Abstract

Optical Character Recognition (OCR) problems areoften formulated as isolated character (symbol) classification task followed by a post-classification stage (which contains modules like Unicode generation, error correction etc. ) to generate the textual representation, for most of the Indian scripts. Such approaches are prone to failures due to (i) difficulties in designing reliable word-to-symbol segmentation module that can robustly work in presence of degraded (cut/fused) images and (ii) convert-ing the outputs of the classifiers to a valid sequence of Unicodes.In this paper, we propose a formulation, where the expectations on these two modules is minimized, and the harder recognition task is modelled as learning of an appropriate sequence to sequence translation scheme. We thus formulate the recognition as a direct transcription problem. Given many examples of feature sequences and their corresponding Unicode representations, our objective is to learn a mapping which can convert a word directly in to a Unicode sequence. This formulation has multiple practical advantages: (i) This reduces the number of classes significantly for the Indian scripts. (ii) It removes the need for a reliable word-to-symbol segmentation. (ii) It does not require strong annotation of symbols to design the classifiers, and (iii) It directly generates a valid sequence of Unicodes. We test our method on more than 6000 pages of printed Devanagari documents from multiple sources. Our method consistently outperforms other state of the art implementations.

Abstract

Recognizing text in images taken in the wild is achallenging problem that has received great attention in recentyears. Previous methods addressed this problem by first detectingindividual characters, and then forming them into words. Suchapproaches often suffer from weak character detections, due tolarge intra-class variations, even more so than characters fromscanned documents. We take a different view of the problemand present a holistic word recognition framework. In this,we first represent the scene text image and synthetic imagesgenerated from lexicon words using gradient-based features. Wethen recognize the text in the image by matching the scene andsynthetic image features with our novel weighted Dynamic TimeWarping (wDTW) approach.We perform experimental analysis on challenging publicdatasets, such as Street View Text and ICDAR 2003. Ourproposed method significantly outperforms our earlier work inMishraet al.(CVPR 2012), as well as many other recent works,such as Novikovaet al.(ECCV 2012), Wanget al.(ICPR 2012),Wanget al.(ICCV 2011)

Abstract

Understanding positional semantics of the environment plays an important role in manipulating an object in clutter. The interaction with surrounding objects in the environment must be considered in order to perform the task without causing the objects fall or get damaged. In this paper, we learn the semantics in terms of support relationship among different objects in a cluttered environment by utilizing various photometric and geometric properties of the scene. To manipulate an object of interest, we use the inferred support relationship to derive a sequence in which its surrounding objects should be removed while causing minimal damage to the environment. We believe, this work can push the boundary of robotic applications in grasping, object manipulation and picking-from-bin, towards objects of generic shape and size and scenarios with physical contact and overlap. We have created an RGBD dataset that consists of various objects used in day-to-day life present in clutter. We explore many different settings involving different kind of object-object interaction. We successfully learn support relationships and predict support order in these settings.

Abstract

Detecting compact overlapping communities in large networks is an important pattern recognition proble mwith applications in many domains. Most community de-tection algorithms trade-off between community sizes, their compactness and the scalability of finding communities. Clique Percolation Method (CPM) [1] and Local Fitness Maximization(LFM) [2] are two prominent and commonly used overlapping community detection methods that scale with large networks.However, significant number of communities found by the mare large, noisy, and loose. In this paper, we propose a general algorithm that takes such large and loose communities generated by any method and refines them into compact com-munities in a systematic fashion. We define a new measure of community-ness based on eigenvector centrality, identify loose communities using this measure and propose an algorithm for partitioning such loose communities into compact communities.We refine the communities found by CPM and LFM using our method and show their effectiveness compared to the original communities in a recommendation engine task.

Abstract

Labels associated with social images are valuable source of information for tasks of image annotation, understanding and retrieval.These labels are often found to be noisy, mainly due to the collabo-rative tagging activities of users. Existing methods on annotation havebeen developed and verified on noise free labels of images. In this paper,we propose a novel and generic framework that exploits the collective knowledge embedded in noisy label co-occurrence pairs to derive robust annotations. We compare our method with a well-known image annota-tion algorithm and show its superiority in terms of annotation accuracy on benchmark Corel5K and ESP datasets in presence of noisy labels.

