks
FPGA Implementation of Glaucoma Detection using Neural Networks
 
An Accurate Scheme for Distance Measurement using an Ordinary Webcam
An Accurate Scheme for Distance Measurement using an Ordinary Webcam An Accurate Scheme for Distance Measurement using an Ordinary Webcam
An Accurate Scheme for Distance Measurement using an Ordinary Webcam
 
Stereo Vision Human Motion Detection and Tracking in Uncontrolled Environment
Stereo Vision Human Motion Detection and Tracking in Uncontrolled EnvironmentStereo Vision Human Motion Detection and Tracking in Uncontrolled Environment
Stereo Vision Human Motion Detection and Tracking in Uncontrolled Environment
 
ESPI - Project Report
ESPI - Project Report ESPI - Project Report
ESPI - Project Report
 
Iris Segmentation: a survey
Iris Segmentation: a surveyIris Segmentation: a survey
Iris Segmentation: a survey
 
IRJET-Vision Based Occupant Detection in Unattended Vehicle
IRJET-Vision Based Occupant Detection in Unattended VehicleIRJET-Vision Based Occupant Detection in Unattended Vehicle
IRJET-Vision Based Occupant Detection in Unattended Vehicle
 
Proposed Multi-object Tracking Algorithm Using Sobel Edge Detection operator
Proposed Multi-object Tracking Algorithm Using Sobel Edge Detection operatorProposed Multi-object Tracking Algorithm Using Sobel Edge Detection operator
Proposed Multi-object Tracking Algorithm Using Sobel Edge Detection operator
 
Exercise Recognition System using Facial Image Information from a Mobile Devi...
Exercise Recognition System using Facial Image Information from a Mobile Devi...Exercise Recognition System using Facial Image Information from a Mobile Devi...
Exercise Recognition System using Facial Image Information from a Mobile Devi...
 
Program for 2015 ieee international conference on consumer electronics taiw...
Program for 2015 ieee international conference on consumer electronics   taiw...Program for 2015 ieee international conference on consumer electronics   taiw...
Program for 2015 ieee international conference on consumer electronics taiw...
 

Similar to FPGA-Based Contact Lenses Try-On System

Similar to FPGA-Based Contact Lenses Try-On System (20)

IRJET- Object Detection and Recognition for Blind Assistance
IRJET- Object Detection and Recognition for Blind AssistanceIRJET- Object Detection and Recognition for Blind Assistance
IRJET- Object Detection and Recognition for Blind Assistance
 
Brain tumor pattern recognition using correlation filter
Brain tumor pattern recognition using correlation filterBrain tumor pattern recognition using correlation filter
Brain tumor pattern recognition using correlation filter
 
IRJET - Human Eye Pupil Detection Technique using Center of Gravity Method
IRJET - Human Eye Pupil Detection Technique using Center of Gravity MethodIRJET - Human Eye Pupil Detection Technique using Center of Gravity Method
IRJET - Human Eye Pupil Detection Technique using Center of Gravity Method
 
Drishyam - Virtual Eye for Blind
Drishyam - Virtual Eye for BlindDrishyam - Virtual Eye for Blind
Drishyam - Virtual Eye for Blind
 
IRJET- Smart Mirror using Eye Gaze Tracking
IRJET- Smart Mirror using Eye Gaze TrackingIRJET- Smart Mirror using Eye Gaze Tracking
IRJET- Smart Mirror using Eye Gaze Tracking
 
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
 
IRJET- Analysing Wound Area Measurement using Android App
IRJET- Analysing Wound Area Measurement using Android AppIRJET- Analysing Wound Area Measurement using Android App
IRJET- Analysing Wound Area Measurement using Android App
 
IRJET- Analysis of Yawning Behavior in IoT based of Drowsy Drivers
IRJET- Analysis of Yawning Behavior in IoT based of Drowsy DriversIRJET- Analysis of Yawning Behavior in IoT based of Drowsy Drivers
IRJET- Analysis of Yawning Behavior in IoT based of Drowsy Drivers
 
