Research Publications

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194

This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.

Browse

Filters

2018 - 201912020 - 20253

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Feature extraction

Search Results

Now showing 1 - 4 of 4
  • Thumbnail Image
    PublicationOpen Access
    Feature Analysis of Blood Spatter Patterns with Image Processing
    (Faculty of Engineering, 2025-09-09) Khemaratne, T; Malasinghe, L
    Bloodstain Pattern Analysis (BPA) is a vital component in forensic investigations that aids in reconstructing the sequence of events at a crime scene. It is centralized in and revolves around the categorization of the patterns based on their features, as this is the most significant and critical stage of BPA. Therefore, a preliminary measure of BPA is via the thorough evaluation of images photographed of the crime scene to collect evidence as much as possible to arrive at the correct conclusion and to deduce the relevant details accurately. However, currently existing BPA methods are vulnerable to subjectivity, hence which can lead to pre-assumptions, without thoroughly and completely observing the crime scene, and consequently cause the arrival of incorrect conclusions and discrepancies in BP feature classification. Additionally, other flaws such as unintentional crime scene contamination and evidence tampering exist in these current methods as well. Henceforth, it is imperative that a novel method is constructed to eliminate these issues and arrive at the correct conclusions. This study introduces a robust image-processing-based methodology for extracting and quantifying bloodstain pattern features, thereby enhancing objectivity and reducing human error. The proposed technique encompasses critical stages: image acquisition, preprocessing, segmentation, feature extraction, and analysis. Through the use of image enhancement and segmentation algorithms, essential attributes such as impact angles, tail-to-body ratios, shape irregularities, and distribution densities are computed. The results were validated against original findings and show close agreement in feature values such as convergence area and circularity. The approach demonstrates the potential to integrate with existing BPA tools, facilitating automated, accurate, and reproducible forensic analysis.
  • Thumbnail Image
    PublicationOpen Access
    Real-time Multi-spectral Iris Extraction in Diversified Eye Images Utilizing Convolutional Neural Networks
    (IEEE, 2024-07-03) Rathnayake, R; Madhushan, N; Jeeva, A; Darshani, D; Pathirana, I; Ghosh, S; Subasinghe, A; Silva, B N; Wijenayake, U
    Iris extraction has gained prominence due to its application versatility across many domains. However, achieving real-time iris extraction poses challenges due to several factors. Learning-based algorithms outperform non-learning-based iris extraction methods, delivering superior accuracy and performance. In response, this article proposes a Convolutional Neural Networks (CNN)-based, accurate direct iris extraction mechanism for a broad spectrum of eye images. The innovation of our approach lies in its proficiency with varied image types, including those where the iris is partially obscured by the eyelid. We enhance the method’s reliability by introducing a modified Circular Hough Transform (CHT). Extensive testing demonstrates our method’s excellent real-time performance across diverse image types, even under challenging conditions. These findings underscore the proposed method’s potential as a cost-effective and computationally efficient solution for real-time iris extraction in varied application domains.
  • Thumbnail Image
    PublicationEmbargo
    A Data Mining Approach to Identify the Factors Affecting the Academic Success of Tertiary Students in Sri Lanka
    (Springer, Cham, 2018-02-11) Kasthuriarachchi, S; Bhatt, C. M; Liyanage, S. R
    Educational Data Mining has become a very popular and highly important area in the domain of Data mining . Application of data mining to education arena arises as a paradigm oriented to design models, methods, tasks and algorithms for discovering data from educational domain. It attempts to uncover data patterns, structure association rules, establish information of unseen relationships with educational data and many more operations that cannot be performed using traditional computer based information systems. It grows and adopts statistical methods, data mining methods and machine-learning to study educational data produced mostly by students, educators, educational management policy makers and instructors. The main objective of applying data mining in education is primarily to advance learning by enabling data oriented decision making to improve existing educational practices and learning materials. This study focuses on finding the key factors affecting the performance of the students enrolled for technology related degree programs in Sri Lanka. The findings of this study will positively affect the future decisions about the progress of the students’ performance, quality of the education process and the future of the education provider.
  • Thumbnail Image
    PublicationEmbargo
    NoFish; Total Anti-Phishing Protection System
    (2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Atimorathanna, D.N.; Ranaweera, T.S.; Pabasara, R.A.H.D.; Perera, J.R.; Abeywardena, K.Y.
    Phishing attacks have been identified by researchers as one of the major cyber-attack vectors which the general public has to face today. Although many vendors constantly launch new anti-phishing products, these products cannot prevent all the phishing attacks. The proposed solution, “NoFish” is a total anti-phishing protection system created especially for end-users as well as for organizations. This paper proposes a machine learning & computer vision-based approach for intelligent phishing detection. In this paper, a realtime anti-phishing system, which has been implemented using four main phishing detection mechanisms, is proposed. The system has the following distinguishing properties from related studies in the literature: language independence, use of a considerable amount of phishing and legitimate data, real-time execution, detection of new websites, detecting zero hour phishing attacks and use of feature-rich classifiers, visual image comparison, DNS phishing detection, email client plugin and especially the overall system is designed using a level-based security architecture to reduce the time-consumption. Users can simply download the NoFish browser extension and email plugin to protect themselves, establishing a relatively secure browsing environment. Users are more secure in cyberspace with NoFish which depicts a 97% accuracy level.