Browsing by Author "Ranathunga, L"

Now showing 1 - 20 of 40

item: Conference-Full-text
Adaptive Surveillance System using a Camera Network
Yatanwala, YWTM; Senadeera, KMSK; Ruhunuwickrama, OPI; Wijepala, NGNP; Ranathunga, L
CCTV Surveillance Systems have been used in many places to address security issues. Those systems will store a large amount of activities in every moment and most of the times data is stored in separate places without having integrity. Considering large premises, more cameras and more operators are required to handle the situation. Continuous and careful attention is essential to identify the activities of a large crowd. Moreover, there is no proper mechanism to search and retrieve important information from the videos whenever it is needed. In this paper we introduce a new approach to uniquely address those issues, using different image processing algorithms and inter process communication techniques which were implemented to acquire more reliable and accurate timely information from CCTV records in advance.
item: Thesis-Full-text
Analysis on secured e-payment authentication model for e-commerce portals
Walpitagamage, YS; Ranathunga, L
The research focuses on to introducing a secure e-payment authentication model for ecommerce portals. E-commerce can be defined as one of the most rapidly development mechanisms in the world economy. Therefore, a secured payment authentication model is essential for any e-commerce portal. Also today there are various security mechanisms to ensure the security of these e-commerce portals. However, the research background analysis has recognized that there are still problematic areas in existing payment methods. Therefore, this research mainly focuses on introducing a secured e-payment authentication model for e-commerce portals which will ensure the exchange of money more securely and conveniently over the internet. The introducing system is a web based electronic payment authentication processing system that can be used to make a secured electronic payment. In order to provide high security to the electronic transactions, the system validates the payments by using a onetime transaction code generating software installed into users PC or mobile phone. This code generating software uses unique hashing polynomial equation for each individual. The system only validates the transactions, only ifthe user enters the correct secure code in the transaction processing web page. The solution can mainly provide good security against the man in the middle attacks and the phishing attacks. Also this system has been designed to minimize the issues in existing electronic payment systems by providing a great convenient to the users. As a result, this research can be brought into play as a guide for e-payment authentication.
item: Conference-Full-text
Approach for general lossless visible watermarking
(Information Technology Research Unit, Faculty of Information Technology, University of Moratuwa, Sri Lanka, 2017-12) Mahenthirarasa, T; Ranathunga, L; Amalraj, CRJ; Sudantha, BH
the impact of the Internet has influenced in many new circumstances for the creation and delivery of content in digital form. An important issue that arises in these applications is the protection of the rights of all participants. It has been recognized for quite some time that current copyright laws are inadequate for dealing with digital image. This has led to an interest towards developing new copy deterrence and protection mechanisms. One such effort that has been attracting increasing interest is based on digital image watermarking techniques. Digital image watermarking is the process of embedding information into digital image content such that the information can later be extracted or detected for a variety of purposes including copy right protection and control. A visible watermark typically consists of a conspicuously visible message or a company logo indicating the ownership of the image. The system is designed for choosing best watermark for the cover image and three new algorithms for the visible watermarking process. Comparing and testing the three proposed algorithms is done in the evaluation process and highlight the best things of the algorithms proposed by using PSNR values.
item: Article-Full-text
An approach to measure the pedagogy in slides with voice-over type instructional videos
(Academic Publishing, 2022) Suriyawansa, K; Kodagoda, N; Ranathunga, L; Abdullah, NA
E-learning provides a more suitable learning environment for educators and learners. Hence, the e-learning community has rapidly increased over the years. At present, e-learning environments use several materials to transfer knowledge to learners. Out of various types of materials, instructional videos have become the prominent source of information in popular e-learning environments. Instructional videos in e-learning can be categorised into many types based on the content presentation method. Voice-over slides are popular instructional videos at present. Since the instructional materials are a key component of an e-learning environment, maintaining the required quality of these materials is vital. Using proper pedagogy in instructional materials mainly enhances the quality. There are many pedagogical principles proposed over the years, and these principles address different features of all instructional materials. Therefore, it is necessary to derive the applicable pedagogical principles based on the features available in the instructional video to analyse the pedagogy in an instructional video. The investigation related to this paper aims to derive an approach to analysing and quantifying the pedagogy in slides with voice-over type instructional videos. In this study, a thorough literature review first identified the pedagogical principles applicable to slides with voice-over type instructional videos. Next, the prominence of the identified pedagogical principles was derived from a Likert-scale survey conducted by several Information Technology undergraduates. The survey response assigned a rank to each identified pedagogical principle. The rank was derived by the mean score obtained for each pedagogical principle. Next, one-way ANOVA tests were performed for the mean score of pedagogical principles to derive their prominence levels. The ANOVA tests were conducted by adding adjacent pedagogical principles with a non-identical rank until the ANOVA results claimed a significant difference in variances. A new level was defined when the ANOVA results showed a significant difference. This study proposed a pedagogical score calculation formula using these levels (derived from the statistical analysis) to derive a qualitative measure of the use of pedagogy in slides with voice-over type instructional videos. The pedagogical evaluators and content developers can use the proposed scoring method to quantify and compare the pedagogy in slides with voice-over instructional videos.