POTHOLE DETECTION SYSTEM USING YOLO v4 ALGORITHM
POTHOLE DETECTION SYSTEM USING YOLO v4 ALGORITHMPOTHOLE DETECTION SYSTEM USING YOLO v4 ALGORITHM
POTHOLE DETECTION SYSTEM USING YOLO v4 ALGORITHM
 
IRJET - Blind Guidance using Smart Cap
IRJET - Blind Guidance using Smart CapIRJET - Blind Guidance using Smart Cap
IRJET - Blind Guidance using Smart Cap
 
Intelligent System For Face Mask Detection
Intelligent System For Face Mask DetectionIntelligent System For Face Mask Detection
Intelligent System For Face Mask Detection
 
A Study of Motion Detection Method for Smart Home System
A Study of Motion Detection Method for Smart Home SystemA Study of Motion Detection Method for Smart Home System
A Study of Motion Detection Method for Smart Home System
 
A SURVEY ON KIDNEY STONE DETECTION USING IMAGE PROCESSING AND DEEP LEARNING
A SURVEY ON KIDNEY STONE DETECTION USING IMAGE PROCESSING AND DEEP LEARNINGA SURVEY ON KIDNEY STONE DETECTION USING IMAGE PROCESSING AND DEEP LEARNING
A SURVEY ON KIDNEY STONE DETECTION USING IMAGE PROCESSING AND DEEP LEARNING
 
IRJET- Glaucoma Detection using Convolutional Neural Network
IRJET- Glaucoma Detection using Convolutional Neural NetworkIRJET- Glaucoma Detection using Convolutional Neural Network
IRJET- Glaucoma Detection using Convolutional Neural Network
 
IRJET - Effective Workflow for High-Performance Recognition of Fruits using M...
IRJET - Effective Workflow for High-Performance Recognition of Fruits using M...IRJET - Effective Workflow for High-Performance Recognition of Fruits using M...
IRJET - Effective Workflow for High-Performance Recognition of Fruits using M...
 
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
A Novel Framework For Preprocessing Of Breast Ultra Sound Images By Combining...
 
Sanjaya: A Blind Assistance System
Sanjaya: A Blind Assistance SystemSanjaya: A Blind Assistance System
Sanjaya: A Blind Assistance System
 
ROAD POTHOLE DETECTION USING YOLOV4 DARKNET
ROAD POTHOLE DETECTION USING YOLOV4 DARKNETROAD POTHOLE DETECTION USING YOLOV4 DARKNET
ROAD POTHOLE DETECTION USING YOLOV4 DARKNET
 
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
IRJET- A Real Time Yolo Human Detection in Flood Affected Areas based on Vide...
 
IRJET- Criminal Recognization in CCTV Surveillance Video
IRJET-  	  Criminal Recognization in CCTV Surveillance VideoIRJET-  	  Criminal Recognization in CCTV Surveillance Video
IRJET- Criminal Recognization in CCTV Surveillance Video
 

More from journal ijrtem

Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...
Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...
Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...
journal ijrtem
 
A study on financial aspect of supply chain management
A study on financial aspect of supply chain management	A study on financial aspect of supply chain management
A study on financial aspect of supply chain management
journal ijrtem
 

More from journal ijrtem (20)

The effect of functionalized carbon nanotubes on thermalmechanical performanc...
The effect of functionalized carbon nanotubes on thermalmechanical performanc...The effect of functionalized carbon nanotubes on thermalmechanical performanc...
The effect of functionalized carbon nanotubes on thermalmechanical performanc...
 
Development Issues and Problems of Selected Agency in Sorsogon, An investigat...
Development Issues and Problems of Selected Agency in Sorsogon, An investigat...Development Issues and Problems of Selected Agency in Sorsogon, An investigat...
Development Issues and Problems of Selected Agency in Sorsogon, An investigat...
 
Positive and negative solutions of a boundary value problem for a fractional ...
Positive and negative solutions of a boundary value problem for a fractional ...Positive and negative solutions of a boundary value problem for a fractional ...
Positive and negative solutions of a boundary value problem for a fractional ...
 
