Browsing by Author "Wickramarathna, S.D.H.S."

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    2D to 3D Image Visualizer
    (Uva Wellassa University of Sri Lanka, 2012) Bandara, P.B.M.M.A.; Wickramarathna, S.D.H.S.
    The ordinary photographs are only considered about just an individual photograph itself. Since these photographs act individual character in a scene there is no way to visualize a connection between them. Also browsing of each captured photographs is not relative to other though these photographs are in the same scene. But there is a possible way to reorganize the relative position and orientation of ordinary photographs which are captured by a digital camera device. That is, reorganize the important features on each photographs using feature detection algorithm, then match each photograph by matching these features, then estimate the relative camera pose against each photograph in order to calculate relative replacement and orientation of each photographs on 3D environment. It is useless to calculate the 3D replacement without visualizing them, because the real world scenes are in 3D environment. Therefore, 3D visualizer, to visualize all calculated photographs is developed with very user friendly and interactive way. This project is to develop a system for interactively browsing and exploring unstructured collections of photographs of a scene using a three-dimension interface.
  • No Thumbnail Available
    Item
    Android Application for Vehicle Security System
    (Uva Wellassa University of Sri Lanka, 2012) Perera, P.D.S.; Wickramarathna, S.D.H.S.
    Current vehicle security systems available in the market are based on Infrared or Radio Frequency technology using a circuit which is attached to the key. This Security system is controlled by a small gadget that is always attached to the key of the vehicle. One of the weaknesses in the current system is that anyone who has the key can unlock the functions of the vehicle and it is one of the major security threats. Proposed system can eradicate this threat by using the password base control system with Bluetooth technology which applicable to any Android Mobile phone (G. Held). This research is based on designing and developing an Android application for vehicle security system [2] which will facilitate the door locking/opening, parking light on/off, air conditioning system on/off and engine off. This application supplies a convenient, efficient and reliable security service to the vehicle owners
  • No Thumbnail Available
    Item
    Augmented Reality Based Advertising System for Modern Home Items
    (Uva Wellassa University of Sri Lanka, 2013) Wickramasinghe, A.A.M.W.; Wickramarathna, S.D.H.S.
    The main purpose behind this project concept is take full advantage of the internet and mobile world as a powerful marketing channel for profitable and interactive shopping. The system is capable for the control of the shopping experience is placed firmly in the consumer’s hand with the advanced technological experience with Augmented Reality concept. The basic goals of the research can identified as augmented reality for usable business model (Schwald et al., 2003). The users can experience the virtual 3D object interactively with the real environment. Therefore it allows users to visualize how a certain concept would look like in their home even before buying it using 3D models and video augmented advertising. The system consists with mobile application and a web site. This system will be also useful as an advertising system between consumers and dealers .And also this system is a further step to introduce last technologies in the world of marketing. As a whole user can provide the image of maker in to the system, which used to identify the position to locate the rendered 3D object. Then the application should launch from the android phone and the focus the camera towards the marker. The system starts recognition process and then rendered the particular 3D view of the selected item on to the marker. After the rendered process completed the system options allowed the user to apply the system co functionalities such as 3D model resizing, rotation and transition based on user preference. Methodology Basic foundation of the whole system is augmented reality. Augmented reality, when classified (Milgram et al., 1994) can be placed in between a real environment and a virtual one .The developed system based on Android operating system and developed using java and xml. HTML and java script were used for the web development. AR Toolkit was the foundation for the system development which is an open source framework. The complex scenarios tracking markers and calculating transformation matrix like complex processes were handled using AR Toolkit. Initially the image marker tracked by the video capture and read the pattern related with the marker and the related capture parameters. Then the system detects the makers and recognized the patterns related with video input. Then calculate the camera transformations and render the 3D model on the detected pattern. In the scenario of the video playing the recognized the images within the video capture and then compared it with the inner storage gray scale images and render the relevant video output on the detected image. The system architecture is shown in the Figure 1. The system is relies on OpenGL for rendering purpose which is the main role of the whole developed system and GLUT which is responsible for creating OpenGL window. The marker It must be square in shape, borders must contrast well and the border must be a solid color. The image used for the video rendering should be gray scale and have identical edges within it. Due to the system performances based rely on the device capabilities the system testing was conducted over number of devices in the development process.