item: Article-Abstract
Automatic evaluation software for contact centre agents’ voice handling performance
Perera, KKANN; Priyadarshana, YHPP; Gunathunga, KIH; Ranathunga, L; Karunarathne, PM; Thanthriwatta, TM
Evaluating the contact center agent’s voice handling skills is important in order to enhance the customer satisfaction, through employee performance. Conventionally, supervisors in call center monitoring divisions listen to contact center agents’ conversations and then assign scores for the voice of the agent which end up in most cases bias and as erroneous evaluations. In order to minimize the above mentioned problems, this paper discusses a system, we implemented to evaluate contact center agents’ voices automatically avoiding human error and bias decisions. This software application considers speech rate, voice intensity level and emotional state of the contact center agent for their voice handling evaluations. According to the conducted research, it can be seen that the accuracy of evaluating the giving of instructions clearly using speech rate is 72%, evaluating listener comfortable voice intensity of agent is 83% and accuracy of emotion recognition of the agent’s is 83% in the implemented system.
item: Conference-Full-text
Automatic Glaucoma Detection by Using Funduscopic Images
Atheesan, S; Shanmugarajah, Y; Ajanthan, T; Ranathunga, L
This paper describes an automatic system to identify glaucoma disease from funduscopic images by using digital image processing. Glaucoma caused by increase of pressure in eye and damages in optic nerve. Glaucoma tends to be grown and may not show until final stage. Through this system, doctors can easily identify patient’s condition quickly and do treatment. Rural people also will get advantage through this system. Glaucoma is identified through cup to disc ratio (CDR) calculation and orientation of the blood vessels in this system. For that Optical disk’s inner circle (cup) and outer circle (disc) is extracted. From that radius is calculated. The outer and inner circles are extracted by using average and maximum grey level pixels respectively with the use of histogram. Then find contours and draw circle which is best fitting the contours. The radius of cup and disc are found. After calculating CDR, the abnormal image can be found if CDR exceeds a particular threshold value. Otherwise it is normal image. The system extracts the blood vessels and through the orientation of the blood vessel glaucoma is identified.
item: Conference-Abstract
Calibration checklist to use in an automated pedagogical evaluation process of web based E-Learning
(2014-06-20) De Sirisuriya, SCMS; Ranathunga, L; Karunanayaka, SP; Abdullah, NA
E-Learning becomes widely spread in the past few years because it enables learner to participate in anytime, anyplace personalized training. Designing rich E-Learning environment is an important factor to enhancing the effectiveness of web based education. Therefore the necessity of evaluating the web based E-Learning content is arising. The evaluation of E-Learning content is beneficial for learner to choose the best learning material, as well as instructional designer to improve the quality of their learning materials. Inconsistency is the biggest challenge faced by pedagogical reviewers in manual pedagogical evaluation process of web based E-Learning since different institutes used different set of checklists in order to pedagogically evaluate their web based E-Learning content. This paper puts forth web based E-Learning pedagogy evaluation formulae formation technique derived through a standardized checklist, which generally used in pedagogical evaluation process of web based E-Learning content. This wouldhelp to develop a theoretical framework to automate the pedagogical evaluation process of web based E-Learning content and subsequently design and develop a supporting tool for assisting pedagogical reviewers in the evaluating process. Also this paper discusses the challenges and design rational of the tool designed to setup the framework for pedagogy review of web-based E-Learning.