ORGANIC FOODS
ORGANIC FOODSORGANIC FOODS
ORGANIC FOODS
 
MOLECULAR COMPUTING
MOLECULAR COMPUTINGMOLECULAR COMPUTING
MOLECULAR COMPUTING
 
THE ESSENCE OF INDUSTRY 4.0
THE ESSENCE OF INDUSTRY 4.0THE ESSENCE OF INDUSTRY 4.0
THE ESSENCE OF INDUSTRY 4.0
 
GREEN CHEMISTRY: A PRIMER
GREEN CHEMISTRY: A PRIMERGREEN CHEMISTRY: A PRIMER
GREEN CHEMISTRY: A PRIMER
 
Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...
Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...
Rural Livelihood and Food Security: Insights from Srilanka Tapu of Sunsari Di...
 
Augmented Tourism: Definitions and Design Principles
Augmented Tourism: Definitions and Design PrinciplesAugmented Tourism: Definitions and Design Principles
Augmented Tourism: Definitions and Design Principles
 
A study on financial aspect of supply chain management
A study on financial aspect of supply chain management	A study on financial aspect of supply chain management
A study on financial aspect of supply chain management
 
Existence results for fractional q-differential equations with integral and m...
Existence results for fractional q-differential equations with integral and m...Existence results for fractional q-differential equations with integral and m...
Existence results for fractional q-differential equations with integral and m...
 
Multi products storage using randomness
Multi products storage using randomnessMulti products storage using randomness
Multi products storage using randomness
 
Study of desalination processes of seawater from the desalination plant of La...
Study of desalination processes of seawater from the desalination plant of La...Study of desalination processes of seawater from the desalination plant of La...
Study of desalination processes of seawater from the desalination plant of La...
 
Effect of Cash Management on The Financial Performance of Cooperative Banks i...
Effect of Cash Management on The Financial Performance of Cooperative Banks i...Effect of Cash Management on The Financial Performance of Cooperative Banks i...
Effect of Cash Management on The Financial Performance of Cooperative Banks i...
 
Technical expertise on the cause of engine failure of the Mitsubishi Pajero S...
Technical expertise on the cause of engine failure of the Mitsubishi Pajero S...Technical expertise on the cause of engine failure of the Mitsubishi Pajero S...
Technical expertise on the cause of engine failure of the Mitsubishi Pajero S...
 
Clustering based Time Slot Assignment Protocol for Improving Performance in U...
Clustering based Time Slot Assignment Protocol for Improving Performance in U...Clustering based Time Slot Assignment Protocol for Improving Performance in U...
Clustering based Time Slot Assignment Protocol for Improving Performance in U...
 
Design and Implementation of Smart Bell Notification System using IoT
Design and Implementation of Smart Bell Notification System using IoT	Design and Implementation of Smart Bell Notification System using IoT
Design and Implementation of Smart Bell Notification System using IoT
 
Assessment of the Water Quality of Lake Sidi Boughaba (Ramsar Site 1980) Keni...
Assessment of the Water Quality of Lake Sidi Boughaba (Ramsar Site 1980) Keni...Assessment of the Water Quality of Lake Sidi Boughaba (Ramsar Site 1980) Keni...
Assessment of the Water Quality of Lake Sidi Boughaba (Ramsar Site 1980) Keni...
 
