Clustering techniques such as K-means and Forgy as well as their improved version ISODATA group data around one seed point for each cluster. It is well known that these methods do not work well if the shape of the clu...
详细信息
Clustering techniques such as K-means and Forgy as well as their improved version ISODATA group data around one seed point for each cluster. It is well known that these methods do not work well if the shape of the cluster is elongated or nonconvex. We argue that for a elongated or nonconvex shaped cluster, more than one seed is needed, In this paper a multiseed clustering algorithm is proposed. A density based representative point selection algorithm is used to choose the initial seed points. To assign several seed points to one cluster, a minimal spanning tree guided novel technique is proposed. Also, a border point detection algorithm is proposed for the detection of shape of the cluster. This border in turn signifies whether the cluster is elongated or not. Experimental results show the efficiency of this clustering technique.
Skew angle detection of scanned documents containing most popular indian scripts (Devnagari and Bangla) is considered. Most characters in these scripts have horizontal lines at the top, called headlines. The character...
详细信息
Skew angle detection of scanned documents containing most popular indian scripts (Devnagari and Bangla) is considered. Most characters in these scripts have horizontal lines at the top, called headlines. The character head lines mostly join one another in a word and the word appears as a single component. In the proposed method the components are at first labeled. The upper envelope of a component is found by columnwise scanning from an imaginary line above the component. Portions of upper envelope satisfying the properties of digital straight line are detected. They are clustered as belonging to single text lines. Estimates from individual clusters are combined to get the skew angle. Apart from accuracy and efficiency, an advantage of the method is that character segmentation and zone detection can be readily done from head line information, which is useful in Optical Character recognition approaches of these scripts.
In this paper we propose a neural network model to synthesise texture images. The model is based on a continuous Hopfield-like network where each pixel of the image is occupied by a neuron that is eight-connected to i...
详细信息
In this paper we propose a neural network model to synthesise texture images. The model is based on a continuous Hopfield-like network where each pixel of the image is occupied by a neuron that is eight-connected to its neighbours. A state of the neuron denotes a certain grey level of the corresponding pixel. The firing of the neuron changes its state, and hence the grey level of the corresponding pixel. Different two-tone and grey-tone texture images can be synthesised by manipulating the connection weights and by varying the algorithm iteration number. For grey-tone texture synthesis, a Markov chain principle has been employed to decide on the multiple state transition of a neuron. The model can be employed for texture propagation with the advantage that it allows propagation without showing any blocky effect.
An NLP system for indian languages should have a lexical subsystem that is driven by a morphological analyzer. Such an analyzer should be able to parse a word into its constituent morphemes and obtain lexical projecti...
详细信息
An NLP system for indian languages should have a lexical subsystem that is driven by a morphological analyzer. Such an analyzer should be able to parse a word into its constituent morphemes and obtain lexical projection of the word as a unification of the projections of the constituent morphemes. Lexical projections considered here are f-structures of the Lexical Functional Grammar (LFG). A formalism has been proposed, by which the lexicon writer may specify the lexicon in four levels. The specifications are compiled into a stored lexical knowledge base on one hand and a formulation of derivational morphology called Augmented Finite State Automata (AFSA) on the other to achieve a compact lexical representation. The aspects of AFSA, especially its power of morphological parsing of words in a computationally attractive manner, has been discussed. An additional utility of the AFSA, in the form of spelling error corrector, has also been discussed. Bangla, or Bengali is considered as a case study. Implementation notes based on object-oriented programming principles has been provided.
This paper presents an application of backpropagation neural network for the detection of linear structures in remote-sensing images. The purpose of the approach is two-fold. First, to exploit the advantages of a neur...
详细信息
This paper presents an application of backpropagation neural network for the detection of linear structures in remote-sensing images. The purpose of the approach is two-fold. First, to exploit the advantages of a neural network classifier over the tranditional ones. Second, to avoid the strategic phases of enhancement and thresholding. Once the network is learnt, the classification scheme is real-time. Two critical issues in the present approach an the selection of the network architecture and the rate of convergence of learning. Solutions to these two problems are proposed. Experimental results on IRS and SPOT images are presented. Satisfactory classification results have been obtained using the network.
Given a set of points in multi-dimensional space, we propose a new definition for the neighbors of an arbitrary point P. The definition tries to capture the idea that the neighbors should be as near to P and as symmet...
详细信息
Given a set of points in multi-dimensional space, we propose a new definition for the neighbors of an arbitrary point P. The definition tries to capture the idea that the neighbors should be as near to P and as symmetrically placed around P as possible. In contrast, the conventional nearest neighborhood considers only nearness as the criterion for neighborhood. We propose an iterative procedure to compute the neighbors where the first neighbor is the nearest neighbor. The second and other neighbors are chosen so that at any stage the distance between the centroid of the neighbors and P is as small as possible. The centroid criterion takes care of symmetrical placement of the neighbors. One can use median instead of centroid to define the neighbors. The new definition is free from any user-specified parameter and can be used for pattern classification, clustering and low-level description of dot patterns.
This paper considers optical character recognition (OCR) of Bangla, the second most popular script in the indian subcontinent. A complete OCR system is described for documents of single Bangla font, where more than th...
详细信息
This paper considers optical character recognition (OCR) of Bangla, the second most popular script in the indian subcontinent. A complete OCR system is described for documents of single Bangla font, where more than three hundred character shapes are recognized by a combination of template and feature-matching approach. Here the document image captured by a flatbed scanner is subject to tilt correction, line, word and character segmentation, simple and compound character separation, feature extraction and finally character recognition. Some character occurrence statistics have been computed to aid the recognition process. The simple character recognition is done by a feature-based tree classifier, and the compound character recognition involves a template matching approach preceded by a feature-based grouping. At present, recognition accuracy of about 96% is obtained by the system.
Extraction of some meta-information from printed documents without carrying out optical character recognition (OCR) is considered. It can be statistically verified that important terms in technical articles are mainly...
详细信息
ISITRA is a new scheme of signal decomposition and reconstruction. In ISITRA, the space of PRF sets is much larger and more well-behaved than that in the existing schemes like filter bank or wavelets. Since such a spa...
详细信息
This paper looks at the problem of searching for indian language (IL) content on the Web. Even though the amount of IL content that is available on the Web is growing rapidly, searching through this content using the ...
详细信息
ISBN:
(纸本)9781605584164
This paper looks at the problem of searching for indian language (IL) content on the Web. Even though the amount of IL content that is available on the Web is growing rapidly, searching through this content using the most popular websearch engines poses certain problems. Since the popular search engines do not use any stemming / orthographic normalization for indian languages, recall levels for IL searches can be low. We provide some examples to indicate the extent of this problem, and suggest a simple and efficient solution to the problem. Copyright 2008 ACM.
暂无评论