item: Conference-Abstract
Calibration Checklist to Use in an Automated Pedagogical Evaluation Process of Web Based ELearning
(2015-09-18) de S Sirisuriya, SCM; Karunanayaka, SP; Ranathunga, L; Abdullah, NA
E-Learning becomes widely spread in the past few years because it enables learner to participate in anytime, anyplace personalized training. Designing rich E-Learning environment is an important factor to enhancing the effectiveness of web based education. Therefore the necessity of evaluating the web based E-Learning content is arising. The evaluation of ELearning content is beneficial for learner to choose the best learning material,as well as instructional designer to improve the quality of their learning materials. Inconsistency is the biggest challenge faced by pedagogical reviewers in manual pedagogical evaluation process of web based E-Learning since different institutes used different set of checklists in order to pedagogically evaluate their web based E-Learning content. This paper puts forth web based E-Learning pedagogy evaluation formulae formation technique derived through a standardized checklist, which generally used in pedagogical evaluation process of web based E-Learning content.This wouldhelp to develop a theoretical framework to automate the pedagogical evaluation process of web based E-Learning content and subsequently design and develop a supporting tool for assisting pedagogical reviewers in the evaluating process.Also this paper discusses the challenges and design rational of the tool designed to setup the framework for pedagogy review of web-based E-Learning.
item: Conference-Abstract
Can pedagogical evaluation process of web based E-Learning be automated?
(2014-06-24) de S Sirisuriya, SCM; Ranathunga, L; Karunanayaka, SP; Abdullah, NA
E-Learning aims to improve the quality of learning through the use of modern information and communication technologies. Designing E-Learning course materials is the most critical task because its entire educational system depends on the way content is presented. For that reason the necessity of evaluating the web based E-Learning content is arising. The evaluation of E-Learning content is beneficial for learner as well as instructional designer because it facilitates learner to choose the best learning material, and helps designers to improve the quality of their learning materials. This paper describes the importance of automating the pedagogical evaluating process of web based E-Learning contents and the theoretical framework used in the evaluation process. The aim of this research is to improve the quality of the content in e-Learning websites using the feedback given by the automated pedagogical evaluation process.
item: Conference-Full-text
Cloud movement analysis using Lucas Kanade method
(Institute of Electrical and Electronics Engineers, Inc., 2021-09) Weligamage, SU; Ravindu, HM; Bandara, T; Ranathunga, L; Abeykoon, AMHS; Velmanickam, L
Weather forecasting is an important task as it helps people to manage their work.Cloud movement is a major factor for the variation of the weather. Along with the other factors, cloud movement scan beused to predict the weather changes. This paper propose a method to analyze the cloud movements and calculate the motion vectors using Lucas Kanade method. Cloud velocity vector scan beused with cloud types, wind and thermal data to predict the cloud patterns which helps to forecast weather changes. Proposed method has implemented on a software plat form and experiments has been carried out to validate the system.
item: Article-Abstract
A Comprehensive information extraction module for reducing call handling time in a contact centre
Gunathunga, KIH; Priyadarshana, YHPP; Perera, KKANN; Ranathunga, L; Karunaratne, PM; Thanthriwatta, TM
Information extraction plays an important role in text related research and application areas such as text mining and dialogue systems. Information extraction can be done using key word extraction and measuring the semantic similarity between texts. These concepts are applied to address a key issue in the telecommunication contact centre domain where the customer dissatisfaction is increasing due to higher call handling time. The proposed method is a combined with a key word based approach and a semantic similarity based approach with the use of semantic nets. The semantic similarity of two sentences is calculated using word similarity and the word order. Experiments on two sets of sentence pairs illustrates that proposed method provides a similar measure which is significantly correlated to human intuition. The overall accuracy of the information extraction module is approximately 70% based on the evaluation results.
item:
Conventional video shot segmentation to semantic shot segmentation
(2015-09-18) Ranathunga, L; Zainuddin, R; Abdullah, NA
Video shot segmentation is a preliminary process used in video content analysis which requires for content description. Conventional shot segmentation techniques nourished with statistical approaches depend on chromatic distributions of video frames. However, these conventional approaches lagging behind in performing semantic shot segmentation where more intuitive and perceptive for human understanding and search. This paper presents a novel mechanism which capable of perform semantic shot segmentation without additional computational and description cost for semantic video content depiction process. This mechanism bypasses the traditional video shot segmentation which is normally performs at the beginning of video content depiction and instead it perform meaningful shot boundary identification at the end based on the results of video visual concept classification. This is a positive starting point to perform structuring of video content using semantic units of shots rather than abrupt discontinued shots. Further, this paper introduces a search mechanism empowered by semantic shot segmentation.