The case of a cyclist and tractor traffic accident
The case of a cyclist and tractor traffic accident	The case of a cyclist and tractor traffic accident
The case of a cyclist and tractor traffic accident
 
A Smart Approach for Traffic Management
A Smart Approach for Traffic Management	A Smart Approach for Traffic Management
A Smart Approach for Traffic Management
 

Recently uploaded

Online blood donation management system project.pdf
Online blood donation management system project.pdfOnline blood donation management system project.pdf
Online blood donation management system project.pdf
Kamal Acharya
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
Kamal Acharya
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
Neometrix_Engineering_Pvt_Ltd
 

Recently uploaded (20)

İTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering WorkshopİTÜ CAD and Reverse Engineering Workshop
İTÜ CAD and Reverse Engineering Workshop
 
fundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projectionfundamentals of drawing and isometric and orthographic projection
fundamentals of drawing and isometric and orthographic projection
 
Natalia Rutkowska - BIM School Course in Kraków
Natalia Rutkowska - BIM School Course in KrakówNatalia Rutkowska - BIM School Course in Kraków
Natalia Rutkowska - BIM School Course in Kraków
 
Online blood donation management system project.pdf
Online blood donation management system project.pdfOnline blood donation management system project.pdf
Online blood donation management system project.pdf
 
Toll tax management system project report..pdf
Toll tax management system project report..pdfToll tax management system project report..pdf
Toll tax management system project report..pdf
 
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptxCloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
Cloud-Computing_CSE311_Computer-Networking CSE GUB BD - Shahidul.pptx
 
fluid mechanics gate notes . gate all pyqs answer
fluid mechanics gate notes . gate all pyqs answerfluid mechanics gate notes . gate all pyqs answer
fluid mechanics gate notes . gate all pyqs answer
 
Event Management System Vb Net Project Report.pdf
Event Management System Vb Net  Project Report.pdfEvent Management System Vb Net  Project Report.pdf
Event Management System Vb Net Project Report.pdf
 
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and VisualizationKIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
KIT-601 Lecture Notes-UNIT-5.pdf Frame Works and Visualization
 
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and ClusteringKIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
KIT-601 Lecture Notes-UNIT-4.pdf Frequent Itemsets and Clustering
 
Hall booking system project report .pdf
Hall booking system project report  .pdfHall booking system project report  .pdf
Hall booking system project report .pdf
 
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWINGBRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
BRAKING SYSTEM IN INDIAN RAILWAY AutoCAD DRAWING
 
Architectural Portfolio Sean Lockwood
Architectural Portfolio Sean LockwoodArchitectural Portfolio Sean Lockwood
Architectural Portfolio Sean Lockwood
 
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data AnalysisIT-601 Lecture Notes-UNIT-2.pdf Data Analysis
IT-601 Lecture Notes-UNIT-2.pdf Data Analysis
 
Immunizing Image Classifiers Against Localized Adversary Attacks
Immunizing Image Classifiers Against Localized Adversary AttacksImmunizing Image Classifiers Against Localized Adversary Attacks
Immunizing Image Classifiers Against Localized Adversary Attacks
 
Standard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - NeometrixStandard Reomte Control Interface - Neometrix
Standard Reomte Control Interface - Neometrix
 
Arduino based vehicle speed tracker project
Arduino based vehicle speed tracker projectArduino based vehicle speed tracker project
Arduino based vehicle speed tracker project
 
Construction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptxConstruction method of steel structure space frame .pptx
Construction method of steel structure space frame .pptx
 
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdfRESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
RESORT MANAGEMENT AND RESERVATION SYSTEM PROJECT REPORT.pdf
 
2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge2024 DevOps Pro Europe - Growing at the edge
2024 DevOps Pro Europe - Growing at the edge
 