Abstract

In this work, we aim at understanding semantic interaction among graspable objects in both direct and indirect physical contact for robotic manipulation tasks. Given an object of interest, its support relationship with other graspable objects is inferred hierarchically. The support relationship is used to predict the “support order” or the order in which the surrounding objects need to be removed in order to manipulate the target object. We believe, this can extend the scope of robotic manipulation tasks to typical clutter involving physical contact, overlap and objects of generic shapes and sizes. We have created an RGBD dataset consisting of various objects present in clutter using Kinect. We conducted our experimentation and analysed the performance of our work on the images from the same dataset.

Abstract

Labels associated with social images are valuable source of information for tasks of image annotation, understanding and retrieval. These labels are often found to be noisy, mainly due to the collaborative tagging activities of users. Existing methods on annotation have been developed and verified on noise free labels of images. In this paper, we propose a novel and generic framework that exploits the collective knowledge embedded in noisy label co-occurrence pairs to derive robust annotations. We compare our method with a well-known image annotation algorithm and show its superiority in terms of annotation accuracy on benchmark Corel5K and ESP datasets in presence of noisy labels.

Abstract

The past few years have witnessed the development of non-spherical metal nanoparticles with complex morphologies, which offer tremendous potential in materials science, chemistry, physics and medicine. Covering all important aspects and techniques of preparation and characterization of metal nanoparticles with controlled morphology and architecture, this book provides a sound overview-from the basics right up to recent developments. Renowned research scientists from all over the world present the existing knowledge in the field, covering theory and modeling, synthesis and properties of these nanomaterials. By emphasizing the underlying concepts and principles in detail, this book enables researchers to fully recognize the future research scope and the application potential of the complex-shaped metal nanoparticles, inspiring further research in this field.

Abstract

The relationship between the NMR methyl group axial order parameter and the side chain conformational entropy is investigated in inhibitor-bound and apo human HIV protease using molecular dynamics simulation. Three distinct entropic classes of methyl-bearing side chains, determined by the topological distance of the methyl group from the protein backbone (i.e., the number of χ-bonds between the Cα and the carbon of the CH3 group), are revealed by atomistic trajectory analyses performed in the local frame of reference of individual methyl probes. The results demonstrate that topologically equivalent methyl groups experience similar nonbonded microenvironments regardless of the type of residues to which they are attached. Similarly, methyl groups that belong to the same side chain but that are not topologically equivalent exhibit different thermodynamic and dynamic properties. The two-parameter classification (based upon entropy and methyl axial order parameter) of side chains described here permits improved estimates of the conformational entropies of proteins from NMR motional parameters.

Abstract

Toggle navigation CCSD. HAL: HAL; HALSHS; TEL; MédiHAL; Liste des portails; AURéHAL; API; Data; Documentation. Episciences.org: Episciences.org; Revues; Documentation. Sciencesconf.org; Support. Connexion: Connexion; Connexion avec ORCID; se connecter avec Fédération; Créer un compte; Mot de passe oublié ? Login oublié ? fr; en. HAL - hal.archives-ouvertes.fr. Accueil; Déposer; Consulter: par thème arXiv; Par type de document; Les derniers dépôts; par année de publication; par laboratoire; —————; HAL; TEL; INSPIRE-HEP; ArXiv; CDS - CERN. Rechercher. in2p3-01577700, version 1. Structure, energetics, and dynamics of smectite clay hydration: Molecular dynamics investigations of hectorite” (oral). Christin P. Morrow A. Ozgur Yazaydin 1 Marimuthu Krishnan Geoffrey M. Bowers Andrey G. Kalinichev 2 R. James Kirkpatrick Détails. 1 Department of Chemistry. 2 SUBATECH - Laboratoire