item: Conference-Full-text
A data driven approach for detection and correction of spelling errors in sinhala essays
(Faculty of Information Technology, University of Moratuwa., 2021-12) Samarasinghe, PM; Sewwandi, WBI; Ranathunga, L; Wijetunge, WASN; Ganegoda, GU; Mahadewa, KT
This paper proposes novel approaches for checking and correcting spelling errors in Sinhala essays written by candidates of grade five scholarship examination. They don't have a proper mechanism to identify their spelling mistakes in essays by themselves. Spelling errors by such students may occur due to the violation of spelling rules, missing or adding of letters, missing modifiers, inaccurate spelling in a similar structure, and similar sound letters]. To mitigate such challenges, the Sinhala corpus file has been developed to identify the accurate and inaccurate spellings of the written words. The role of this application is to identify the correct and incorrect words which are entered by the user and generate the most correct words as suggestions for the incorrect words. This paper introduces three new novel approaches to detect the correctly spelled words in Sinhala essays namely object word checker method, suffixes checker method and similar word checker method. With addition to that this paper discusses three approaches to generate accurate suggestions including one novel approach. When evaluating the accuracy of the spelling error detection and correction module the overall results for precision, recall, and the f -measure were recorded as 83.05%, 85.57%, and 86.62% respectively.
item: Conference-Abstract
DCT coefficient dependent quantization table modification steganographic algorithm
(2015-09-18) Senthooran, V; Ranathunga, L; LSB; quantization tables; imperceptibility; embedding capacity
In frequency domain based image steganographic methods, especially Discrete Cosine Transformation (DCT), the selection of rounded quantized DCT coefficients in each block for data embedding is still an open issue. This paper presents a new data hiding technique based on the DCT coefficients and modified quantization table values. Embedding strength of each coefficients are determined by the mathematical formula which compare the DCT coefficient and appropriate quantization table value in order then the secrete bits are embedded in frequency components of the quantized DCT coefficients using least significant bit (LSB) method to enable large embedding capacity without image degradation. Further, we investigate this technique for the different cover images in different quality factors by applying scaled and modified quantization tables. A comparison of image quality and embedding capacity between the proposed method and some of other existing methods in literature are analysed. The performance of our proposed method produce satisfactory results compared with other methods.
item: Conference-Abstract
A Feature clustering approach based on histogram of oriented optical flow and superpixels
Bandara, AMRR; Ranathunga, L; Abdullah, NA
Visual feature clustering is one of the cost-effective approaches to segment objects in videos. However, the assumptions made for developing the existing algorithms prevent them from being used in situations like segmenting an unknown number of static and moving objects under heavy camera movements. This paper addresses the problem by introducing a clustering approach based on superpixels and short-term Histogram of Oriented Optical Flow (HOOF). Salient Dither Pattern Feature (SDPF) is used as the visual feature to track the flow and Simple Linear Iterative Clustering (SLlC) is used for obtaining the superpixels. This new clustering approach is based on merging superpixels by comparing short term local HOOF and a color cue to form high-level semantic segments. The new approach was compared with one of the latest feature clustering approaches based on K-Means in eight-dimensional space and the results revealed that the new approach is better by means of consistency, completeness, and spatial accuracy. Further, the new approach completely solved the problem of not knowing the number of objects in a scene.
item: Conference-Full-text
GPS assisted traffic alerting and road congestion reduction mechanism
(2015-07-15) Priyadarshana, YHPP; Nipuni, KKA; Perera, N; Karthik, V; Jayaseelan, R; Abhayawardhana, ARK; Sandamali, HAK; Ranathunga, L; Ruvini, WM; Weerasinghe, M
Traffic congestion is one of the major problems which almost all people face in their day-to-day life. Resources such as time, fuel and money are wasted because of this problem. Both government and non-government parties have taken many actions to reduce this problem but it remains as it was. There are some solutions which provide non-live traffic alerts through mobile phones such as Dialog SatNav, Mobitel T-Navi. Alternative Traffic Alert (ANT) system provides real time traffic alerts to road travellers, giving them the best condition, cost beneficial and optimal alternative route to use at a time of a traffic jam. ANT Solution is implemented with the use of Global Positioning System (GPS) based vehicle tracking, vehicle motion based traffic condition evaluation, mobile and web technologies. This ANT approach supports any mobile phone while other available systems only limited to SMART phones. In addition ANT also performs cost, distance and velocity calculations before determining the best and optimal alternative route.