FPGA-Based Contact Lenses Try-On System

  • 1. Invention Journal of Research Technology in Engineering & Management (IJRTEM) ISSN: 2455-3689 www.ijrtem.com Volume 1 Issue 4 ǁ June. 2016 ǁ PP 01-04 | Volume 1| Issue 4 | www.ijrtem.com | June 2016| 1 FPGA-Based Contact Lenses Try-On System Chen-Chien Hsu, Hsiang-Yu Huang, Man-Wei Huang, Wei-Yen Wang, and Chiang-Heng Chien (Department of Electrical Engineering, National Taiwan Normal University, Taiwan, R.O.C.) ABSTRACT : A hardware/software (HW/SW) co-design approach developing a contact lenses try-on system via the use of the Field Programmable Gate Array (FPGA) [1] is proposed in this paper. To achieve an interactive user-friendly environment, the menu of contact lenses and the result that shows howit looks when wearing the contact lens are displayed on the LCD touch panel directly. After capturing the user’s image via CMOS sensors, image processing is employed to determine user’s irises from the image. A particle filter algorithm is then introduced to track the irises so that the contact lenses chosen by the user can be overlapped on the image to provide a natural examination of the effect of the contact lenses try-on system. Experimental results show good performances of the proposed system. Keywords: FPGA, Eye Tracking, Particle Filter, Nios II, Image Processing 1. Introduction Contact lenses, a thin lens placed directly on the surface of the eyes, are regarded as a medical device to enhance visual abilities. Many people wear color cosmetic contact lenses for aesthetic reasons nowadays. To meet the consumer’s demand, more and more contact lenses manufactures produce color cosmetic contact lenses. However, it is difficult to decide preferable contact lenses since consumers are often not allowed to try it on. This is because the costs of color cosmetic contact lenses are relatively high, and only a few manufactures provide samples for consumers. To solve this problem, this research develops a system that allows consumers to virtually try on color cosmetic contact lenses without physically wearing it so that consumers can easily choose their preferable ones. To allow a natural presentation of the contact lenses, eye tracking is one of the key points in the proposed contact lenses try-on system. The white part of the eye is sclera, which interferes less during the course of tracking. The black part is iris, which is the main object to be tracked. There are different light sources for use in eye tracking, such as infrared light and natural light. If infrared light is used, little effort is required for image processing. However, there is a safety concern in which infrared light might potentially damage human’s eyes. Therefore, the desired natural light source is used, where a particle filter [2][3] algorithm is developed to track the exact position of the iris after the image has been captured. HSV color space is used to remove the shadow caused by natural light while a 5x5 median filter is used to remove impulsive noise. Binarization is also very important to identify the object of interest in the image. Finally, dilation and erosion are used to reconstruct and decompose the image. The development platform of the contact lenses try-on system is based on Altera’s DE2 development board, which provides high speed SSRAM, SDRAM with large data storage, uClinux operating system, the Cyclone II, and SoPC Builder’s logical module. Altera also provides devices such as COMS sensor to capture images and LCD touch panel to display the menu and the results. 2. Proposed Contact Lenses Try-On System 1.1 Design Architecture Figure 1 Hardware Design of the proposed contact lenses try-on system
  • 2. FPGA-Based Contact Lenses Try-On System | Volume 1| Issue 4 | www.ijrtem.com | June 2016| 2 Fig. 1 shows the hardware design of the proposed contact lenses try-on system. After the CMOS sensor receives data from the image capturing user’s face, the image is gone through image processing for eye tracking. The menu of the contact lenses is then shown on the LCD touch panel under the control of CMOS Master Controller, NIOS II processor, and LTM Master Controller. Finally, Quatrus II software by Altera [4] is used to integrate the system. 1.2 Overall Flow Chart Fig. 2 (a) shows the flowchart of this system. First, the menu of contact lenses try-on system is displayed on the LCD touch panel. Then, the user touches the panel to choose what kind of contact lenses they would like to try on. As the user had chosen their preferable contact lenses, D5M will capture the user’s image. After that, image processing is used to distinguish the facial part from the background for eye tracking. The location of the iris is tracked via particle filter as a consequence. Finally, the image of the contact lenses chosen by the user is overlapped on the image and the result is presented on the LCD board. (a) (b) Figure 2 (a) Flow chart of the proposed contact lenses try-on system. (b) Flow chart of the particle filter algorithm for tracking. 