Showing papers by "Santanu Chaudhury published in 2001"

Recognizing large 3-D objects through next view planning using an uncalibrated camera

Abstract: We present a new on-line scheme for the recognition and pose estimation of a large isolated 3-D object, which may not entirely fit in a camera's field of view. We do not assume any knowledge of the internal parameters of the camera, or their constancy. We use a probabilistic reasoning framework for recognition and next view planning. We show results of successful recognition and pose estimation even in cases of a high degree of interpretation ambiguity associated with the initial view.

A model guided document image analysis scheme

Abstract: This paper presents a new model-based document image segmentation scheme that uses XML-DTDs (eXtensible Markup Language Document Type Definitions). Given a document image, the algorithm has the ability to select the appropriate model. A new wavelet-based tool has been designed for distinguishing text from non-text regions and characterization of font sizes. Our model-based analysis scheme makes use of this tool for identifying the logical components of a document image.

Reconstruction-based recognition of scenes with translationally repeated quadrics

Abstract: This paper addresses the problem of invariant-based recognition of quadric configurations from a single image. These configurations consist of a pair of rigidly connected translationally repeated quadric surfaces. This problem is approached via a reconstruction framework. A new mathematical framework, using relative affine structure, on the lines of Luong and Vieville (1996), has been proposed. Using this mathematical framework, translationally repeated objects have been projectively reconstructed, from a single image, with four image point correspondences of the distinguished points on the object and its translate. This has been used to obtain a reconstruction of a pair of translationally repeated quadrics. We have proposed joint projective invariants of a pair of proper quadrics. For the purpose of recognition of quadric configurations, we compute these invariants for the pair of reconstructed quadrics. Experimental results on synthetic and real images, establish the discriminatory power and stability of the proposed invariant-based recognition strategy. As a specific example, we have applied this technique for discriminating images of monuments which are characterized by translationally repeated domes modeled as quadrics.

A Framework for Reconstruction based Recognition of Partially Occluded Repeated Objects

Abstract: In this paper we propose a reconstruction based recognition scheme for objects with repeated components, using a single image of such a configuration, in which one of the repeated components may be partially occluded. In our strategy we reconstruct each of the components with respect to the same frame and use these to compute invariants.We propose a new mathematical framework for the projective reconstruction of affinely repeated objects. This uses the repetition explicitly and hence is able to handle substantial occlusion of one of the components. We then apply this framework to the reconstruction of a pair of repeated quadrics. The image information required for the reconstruction are the outline conic of one of the quadrics and correspondence between any four points which are images of points in general position on the quadric and its repetition. Projective invariants computed using the reconstructed quadrics have been used for recognition. The recognition strategy has been applied to images of monuments with multi-dome architecture. Experiments have established the discriminatory ability of the invariants.

Knowledge representation for Web based services in a multi-cultural environment

Abstract: With the Internet being a global resource, Web based applications need to break the barriers of language and culture. The core of an intelligent Web based application comprises an ontological description of the domain. A domain ontology needs a medium for expression, which usually consists of terminology borrowed from a natural language. Thus, a knowledge based application becomes susceptible to linguistic and cultural context. The authors present a novel knowledge representation technique that distinguishes between the abstract concepts in a domain and their expressions. It can associate expressions from different languages with the concepts in an ontology network. Non-textual symbols and media property specifications can also be used to express the concepts using this technique. The resulting ontology can thus be used in a multi-lingual and multi-cultural environment. An RDF based language is used as a vehicle for the knowledge representation scheme.

Making Indian Language Legacy Documents Accessible Via Web

Abstract: The reliable optical character recognition is not available for scripts of Indian languages. Thus, the only way to make legacy documents in Indian languages available on the web is by scanning them. This work is an attempt to cater to the need for a better representation and efficient storage technique for Indian language documents and their near perfect regeneration at the browser. We work with the segments (corresponding to text, image or white spaces) extracted from the original document page. For compressing the segments separately, we use Shape-Adaptive Wavelet based coding scheme, Run Length encoding and Arithmetic Bit-plane coding. An XML representation scheme is being used to represent the document page and the data is stored at a server. A plug-in has been implemented that decodes the data encoded coming from the server and displays the document page on the web browser thereby making the document pages web accessible. keywords: document image analysis, shape adaptive compression, entropy based quantization, eBooks

A New Look at Books: E-books

Abstract: E-book refers to books in Electronic form. In this paper we provide a review of the technological issues involved in design and construction of e-books. We also address the issues involved in designing e-books in Indian languages. We have proposed a novel scheme for construction and delivery of legacy documents (in Indian and other languages) in the form of e-books with the facility of hyper-linking and indexing of various logical components in the document image.

Guest Editorial: Introduction to IT Enabled Services

Abstract: Information Technology is the umbrella term that encompasses the entire field of information processing, information storage and information dissemination using computer and communication technology. Due to the rapid expansion of information infrastructure, the interdependent capacities for digital communication and computational power, every aspect of our life is being transformed by information technology. Emerging services, enabled by the power of information technology, are now offering hitherto unknown facilities in the field of health-care, governance, education, finance and commerce, communication, entertainment and culture.