  • No Thumbnail Available
    Item
    Bone Crack Detector based on X-Ray using Fuzzy Logic and Neural Network
    (Uva Wellassa University of Sri Lanka, 2013) Abesinghe, K.A.W.P.; Wickramarathna, S.D.H.S.
    An x-ray (radiograph) is a noninvasive medical test (Tian Tai Pengn, 2002) that helps physicians diagnose and treat medical conditions. X-Ray images are used by doctors to detect the crack and abnormal conditions of the bones. Doctors are analyzing thousands of X-Ray images at hospital day by day. That activity is monotonous and also consuming lot of time. Bones contain much calcium, which due to its relatively high atomic number absorbs X-Rays efficiently. This reduces the amount ofX-rays reaching the detector in the shadow of the bones, making them clearly visible on the radiograph. A recognition system has three parts; Image Processing and feature extraction, Fuzzy Logic based identification and Neural Network based verification. The main objective of this study is Computer-assisted decision-making system to detect the crack of the bone in X-Ray image. Image Preprocessing is applying for enhance the features of the image. Edges based filters apply for enhance the edges because edges perform the vital role for detecting the crack of the bone image. Then system detects the edges of the image using canny edge detector. Background of the image is eliminated as the next step. System is finally detecting the edges that could be a crack or not. System could detect the actual crack and also some specific features of the bone. Those specific features of the bone are smooth lines and cracks are rough line. Using that specific characteristics system separate crack lines form some features of the bone. Finally abstract the features information for Fuzzyfication. Fuzzy Classifier contains fuzzy inference engine, input output variables. Input variables are information about the edges. Output variables are the detected crack. System is using two fuzzy sets and three fuzzy functions for each fuzzy set. One fuzzy set is Fuzzy Multiplication and other is Fuzzy Ratio. The fuzzy rules calculate the output and those outputs send to Neural Network for verification. Neural Network (Davis et al., 1999) takes the input from the Fuzzyfication and specific some parameters taken from image. Eight neurons for input layers, ten neurons for hidden layer and three neurons for output layer use for Neural Network. Supervise training uses for trains the Neural Network. Output obtains as pattern. Finally Neural Network verifies the fuzzy output and correctly says crack or not a crack.
  • No Thumbnail Available
    Item
    Human Ear Recognition System
    (Uva Wellassa University of Sri Lanka, 2013) Jayathilaka, W.M.S.D.; Wickramarathna, S.D.H.S.
    Biometric features are widely used today for identification purposes. The most interesting human anatomical parts for biometrics systems are finger prints, the irises, face and ear. These parts contain a large volume of unique features that allow identifying humans. Among them the ear has a large amount of unique features (Bhanuet al., 2008). The shape and appearance of an ear are fixed while other biometric features are changed with age (Singh et al., 2013). There are no developed systems for identifying a human by using the ear. This System can be used for criminal investigation purposes. Police Departments, Custom Departments and other government agencies can use this system as a tool for person identification. Methodology The system will accept an image which contains the ear of a person and register the image and store its color information taken from 25 regions. When it searches information of a person by his/her ear, it will compare the values with stored database values using Euclidean distance and output the corresponding personal information. The Human Ear Recognition System is an Image based recognition system consisting of three main modules as shown in Figure 1. The Widget module contains Graphical User Interfaces of the system. The process component supports preprocessing of the ear image before registering the ear in the system. It performs image rotation, cropping and edge detection. Registration component supports the registration of personal information with a preprocessed image of the ear. The search component supports searching a particular person from the system by using his/her ear image. The Service module contains functionalities to detect the edges of the ear, rescale the ear image and compare the particular ear with the ear database. The average color values of pixels within predefined 25 areas are taken in to account (Figure 2). The comparison is based on Euclidean Distance. The Database module supports the Widget module and the Service module to access the database. The Database includes records of personal information, a photograph of particular person and an ear image of the person. These data can be accessed only through the Database module. Result and Discussion The system is able to recognize a person by ear, independent of the angle of the ear. However problems were occurred due to various lighting conditions, which affects the detection the edges of the ear. Therefore, there should be standards to take an ear image that will not change from time to time. So the ear image that is going to be recognized should be taken by following the same standards as registered images were taken. The collections of ears used in this research were provided by IIT Delhi Ear Database. They were taken under identical conditions. The accuracy level of system for those images is 90%.