item:
Hierarchical region based template matching technique for global motion reduction of Coronary Cineangiograms
Kulathilake, KASH; Ranathunga, L; Constantine, GR; Abdullah, NA
The Coronary Cineangiogram (CCA) is an invasive medical image modality which is used to determine the stenosis in the Coronary Arteries. The global motion occurring due to the heart beat makes great disturbance to obtain the visual alignment among the vessel structure shown in the CCA frames. Therefore, the recorded vessel structure’s position in CCA varies within the frame sequence. This paper describes a hierarchical region based template matching technique to reconstruct the CCA by reducing the global motion artifacts. This proposed motion reduction technique is efficient and it reconstructs the CCA by reducing the background motion as desired. Experimental results of this method have shown its’ ability to maintain the visual alignment of the internal blood flow among the frames.
item: Thesis-Full-text
Improvement of coronary angiography for quantitative coronary analysis by using a computer vision technique
Kulathilake, KASH; Ranathunga, L
Coronary cine-angiography is an invasive medical image modality, which is widely used in Interventional Cardiology for the detection of stenosis in Coronary arteries. Quantitative coronary analysis is one of the demanding areas in medical imaging and in this study a semi automated quantitative coronary analysis method has been proposed. Direct coronary cineangiogram frames are processed in order to obtain the features of lumen such as, vessel boundary, skeleton and luminal diameter along the vessels’ skeleton as the results. The proposed method consists of four main implementation phases namely, pre-processing, segmentation, vessel path tracking and quantitative analysis. The visual quality of the input frames is enhanced within the pre-processing phase. The proposed segmentation phase is implemented based on a spatial filtering and region growing approach. A clinically important vessel region is processed to detect the vessel boundary and skeleton, which is required as prior knowledge for quantitative analysis. Moreover, the vessel diameter is computed while tracking the vessel skeleton path starting from a given seed. The proposed segmentation method possesses 93.73% mean segmentation accuracy and 0.053 mean fallout rate. Moreover, the proposed quantitative analysis method has been validated for assessing its’ technical supportability using a clinically approved data set. As a result of that, this proposed method computes the vessel diameter along the vessel skeleton in single pixel gap and develops the ability to determine the diameter stenosis as the quantitative analysis results. Additionally, the clinical feasibility of the proposed method has been validated to emphasize the clinical usability. Moreover, this study can be further extended to make clinical decisions on stenosis through the functional significance of the vasculature by using proper medical image modality like biplane angiography.
item: Conference-Abstract
Invariant properties of a locally salient dither pattern with a spatial-chromatic histogram
(2014-06-18) Bandara, AMRR; Ranathunga, L; Abdullah, NA
Compacted Dither Pattern Code (CDPC) is a recently found feature which is successful in irregular shapes based visual depiction. Locally salient dither pattern feature is an attempt to expand the capability of CDPC for both regular and irregular shape based visual depiction. This paper presents an analysis of rotational and scale invariance property of locally salient dither pattern feature with a two dimensional spatial-chromatic histogram, which expands the applicability of the visual feature. Experiments were conducted to exhibit rotational and scale invariance of the feature. These experiments were conducted by combining linear Support Vector Machine (SVM) classifier to the new feature. The experimental results revealed that the locally salient dither pattern feature with the spatial-chromatic histogram is rotationally and scale invariant.
item: Conference-Abstract
An investigation of quantization table modification on JPEG steganography
(2015-09-18) Senthooran, V; Ranathunga, L
Imperceptibility and the embedding capacity are the two most important aspects to be concerned in any image based steganographic research studies. It is necessarily considered to maximize the amount of embedding capacity while preserving the security against detection by unauthorized people in any steganographic methods. Many research studies have exposed that the modified quantization tables significantly reduce the distortion in the quality of stego-images and increase the embedding capacity of stego-images in DCT based steganographic techniques. In this paper, we investigate the aforementioned requirements in JPEG based steganographic techniques with the existing quantization table modification techniques by evaluating the experimental results and derive modified quantization tables to compare the previous results of some existing quantization modification techniques. Our experimental results reveal that the modified tables can provide a significance improvement in information-hiding capacity and visual quality than the other methods tested.