Abstract

Digitized books and manuscripts in digital libraries are often stored as images or graphics. They are not searchable at the content level due to the lack of OCRs or poor quality of the scanned images. Portable Document Format (PDF) has emerged as the most popular document representation schema for wider access across platforms. When there is no textual (UNICODE, ASCII) representation available, scanned images are stored in the graphics stream of PDF. In this paper, we propose a novel solution to search the textual data in graphics stream of the PDF files at content level. The proposed solution is demonstrated by enhancing an open source PDF viewer (Xpdf). Indian language support is also provided. Users can type a word in Roman (ITRANS), view it in a font, and search in textual and graphics stream of PDF documents simultaneously.

Abstract

This paper presents a novel approach to construct an eigen space representation from limited number of views, which is equivalent to the one obtained from large number of images captured from multiple view points. This procedure implicitly incorporates a novel view synthesis algorithm in the eigen space construction process. Inherent information in an appearance representation is enhanced using geometric computations. We experimentally verify the performance for orthographic, affine and projective camera models. Recognition results on the COIL and SOIL image database are promising.

Abstract

For the first time, search is enabled over a massive collection of 21 Million word images from digitized document images. This work advances the state-of-the-art on multiple fronts: i) Indian language document images are made searchable by textual queries, ii) interactive content-level access is provided to document images for search and retrieval, iii) a novel recognition-free approach, that does not require an OCR, is adapted and validated iv) a suite of image processing and pattern classification algorithms are proposed to efficiently automate the process and v) the scalability of the solution is demonstrated over a large collection of 500 digitised books consisting of 75,000 pages. Character recognition based approaches yield poor results for developing search engines for Indian language document images, due to the complexity of the script and the poor quality of the documents. Recognition free approaches, based on word-spotting, are not directly scalable to large collections, due to the computational complexity of matching images in the feature space. For example, if it requires 1 mSec to match two images, the retrieval of documents to a single query, from a large collection like ours, would require close to a day’s time. In this paper we propose a novel automatic annotation based approach to provide textual description of document images. With a one time, offline computational effort, we are able to build a text-based retrieval system, over annotated images. This system has an interactive response time of about 0.01 second. However, we pay the price in the form of massive offline computation, which is performed on a cluster of 35 computers, for about a month. Our procedure is highly automatic, requiring minimal human intervention

Abstract

This paper presents an approach to identify the importance of different parts of a video sequence from the recognition point of view. It builds on the observations that: (1) events consist of more fundamental (or atomic) units, and (2) a discriminant-based approach is more appropriate for the recognition task, when compared to the standard modelling techniques, such as PCA, HMM, etc. We introduce discriminative actions which describe the usefulness of the fundamental units in distinguishing between events. We first extract actions to capture the fine characteristics of individual parts in the events. These actions are modelled and their usefulness in discriminating between events is estimated as a score. The score highlights the important parts (or actions) of the event from the recognition aspect. Applicability of the approach on different classes of events is demonstrated along with a statistical analysis.

Abstract

This paper presents a vision-based control for positioning a camera with respect to an unknown piecewise planar object. We introduce a novel homography-based approach that integrates information from multiple homographies to reliably estimate the relative displacement of the camera. This approach is robust to image measurement errors and provides a stable estimate of the camera motion that is free from degeneracies in the task space. We also develop a new control formulation that meets the contradictory requirements of producing a decoupled camera trajectory and ensuring object visibility by only utilizing the homography relating the two views. Experimental results validate the efficiency and robustness of our approach and demonstrate its applicability

Abstract

In this paper we address the problem of temporal segmentation of videos. We present a multi-modal approach where clues from different information sources are merged to perform the segmentation. Specifically, we segment videos based on textual descriptions or commentaries of the action in the video. Such a parallel information is available for cricket videos, a class of videos where visual feature based (bottom-up) scene segmentation algorithms generally fail, due to lack of visual dissimilarity across space and time. With additional topdown information from textual domain, these ambiguities could be resolved to a large extent. The video is segmented to meaningful entities or scenes, using the scene level descriptions provided by the commentary. These segments can then be automatically annotated with the respective descriptions. This allows for a semantic access and retrieval of video segments, which is difficult to obtain from existing visual feature based approaches. We also present techniques for automatic highlight generation using our scheme.

Abstract

Terrains and other geometric models have been traditionally storedlocally. Their remote access presents the characteristics that are acombination of data serving such as files and real-time streaminglike audio-visual media. In this sketch we describe a client-serversystem to serve and stream large terrains to heterogenous clients.This process is sensitive to both the client’s capabilities as well asthe available network bandwidth. Level of Detail and view predic-tion are used to alleviate the effects of changing latency and band-width. We discuss the design of a terrain streaming system andpresent preliminary results

Abstract

Recording dynamic events, such as a sports event,a ballet performance, or a lecture, digitally for ex-periencing in a spatiotemporally distant setting re-quires 4D capture: three dimensions for their geom-etry/appearance over the fourth dimension of time.Cameras are suitable for this task as they are non-intrusive, universal, and inexpensive. Computer Vi-sion techniques have advanced sufficiently to make the4D capture possible. In this paper, we present a his-torical perspective on the Virtualized RealityTMsys-tem developed since early 90s to early 2000 at CMUfor the 4D capture of dynamic events

Abstract

Depth Images are viable representations that can be computed from the real world using cameras and/or other scanning devices. The depth map provides 2-kD structure of the scene. A set of Depth Images can provide hole-free rendering of the scene. Multiple views need to blended to provide smooth hole-free rendering, however. Such a representation of the scene is bulky and needs good algorithms for real-time rendering and efficient representation. In this paper, we present a discussion on the Depth Image representation and provide a GPU-based algorithm that can render large models represented using DIs in real time. We then present a proxy-based compression scheme for Depth Images and provide results for the same. Results are shown on synthetic scenes under different conditions and on some scenes generated from images. Lastly, we initiate discussion on varying quality levels in IBR and show a way to create representations using DIs with different trade-offs between model size and rendering quality. This enables the use of this representation for a variety of rendering situations.

Abstract

In this paper, we present a new approach for object removaland video completion of indoor scenes. In indoor images, the frames arenot affine related. The region near the object to be removed can havemultiple planes with sharply different motions. Dense motion estimationmay fail for such scenes due to missing pixels. We use feature tracking tofind dominant motion between two frames. The geometry of the motionof multiple planes is used to segment the motion layers into componentplanes. The homography corresponding to each hole pixel is used to warpa frame in the future or past for filling it. We show the application ofour technique on some typical indoor videos.