1.3 Median Filter Since an image could contain a lot of noises that could thereby affect the performance of the system. Therefore, median filer [5] is introduced to remove the noise of the image. According to the experimental results, a size of 5x5 mask is suitably used for the median filter in the proposed system. 1.4 Morphology After the image is processed through color space conversion and median filter, binarization can make the object more obvious. However, the result might be incomplete due to the light or the noise. Therefore, morphology [6] is required to track the location of the center of the object. Morphology[6] includes dilation, erosion, opening, and closing. Dilation and erosion are used in this paper, where dilation refills the losing part of the iris while erosion removes the noise around eyes. Morphology completes the shape of the iris. 1.5 Particle Filter Fig. 2 (b) shows the flowchart of particle filter algorithm for tracking. First, weight assignment deals with calculations of weights valuing each particle. The larger the value is, the higher the possibilityfor this particle to be the location of the iris. Tournament selection [7] is employed so that particles with the top five highest weights are chosen to estimate the location of the iris. Then, a resampling procedure is used to eliminate particles with lower weights and replicate the particles with higher weights. After that, since the object might move and slightly change by the time goes, prediction is required to estimate the location of each particle at the next time. Fig. 3 shows the process of eye tracking by particle filter, where the yellow dots are particles generated by particle filter. Through iterations, an optimal location in the estimation of the iris is obtained thereafter. It is marked in red in the figure.
  • 3. FPGA-Based Contact Lenses Try-On System | Volume 1| Issue 4 | www.ijrtem.com | June 2016| 3 Figure 3 The process of eye tracking by using particle filter algorithm. 3. Experimental Results The proposed contact lenses try-on system is implemented on a Altera’s DE2-70 development board as shown in Fig. 4. Users can choose the contact lenses they would like to try on from the menu shown in Fig. 5 (a). In order to achieve a more natural result, we adjust the display by comparing the color of the iris and the background illumination in that environment shown in Fig. 5 (b). Figure 4 The Altera’s DE2-70 development board. (a) (b) Figure 5 (a) Contact lenses menu for users to choose. (b) The result of the proposed contact lenses try-on system. 4. Conclusion The proposed contact lenses try-on system is a low cost, simple operation, and user-friendly platform, which replaces the high cost contact lenses sample and provides a more efficient way for consumers to try on their preferable color contact lenses. Because contact lenses images are stored in SD card provided by the DE2, new styles of contact lenses can be added anytime when they are available for consumers. Therefore, the proposed system has high flexibilities for both the sellers and consumers aspects.
  • 4. FPGA-Based Contact Lenses Try-On System | Volume 1| Issue 4 | www.ijrtem.com | June 2016| 4 5. Acknowledgements This research is partially supported by the “Aim for the Top University Project” and “Center of Learning Technology for Chinese” of National Taiwan Normal University (NTNU), sponsored by the Ministry of Education, Taiwan, R.O.C. and the “International Research-Intensive Center of Excellence Program” of NTNU and Ministry of Science and Technology, Taiwan, under Grants no. MOST 104-2911-I-003-301 and MOST 103-2221-E-003-027. REFERENCES [1]. Oetken, S. Wildermann, and J. Teich, A Bus-based SoC Architecture for Flexible Module Placement on Reconfigurable FPGAs: Int. Conf. on [2]. Field Programmable Logic and Applications (FPL), Milano, 2010, 234-239. [3]. S. Fazli, H. Moradi, and P. Hamed Bouzari, Particle Filter based Object Tracking with Sift and Color Feature: 2nd Int. Conf. on Machine Vision, Dubai, 2009, 89-93. [4]. D. Xu, L. Huang, and C. Liu, Object Tracking using Particle Filter based on Color Correlogram:2nd Int. Symposium on Intelligent Information Technology Application, Shanghai, 2008, 608-612. [5]. Altera Corporation, Quarts II Handbook (Altera Corporation, 2004). [6]. T. Huang, G. Yang, and G. Tang, A fast two-dimensional median filtering algorithm, IEEE Trans. on Acoust., Speech, and Signal Processing, 27(1), 1979, 13–18. [7]. O. Dgforges, and N. Normand, A generic systolic processor for real time grayscale morphology: Int. Conf. on Acoustics, Speech, and Signal Processing, Istanbul, 2006, 3331-3334. [8]. Z. Michalewicz, Genetic Algorithm + Data Structure = Evolution Programs, Third Ed., Springer, 1996.