Abstract

The word error rate of any optical character recognition system (OCR) is usually substantially below its component or character error rate. This is especially true of Indic languages in which a word consists of many components. Current OCRs recognize each character or word separately and do not take advantage of document level constraints. We propose a document level OCR which incorporates information from the entire document to reduce word error rates. Word images are first clustered using a locality sensitive hashing technique. Individual words are then recognized using a (regular) OCR. The OCR outputs of word images in a cluster are then corrected probabilistically by comparing with the OCR outputs of other members of the same cluster. The approach may be applied to improve the accuracy of any OCR run on documents in any language. In particular, we demonstrate it for Telugu, where the use of language models for post-processing is not promising. We show a relative improvement of 28% for long words and 12% for all words which appear at least twice in the corpus.

Abstract

A standard solution for aligning scripts to movies is to use dynamic time warping with the subtitles (Everingham et al., BMVC 2006). We investigate the problem of aligning scripts to TV video/movies in cases where subtitles are not available, e.g. in the case of silent films or for film passages which are non-verbal. To this end we identify a number of “modes of alignment” and train classifiers for each of these. The modes include visual features, such as locations and face recognition, and audio features such as speech. In each case the feature gives some alignment information, but is too noisy when used independently. We show that combining the different features into a single cost function and optimizing this using dynamic programming, leads to a performance superior to each of the individual features. The method is assessed on episodes from the situation comedy Seinfeld, and on Charlie Chaplin and Indian movies.

Abstract

. In this paper, we propose a convex optimization based approach for piecewise planar reconstruction. We show that the task of reconstructing a piecewise planar environment can be set in an L∞ based Homographic framework that iteratively computes scene plane and camera pose parameters. Instead of image points, the algorithm optimizes over inter-image homographies. The resultant objective functions are minimized using Second Order Cone Programming algorithms. Apart from showing the convergence of the algorithm, we also empirically verify its robustness to error in initialization through various experiments on synthetic and real data. We intend this algorithm to be in between initialization approaches like decomposition methods and iterative non-linear minimization methods like Bundle Adjustment.

Abstract

Cross Language Information Retrieval (CLIR) between languages of the same origin is an interesting topic of research. The similarity of the writing systems used for these languages can be used effectively to not only improve CLIR, but to overcome the problems of textual variations, textual errors, and even the lack of linguistic resources like stemmers to an extent. We have conducted CLIR experiments between three languages which use writing systems (scripts) of Brahmi-origin, namely Hindi, Bengali and Marathi. We found significant improvements for all the six language pairs using a method for fuzzy text search based on Surface Similarity. In this paper we report these results and compare them with a baseline CLIR system and a CLIR system that uses Scaled Edit Distance (SED) for fuzzy string matching.

Abstract

In this paper, we describe an approach for creating semantic wiki pages from regular wiki pages, in the domain of scientific museums, using information extraction methods in general and named entity recognition in particular. We make use of a domain specific ontology called CIDOC-CRM as a base structure for representing and processing knowledge. We have described major components of the proposed approach and a three-step process involving name entity recognition, identifying domain classes using the ontology and establishing the properties for the entities in order to generate semantic wiki pages. Our initial evaluation of the prototype shows promising results in terms of enhanced efficiency and time and cost benefits.

Abstract

In this paper, we report our participation in Update Summarization, Knowledge Base Population and Recognizing Textual Entailment at TAC 2009. This year, we enhanced our basic summaization system with support vector regression to better estimate the combined affect of different features in ranking. A Novelty measure is devised to effectively capture relevance and novelty of a term. For Knowledge Base Population, we analyzed IR approaches and Naive Bayes Classification with Phrase and Token searches. Finally for RTE, we built templates using WordNet and predict entailments.

Abstract

Gold nanoparticle-loaded liposomes can serve as important biophysical and biochemical tools. A rapid, green, one-step synthetic method has been used for direct and controlled loading of gold nanoparticles onto liposomes. The effects of various synthetic parameters on nanoparticle loading as well as on optical properties of the liposome-anchored nanoparticles are discussed. Gold nanoparticle-loaded individual liposomes have been characterized by dark-field microscopy and optical spectroscopy.

Abstract

We report on surface-enhanced Raman scattering (SERS) from single star-shaped gold nanoparticles coated with self-assembled monolayers of 4-mercaptobenzoic acid. SERS is observed without the formation of gold nanoparticle aggregates or resonant excitation of the analyte. Total Raman scattering enhancement factors for single nanostars are comparable to those of nanoparticle assemblies exhibiting coupled plasmon resonances. This renders gold nanostars promising for Raman imaging applications in complex environments such as cells or membranes.

Abstract

Despite the growing importance of other sectors, agriculture continues to hold the key to the growth of GDP, food security, employment and income in India. Over a period of time, agriculture is undergoing a change towards high value crops, livestock, fisheries etc. Along with it substantial changes have occurred in seed varieties, use of chemical inputs, cultivation practices. Such a process has also culminated in distress conditions in the farm sector. Studies1 undertaken in the states of Andhra Pradesh, Karnataka, Maharastra and Punjab have revealed the serious crisis among the farming community. It is pertinent to note that net income is negative in some states( Narayan Moorthy: 2006) and nearly two thirds of the farmers are frustrated with their profession ( Desh

Abstract

The eSaguTMsystem is an IT-based personalized agro advisory system. In this system, the agricultural experts generate the advice by using the latest information about the crop situation received in the form of both photographs and text. The agricultural expert advice is delivered to each farm on a regular basis (typically once in a week/two weeks depending on the type of crop) from the sowing stage to the harvesting stage to the farmer without farmer asking a question. Since 2004, the eSagu system is being developed by operating on several crops and farms in Andhra Pradesh state of India. It has been found that the agriculture expert can prepare the expert advice in an efficient manner based on the crop photographs and the related information. The impact results show that the expert advices helped the farmers to achieve significant savings in the capital investment and improvement in the yield. Encouraged by the results of eSagu experiment, a country-wide integrated agri-service program is planned by Media Lab Asia to provide expert advice and other agri-related services to Indian farming community. In this paper we briefly explain the development of eSagu system, advantages and future plan.