Showing papers by "Santanu Chaudhury published in 2003"
TL;DR: A recognition engine is developed which can reliably recognize these gestures despite individual variations and has the ability to detect start and end of gesture sequences in an automated fashion.
167 citations
03 Aug 2003
TL;DR: This paper has proposed an access mechanism based on word based indexing and personalized annotation based hyperlinking and queryscheme for providing an interactive access interface to acollection of Indian language documents.
Abstract: A large volume of legacy documents in Indian languagesexist only in paper form. Web based interactive access techniquesfor images of these documents can ensure wider disseminationand easy availability. In this paper, we haveproposed an access mechanism based on word based indexingand personalized annotation. The word based indexingscheme exploits typical structural characteristics of Indianscripts. We have combined this word indexing techniquewith personalized annotation based hyperlinking and queryscheme for providing an interactive access interface to acollection of Indian language documents.
22 citations
01 Apr 2003
TL;DR: A characterization of errors in aspect graphs is presented, as well as an algorithm for estimating aspect graphs, given noisy sensor data.
Abstract: Many three-dimensional (3D) object recognition strategies use aspect graphs to represent objects in the model base. A crucial factor in the success of these object recognition strategies is the accurate construction of the aspect graph, its ease of creation, and the extent to which it can represent all views of the object for a given setup. Factors such as noise and nonadaptive thresholds may introduce errors in the feature detection process. This paper presents a characterization of errors in aspect graphs, as well as an algorithm for estimating aspect graphs, given noisy sensor data. We present extensive results of our strategies applied on a reasonably complex experimental set, and demonstrate applications to a robust 3D object recognition problem.
7 citations
06 Jul 2003
TL;DR: This work presents a novel scheme that enables fully automatic extraction of semantic video objects for a class of sequences, and their supervised organization in an object-class hierarchy.
Abstract: We present a novel scheme for object-based video sequence presentation using appearance spaces. Our scheme enables fully automatic extraction of semantic video objects for a class of sequences, and their supervised organization in an object-class hierarchy. The hierarchy can be used for generic classification of query video objects, and transcoding using semantics of video objects.
3 citations
TL;DR: Different soft computing based approaches for image processing and segmentation, which can improve the diagnostic value of the images are reviewed and an architectural framework forsoft computing based application development is suggested.
Abstract: The use of soft computing techniques for medical image analysis is reviewed in this paper. These techniques involve application of fuzzy logic, neural network and evolutionary algorithms. We introduce the different imaging modalities and motivation for using soft computing techniques for medical image analysis. We review different soft computing based approaches for image processing and segmentation, which can improve the diagnostic value of the images. We also present some results with MRI images. Based on these approaches we suggest an architectural framework for soft computing based application development.
1 citations
TL;DR: A description of a system which can extract video object based representation of video sequences and builds up a video objectbased description of the content of the video collection is presented.
Abstract: In this paper, we focus on content based access and manipulation techniques for digital video. We review different techniques developed for extraction of contents of video using visual information. We then present description of a system which can extract video object based representation of video sequences and builds up a video object based description of the content of the video collection. We also present a brief review of another technology which provides for interactive manipulation of the video content through interaction with audio-visual objects like digital actors.