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

This paper presents an XML-based scheme for managing a large multilingual OCR project. In particular we describe how a new XML based tagging scheme has been exploited to achieve the objectives of the project. Managing a large multi-lingual OCR project involving multiple research groups, developing script specific and script independent technologies in a collaborative fashion is a challenging problem. In this paper, we present some of the software and data management strategies designed for the project aimed at developing OCR for 11 scripts of Indian origin for which mature OCR technology was not available.

Abstract

Many of the successful multimedia retrieval systems focus on developing efficient and effective video retrieval solutions with the help of appropriate index structures. In these systems, the query is an example video and the retrieved results are similar video clips which are available apriori in the database. In this paper, we address a complementary problem of filtering a video stream based on a set of given examples. By filtering, we mean to detect, accept or reject the part of a video stream matching any of the given examples. This requires matching of example videos with the on-line video stream. Since the concepts of interest could be complex, we avoid explicit learning of a representation from the example videos to characterize the visual event present in the examples. We model the problem as simultaneous on-line spotting of multiple examples in a video stream. We employ a vocabulary trie for the filtering purpose and demonstrate the applicability of the technique in a variety of situations.

Abstract

Contemporary approaches to semantic indexing for bag of words image retrieval do not adapt well when the image or video collections dynamically get modified. In this paper, We propose an on-line incremental semantic indexing scheme for image retrieval in dynamic image collections. Our main contributions are in the form of a method and a data structure that tackle representation of the term document matrix and on-line semantic indexing where the database changes. We introduce a bipartite graph model (BGM) which is a scalable data structure that aids in online semantic indexing. It can also be incrementally updated. BGM uses tf-idf values for building a semantic bipartite graph. We also introduce a cash flow algorithm that works on the BGM to retrieve semantically relevant images from the database. We examine the properties of both BGM and cash flow algorithm through a series of experiments. Finally, we demonstrate how they can be effectively implemented to build large scale image retrieval systems in an incremental manner.

Abstract

In this paper, we empirically study the performance of a set of pattern classification schemes for character classification problems. We argue that with a rich feature space, this class of problems can be solved with reasonable success using a set of statistical feature extraction schemes. Experimental validation is done on a data set (of more than 5,00,000 characters) collected and annotated from books printed primarily in Malayalam. Scope of this study include (a) applicability of a spectrum of classifiers and features (b) scalability of classifiers (c) sensitivity of features to degradation (d) generalization across fonts and (e) applicability across scripts

Abstract

1. Oxford-IIIT combined: a spatial pyramid intersection kernel SVM image classifier, a sliding-window randomforest object detector, a sliding-window intersection kernel SVM object detector, and a discriminative constellation model facial feature extractor. For each of the twenty features, methods were ranked based on their performance on a validation set and associated to successive runs by decreasing performance. For training, TRECVID annotations were manually corrected and augmented with object bounding boxes, and additional training data was used for under-represented features such as Airplane flying. 2. The different methods yielded a significantly different performance depending on the feature, as expected by their design. 3. The image classifier worked better for scene-level features such as Cityscape, Classroom, Doorway, while the object detectors worked better for Boat or ship, Bus, Person riding a bicycle, and the face feature extractor worked well for Female face closeup. 4. Three conclusions can be drawn: (i) different features are addressed better by specialised methods, (ii) removal of noise from TRECVID annotations (iii) additional data for under-represented features significantly improve performance.

