Computer Science: Recent submissions

  • An adaptive technique for handwritten Tamil character recognition 
    Sarveswaran, K.; Ratnaweera, D.A.A.C. (IEEE, 2007-11)
    Handwritten character recognition is playing a vital role in many areas of modern world. Even though considerable research work has been done in handwritten character recognition, comparatively fewer efforts have been made ...
  • Speeded-up and Compact Visual Codebook for Object Recognition 
    Barathy, M.; Ramanan, A.; Mahesan, S.; Pinidiyaarachchi, U.A.J. (International Journal of Image Processing (IJIP), 2013)
    The well known framework in the object recognition literature uses local information extracted at several patches in images which are then clustered by a suitable clustering technique. A visual codebook maps the ...
  • Control chart pattern clustering using a new self-organizing spiking neural network 
    Pham, D. T.; Packianather, M.S.; Charles, Eugene Yougarajah Andrew (Proceedings of the Institution of Mechanical Engineers, 2008-10-01)
    This paper focuses on the architecture and learning algorithm associated with using a new self-organizing delay adaptation spiking neural network model for clustering control chart patterns. This temporal coding spiking ...
  • Reproducing opportunistic connectivity traces using connectivity models 
    Thabotharan, Kathiravelu; Pears, A. (ACM New York, NY, USA ©2007, 2007-12-10)
    Opportunistic networking is a new communication paradigm which explores the potential of inter-device contacts due to human mobility [3, 5]. Intermittent connectivity, non existence of an end-to-end path between nodes and ...
  • Towards designing a routing protocol for opportunistic networks 
    Thabotharan, Kathiravelu; Ranasinghe, N.; Perera, A. (IEEE, 2010)
    Intermittently connected opportunistic networks experience frequent disconnections and shorter contact durations. Therefore routing of messages towards their destinations needs to be handled from various points of view. ...
  • An enhanced congestion aware adaptive routing protocol for opportunistic networks 
    Thabotharan, Kathiravelu; Ranasinghe, N.; Perera, A. (IEEE, 2011-08)
    The adaptive routing protocol recently proposed by researchers for opportunistic networks often makes an assumption that when each node makes an intelligent decision of choosing a best forwarder node to route its messages, ...
  • Approaches to P2P Internet Application Development 
    Thabotharan, Kathiravelu; Pears, A. (Computer Science and Information Systems, 2011-09-21)
    Research in overlay and P2P networking has been tightly focused on fundamentals in the last few years, leading to developments on a range of important issues. The time has come to integrate these insights into existing and ...
  • What & when?: Distributing Content in Opportunistic Networks 
    Kathiravelu, T.; Pears, A. (Wireless and Mobile Communications,, 2006)
    Tomorrow's mobile data exchanges will often occur using intermittent connectivity and the design and development of mobility models, applications, protocols and infrastructures are an essential part of future research in ...
  • A level set based deformable model for segmenting tumors in medical images 
    Suthakar, Somaskandan; Mahesan, Sinnathamby (IEEE, 2012-03)
    Tumor segmentation from medical image data is a challenging task due to the high diversity in appearance of tumor tissue among different cases. In this paper we propose a new level set based deformable model to segment the ...
  • An efficient and speeded-up tree for multi-class classification 
    Ranganathan, P.; Ramanan, A.; Niranjan, M. (IEEE, 2012-09)
    Support vector machine is a state-of-the-art learning machine that is used in areas, such as pattern recognition, computer vision, data mining and bioinformatics. SVMs were originally developed for solving binary classification ...
  • A Review of Codebook Models in Patch-Based Visual Object Recognition 
    Ramanan, A.; Niranjan, M. (Springer Science+Business Media, LLC, 2011)
    The codebook model-based approach, while ignoring any structural aspect in vision, nonetheless provides state-of-the-art performances on current datasets. The key role of a visual codebook is to provide a way to map the ...
  • A one-pass resource-allocating codebook for patch-based visual object recognition 
    Ramanan, A.; Niranjan, M. (IEEE, 2010)
    Frequencies of occurrence of low-level image features is the representation of choice in the design of state-of-the-art visual object recognition systems. A crucial step in this process is the construction of a codebook ...
  • Robust invariant descriptors for visual object recognition 
    Barathy, Ganesharajah; Mahesan, Sinnathamby; Pinidiyaarachchi, U.A.J (IEEE, 2011)
    In the state-of-the-art visual object recognition, there are a number of descriptors that have been proposed for various visual recognition tasks. But it is still difficult to decide which descriptors have more significant ...
  • Sequential hierarchical pattern clustering 
    Farran, B.; Ramanan, A.; Niranjan, M. (Springer Berlin Heidelberg, 2009-09-07)
    Clustering is a widely used unsupervised data analysis technique in machine learning. However, a common requirement amongst many existing clustering methods is that all pairwise distances between patterns must be computed ...
  • Control chart pattern clustering using a new self-organizing spiking neural network 
    Pham, D.T; Packianather, M.S; Charles, Eugene Yougarajah Andrew (IMechE, 2008)
    This paper focuses on the architecture and learning algorithm associated with using a new self-organizing delay adaptation spiking neural network model for clustering control chart patterns. This temporal coding spiking ...
  • A self-organising spiking neural network trained using delay adaptation 
    Pham, D.T; Packianather, M.S; Charles, Eugene Yougarajah Andrew (IEEE, 2007-06)
    This paper proposes a self-organising delay adaptation spiking neural network model for clustering control chart patterns. This temporal coding spiking neural network model employs a Hebbian-based rule to shift the connection ...
  • A Novel Self-Organised Learning Model with Temporal Coding for Spiking Neural Networks 
    Pham, D.T; Packianather, M.S; Charles, Eugene Yougarajah Andrew (Elsevier Ltd, 2006-07)
    This chapter proposes a novel self-organized learning model with temporal coding for a network of spiking neurons, which encode information through the timing of action potentials. The development of this learning model ...
  • Resource-allocating codebook for patch-based face recognition 
    Ramanan, A.; Niranjan, M. (IEEE, 2009-12)
    In this paper we propose a novel approach to constructing a discriminant visual codebook in a simple and extremely fast way as a one-pass, that we call Resource-Allocating Codebook (RAC), inspired by the Resource Allocating ...
  • Speeding up multi-class texture classification by one-pass vocabulary design and decision tree 
    Ramanan, A.; Ranganathan, P.; Niranjan, M. (IEEE, 2011-08)
    The bag-of-keypoints representation started to be used as a black box providing reliable and repeatable measurements from images for a wide range of applications such as visual object recognition and texture classification. ...
  • Unbalanced decision trees for multi-class classification 
    Ramanan, A.; Suppharangsan, S.; Niranjan, M. (IEEE, 2007-08)
    In this paper we propose a new learning architecture that we call Unbalanced Decision Tree (UDT), attempting to improve existing methods based on Directed Acyclic Graph (DAG) [1] and One-versus-All (OVA) [2] approaches to ...