Chathura De Silva - Profile on Academia.edu (original) (raw)
Uploads
Papers by Chathura De Silva
SiFEB -- A Simple, Interactive and Extensible Robot Playmate for Kids
2014 4th International Conference on Artificial Intelligence with Applications in Engineering and Technology, 2014
In this paper we present work in progress on SiFEB, a simple, interactive and extensible robot pl... more In this paper we present work in progress on SiFEB, a simple, interactive and extensible robot playmate for kids intended to nurture the engagement in STEM (Science, Technology, Engineering and Mathematics) related activities through playing. SiFEB's simplified and interactive hardware and software modules present users without prior experience, with the ability to build robots without going deep in either aspect. Kids can build robots of their interest using attachable hardware modules and related programming components using an easy to understand visual programming language that resembles natural commands. The potential developers may utilize the framework provided, to build hardware and software components to the system expanding the existing capabilities. Preliminary results from the prototypes show that SiFEB has the potential of being an effective learning platform for young children in STEM related areas.
A new radial basis function network classifier for holistic recognition of universal facial expressions
According to psychologists there are six types of universal facial expressions namely, "fear", "s... more According to psychologists there are six types of universal facial expressions namely, "fear", "surprise", "anger", "sad", "disgust" and "happy". Holistic recognition of these facial expressions from static images requires nonlinear classifiers capable of operating on noisy high-dimensional feature spaces. Often radial basis function networks (RBFN) are used for classification in these applications. Conventional RBF networks however, in spite of their capabilities in working with high-dimensional feature spaces, often fail to deliver satisfactory performance in these scenarios due to small training sample sets, noisy features and/or features not following the required class structure. This paper presents an improved RBFN architecture that overcomes these problems through asymmetrical scaling of feature axes according to specific requirements of the class structure of the classification problem. The scaling factors are computed automatically from the available training samples, without any explicit analysis of their multivariate statistical properties. The proposed network yielded an overall recognition rate of over 92% for the 6 expression classes, and a smaller network size compared to other types of RBFN classifiers.
Pattern Recognition, 2008
The paper presents novel modifications to radial basis functions (RBFs) and a neural network base... more The paper presents novel modifications to radial basis functions (RBFs) and a neural network based classifier for holistic recognition of the six universal facial expressions from static images. The new basis functions, called cloud basis functions (CBFs) use a different feature weighting, derived to emphasize features relevant to class discrimination. Further, these basis functions are designed to have multiple boundary segments, rather than a single boundary as for RBFs. These new enhancements to the basis functions along with a suitable training algorithm allow the neural network to better learn the specific properties of the problem domain. The proposed classifiers have demonstrated superior performance compared to conventional RBF neural networks as well as several other types of holistic techniques used in conjunction with RBF neural networks. The CBF neural network based classifier yielded an accuracy of 96.1%, compared to 86.6%, the best accuracy obtained from all other conventional RBF neural network based classification schemes tested using the same database. ᭧
An edge detection scheme using radial basis function networks
A new edge detection scheme based on radial basis function networks is proposed. It is a two-tier... more A new edge detection scheme based on radial basis function networks is proposed. It is a two-tiered scheme where, in the first stage, each pixel in the input image is classified according to its potential for being part of an edge. The second stage then combines these pixels into true edges in the input image. Both stages use radial basis function networks. The scheme illustrates how the input space of edge patterns can be used to train the neural network with a minimum number of parameters. Compared with other neural network paradigms, the proposed scheme is simpler in terms of network size and computational requirements, and provides better results even in low-contrast images
A faster image registration and stitching algorithm
Abstract This paper presents a new algorithm for Image Registration and Stitching. The algorithm ... more Abstract This paper presents a new algorithm for Image Registration and Stitching. The algorithm is designed to be extremely efficient and fast in its execution and is intended for use in stitching images extracted from a video stream of a camera. This algorithm is not ...
We have developed a low cost, WebCam based optical barcode reader, which can extract and decode t... more We have developed a low cost, WebCam based optical barcode reader, which can extract and decode the sequence on a cluttered background. It is composed of three functions: barcode localization from the raw image, transformation of the localized barcode and decoding the sequence with an intelligent algorithm. The localization method is based on detecting the areas with the maximum density difference in two normal directions. The transformation method, capable of identifying any orientation, is based on the Hough line detection method. The decoding method is based on the peak/valley detection method of the barcode waveform and a consistency checking method. The consistency checking method, a constraint network, employs artificial intelligence searching methods. The algorithms used in the barcode reader have been tested on hundreds of images with an accuracy of more than 99%.