Abstract

Design of biomimetic systems is an alternative method of finding biologically active molecules. Peptides incorporating tetrahydrofuran amino acids (TAA) adopt secondary folding patterns and thus mimic natural peptides. The preferred conformation of TAA derived linear and cyclized peptides depends on the stereochemistry of the tetrahydrofuran (THF) ring. Control of stereochemistry of THF ring in the structure of the linear tripeptide Boc-TAA-Leu-Val- OMe containing (2R,5S)-cis TAA, (2S,5R)-cis TAA, (2R,5R)-trans TAA and (2S,5S)-trans TAA is investigated using structural parameters and energetics data obtained from density functional theory (DFT) based calculations at B3LYP/6-31G(d,p) level of theory. We found that the conformations associated with -, -turn structures are stabilized by intramolecular hydrogen bonding interactions. Kinetic control of reactions leading to intra and inter molecular cyclization of tripeptide TAA-Gly-Gly containing (2S,5R)-cis TAA and (2S,5S)-trans TAA is studied at the same level of theory in gas phase.[1] We observe that kinetic control favors cyclodimerization instead of intramolecular cyclization.

Abstract

Cyclic peptides incorporating a 5 membered ring such as furan mimic naturally occurring cyclic peptides[1]. The preferred conformation of linear and cyclic tripeptides incorporating such sugar amino acids depends on the stereochemistry at the chiral center. Control of stereochemistry at C position of amino ethyl furan carboxylic acid (AEFC) unit in the linear and cyclic tripeptides is investigated using structural parameters and energetics data obtained from density functional theory (DFT) based calculations at B3LYP/6-31G(d,p) level of theory. We found that R-isomer of AEFC unit prefers to form bond with its S-isomer. Thermodynamic analysis revealed that linear tripeptide formed by two R-configured isomers of AEFC and one S-configured isomer of AEFC (RRS or RSR linear) is more stable than that formed by three R-configured isomers of AEFC (RRR linear). It is found that the cyclic tripeptide formed by two R-configured isomers of AEFC and one S-configured isomer of AEFC, i. e., cyclic RRS product is formed with high yield than that formed by three R-configured isomers of AEFC (RRR cyclic) though cyclic RRR trimer is more stable than cyclic RRS trimer. This is substantiated by kinetic control of reactions leading to cyclic tripeptides from linear tripeptides. Using NBO analysis stabilizing interactions in all the linear and cyclic tripeptides are identified. Molecular electrostatic potential (MESP) surfaces of cyclic tripeptides provide insights of intramolecular hydrogen bond interactions. The MESP mapped electron density surfaces have shown the charge distribution around the cyclic peptides.

Abstract

Quantum optimal control theory along with time dependent quantum dynamics is used to control the nuclear motion in the hydrogen bonds of adenine-thymine (A-T) DNA base pair [1]. Optimal infrared laser pulses are designed for selective excitations of (a) single N-H


O hydrogen bond and (b) both N-H


O and N-H


N bonds simultaneously. The conjuagte gradient method is employed to optimize the constructed eld dependent grand functional. Optimal laser elds are realized which give more than 99% population transfer to the preselected vibrational states. The mechanism of population transfer during the vibrational excitation process is investigated by projecting the laser driven nuclear wavefunction onto the vibrational states of the system.

Abstract

Conventionally optimal control theory [1, 2, 3] has been used in the theoretical design of laser pulses through the direct variation of the electric field of the laser pulse as a function of time. This often leads to designed laser pulses which contain a broad and seemingly arbitrary frequency structure that varies in time in a manner which may be difficult to realize experimentally. In contrast, in Genetic Algorithm (GA) approach, a few control parameters are used, which are actually available to the experimentalist. In this work, we investigate the possibility of using GA optimization methods in the theoretical design of laser pulses to bring about quantum state transitions in molecules. This allows us to select only a small limited number of parameters to vary and to choose these parameters so that they correspond to those available to the experimentalist. In this work, we apply our methods to the vibrational-rotational excitation of the HF molecule. We choose a small limited number of frequencies and vary only the associated electric field amplitudes and pulse envelopes. We show that laser pulses designed in this way can lead to very high transition probabilities. The mechanism of population transfer during the excitation process is investigated by projecting the laser driven nuclear wave function onto the eigenstates of the system. We have also investigated the possibility of photodissociation of HF molecule by climbing up the vibrational ladder using this genetic algorithm approach.