SiFEB -- A Simple, Interactive and Extensible Robot Playmate for Kids
2014 4th International Conference on Artificial Intelligence with Applications in Engineering and Technology, 2014
In this paper we present work in progress on SiFEB, a simple, interactive and extensible robot pl... more In this paper we present work in progress on SiFEB, a simple, interactive and extensible robot playmate for kids intended to nurture the engagement in STEM (Science, Technology, Engineering and Mathematics) related activities through playing. SiFEB's simplified and interactive hardware and software modules present users without prior experience, with the ability to build robots without going deep in either aspect. Kids can build robots of their interest using attachable hardware modules and related programming components using an easy to understand visual programming language that resembles natural commands. The potential developers may utilize the framework provided, to build hardware and software components to the system expanding the existing capabilities. Preliminary results from the prototypes show that SiFEB has the potential of being an effective learning platform for young children in STEM related areas.
A new radial basis function network classifier for holistic recognition of universal facial expressions
According to psychologists there are six types of universal facial expressions namely, "fear", "s... more According to psychologists there are six types of universal facial expressions namely, "fear", "surprise", "anger", "sad", "disgust" and "happy". Holistic recognition of these facial expressions from static images requires nonlinear classifiers capable of operating on noisy high-dimensional feature spaces. Often radial basis function networks (RBFN) are used for classification in these applications. Conventional RBF networks however, in spite of their capabilities in working with high-dimensional feature spaces, often fail to deliver satisfactory performance in these scenarios due to small training sample sets, noisy features and/or features not following the required class structure. This paper presents an improved RBFN architecture that overcomes these problems through asymmetrical scaling of feature axes according to specific requirements of the class structure of the classification problem. The scaling factors are computed automatically from the available training samples, without any explicit analysis of their multivariate statistical properties. The proposed network yielded an overall recognition rate of over 92% for the 6 expression classes, and a smaller network size compared to other types of RBFN classifiers.
Pattern Recognition, 2008
The paper presents novel modifications to radial basis functions (RBFs) and a neural network base... more The paper presents novel modifications to radial basis functions (RBFs) and a neural network based classifier for holistic recognition of the six universal facial expressions from static images. The new basis functions, called cloud basis functions (CBFs) use a different feature weighting, derived to emphasize features relevant to class discrimination. Further, these basis functions are designed to have multiple boundary segments, rather than a single boundary as for RBFs. These new enhancements to the basis functions along with a suitable training algorithm allow the neural network to better learn the specific properties of the problem domain. The proposed classifiers have demonstrated superior performance compared to conventional RBF neural networks as well as several other types of holistic techniques used in conjunction with RBF neural networks. The CBF neural network based classifier yielded an accuracy of 96.1%, compared to 86.6%, the best accuracy obtained from all other conventional RBF neural network based classification schemes tested using the same database. ᭧
An edge detection scheme using radial basis function networks
A new edge detection scheme based on radial basis function networks is proposed. It is a two-tier... more A new edge detection scheme based on radial basis function networks is proposed. It is a two-tiered scheme where, in the first stage, each pixel in the input image is classified according to its potential for being part of an edge. The second stage then combines these pixels into true edges in the input image. Both stages use radial basis function networks. The scheme illustrates how the input space of edge patterns can be used to train the neural network with a minimum number of parameters. Compared with other neural network paradigms, the proposed scheme is simpler in terms of network size and computational requirements, and provides better results even in low-contrast images
A faster image registration and stitching algorithm
Abstract This paper presents a new algorithm for Image Registration and Stitching. The algorithm ... more Abstract This paper presents a new algorithm for Image Registration and Stitching. The algorithm is designed to be extremely efficient and fast in its execution and is intended for use in stitching images extracted from a video stream of a camera. This algorithm is not ...
We have developed a low cost, WebCam based optical barcode reader, which can extract and decode t... more We have developed a low cost, WebCam based optical barcode reader, which can extract and decode the sequence on a cluttered background. It is composed of three functions: barcode localization from the raw image, transformation of the localized barcode and decoding the sequence with an intelligent algorithm. The localization method is based on detecting the areas with the maximum density difference in two normal directions. The transformation method, capable of identifying any orientation, is based on the Hough line detection method. The decoding method is based on the peak/valley detection method of the barcode waveform and a consistency checking method. The consistency checking method, a constraint network, employs artificial intelligence searching methods. The algorithms used in the barcode reader have been tested on hundreds of images with an accuracy of more than 99%.