Font and Size Independent OCR for Printed Kannada Documents using SVM Classifiers

The following topics were dealt with: document analysis and recognition; multimedia document processing; character recognition; document image processing; cheque processing; form processing; music processing; document segmentation; electronic documents; character classification; handwritten character recognition; information retrieval; postal automation; font recognition; Indian language OCR; handwriting recognition; performance evaluation; graphics recognition; oriental character recognition; and word recognition

Synthesis and characterization of cobalt(II), nickel(II), copper(II) and zinc(II) complexes of 2-nitrobenzoic acid with methyl carbazate as ancillary ligand. Crystal structure of the copper(II) complex

Divalent metal complexes of general formula M(2-nb)(2)(mc)(2)].2(2-nbH), where M = Co(II), Ni(II), Cu(II) or Zn(II), 2-nbH = 2-nitrobenzoic acid and mc = methyl carbazate (NH2NHCOOCH3), have been prepared and characterized by physicochemical and spectroscopic methods. Single-crystal X-ray study of the Cu(II) complex revealed that the molecule is centrosymmetric, with two N,O-chelating mc ligands in equatorial positions and a pair of monodentate 2-nb anions in the axial positions. The lattice 2-nbH molecules help to establish the packing of monomers through hydrogen-bonding interactions. Thermal stability and reactivity of the complexes were studied by TG-DTA. Emission studies show that these complexes are fluorescent.

QUAD: quality assessment of documents

We propose a set of metrics that evaluate the uniformity, sharpness, continuity, noise, stroke width variance,pulse width ratio, transient pixels density, entropy and variance of components to quantify the quality of a document image. The measures are intended to be used in any optical character recognition (OCR) engine to a priori estimate the expected performance of the OCR. The suggested measures have been evaluated on many document images, which have different scripts. The quality of a document image is manually annotated by users to create a ground truth. The idea is to correlate the values of the measures with the user annotated data. If the measure calculated matches the annotated description,then the metric is accepted; else it is rejected. In the set of metrics proposed, some of them are accepted and the rest are rejected. We have defined metrics that are easily estimatable. The metrics proposed in this paper are based on the feedback of homely grown OCR engines for Indic (Tamil and Kannada) languages. The metrics are independent of the scripts, and depend only on the quality and age of the paper and the printing. Experiments and results for each proposed metric are discussed. Actual recognition of the printed text is not performed to evaluate the proposed metrics. Sometimes, a document image containing broken characters results in good document image as per the evaluated metrics, which is part of the unsolved challenges. The proposed measures work on gray scale document images and fail to provide reliable information on binarized document image.

Hybrid online non-negative matrix factorization for clustering of documents

When document corpus is very large, we often need to reduce the number of features. But it is not possible to apply conventional Non-negative Matrix Factorization(NMF) on billion by million matrix as the matrix may not fit in memory. Here we present novel Online NMF algorithm. Using Online NMF, we reduced original high-dimensional space to low-dimensional space. Then we cluster all the documents in reduced dimension using k-means algorithm. We experimentally show that by processing small subsets of documents we will be able to achieve good performance. The method proposed outperforms existing algorithms.

Substitution-Modulated Anticancer Activity of Half-Sandwich Ruthenium(II) Complexes with Heterocyclic Ancillary Ligands

Ten new organometallic half-sandwich ruthenium complexes with heterocyclic ligands have been synthesized (H1-H10). The substituents on the ancillary heterocyclic ligands were varied to understand the effect of substitution on anticancer activity. The crystallographic characterization of five complexes confirms that they adopt three-legged piano-stool structures and are stabilized by intramolecular hydrogen bonding. Complexes H2 and H3 also exhibit halogen bonding in the solid state. In aqueous media, the complexes form dinuclear ruthenium species. Complex H1 with a noncytotoxic heterocycle, 6-fluoro-2-mercaptobenzothiazole, and complex H11 with the unsubstituted 2-mercaptobenzothiazole are the most active against A2780 and KB cell lines. The substitution of the H atoms on the ancillary ligand with Cl or Br atoms leads to a decrease in the anticancer activity. With the exception of fluorine-substituted H5, the complexes with mercaptobenzoxazole (H6-H9) are inactive against all of the tested cell lines. Ruthenium complexes with mercaptonaphthimidazole (H10) and mercaptobenzimidazole (H13) do not show any anticancer activity. The active complexes show a biphasic melting curve when incubated with calf thymus (CT) DNA. These complexes only inhibit thioredoxin reductase (TrxR) enzyme activity to a small extent. The substitution of hydrogen atoms with fluorine atoms in the aromatic heterocyclic ligands on organometallic half-sandwich ruthenium complexes has the most beneficial effect on their anticancer activity.

First hyperpolarizability of Ru-half-sandwich complexes: The effect of halogen atom substitution on the ancillary ligand

The first hyperpolarizability (beta) of a series of half-sandwich Ru complexes with a mercaptobenzothiazole ligand bearing a halogen atom substitution in the para-position has been investigated by hyper-Rayleigh scattering and quantum chemical calculations. The heterocyclic ligand with a bromine atom in the para position makes it a very good donor and charge flows to the Ru center enhancing the beta value of the complex by a factor of 2 compared to the complex with the ligand without the halogen substitution. The resonance (+R) and the inductive (-I) effects exerted by the halogen atom in the para position push electrons in opposing directions in the complex. For the Br and Cl atoms the resonance effect dominates which enables the ligand to donate electrons to the metal center thereby increasing the hyperpolarizability whereas for the fluorine atom, the inductive effect is dominant which reduces the charge flow to the metal and the hyperpolarizability drops even below that of the unsubstituted ligand. This unprecedented halogen atom effect on beta of metal complexes is reported. (C) 2015 Elsevier By. All rights reserved.

Segregating Discourse Segments from Engineering Documents for Knowledge Acquisition

The broader goal of the research being described here is to automatically acquire diagnostic knowledge from documents in the domain of manual and mechanical assembly of aircraft structures. These documents are treated as a discourse used by experts to communicate with others. It therefore becomes possible to use discourse analysis to enable machine understanding of the text. The research challenge addressed in the paper is to identify documents or sections of documents that are potential sources of knowledge. In a subsequent step, domain knowledge will be extracted from these segments. The segmentation task requires partitioning the document into relevant segments and understanding the context of each segment. In discourse analysis, the division of a discourse into various segments is achieved through certain indicative clauses called cue phrases that indicate changes in the discourse context. However, in formal documents such language may not be used. Hence the use of a domain specific ontology and an assembly process model is proposed to segregate chunks of the text based on a local context. Elements of the ontology/model, and their related terms serve as indicators of current context for a segment and changes in context between segments. Local contexts are aggregated for increasingly larger segments to identify if the document (or portions of it) pertains to the topic of interest, namely, assembly. Knowledge acquired through such processes enables acquisition and reuse of knowledge during any part of the lifecycle of a product.

Improved recognition of aged Kannada documents by effective segmentation of merged characters

In optical character recognition of very old books, the recognition accuracy drops mainly due to the merging or breaking of characters. In this paper, we propose the first algorithm to segment merged Kannada characters by using a hypothesis to select the positions to be cut. This method searches for the best possible positions to segment, by taking into account the support vector machine classifier's recognition score and the validity of the aspect ratio (width to height ratio) of the segments between every pair of cut positions. The hypothesis to select the cut position is based on the fact that a concave surface exists above and below the touching portion. These concave surfaces are noted down by tracing the valleys in the top contour of the image and similarly doing it for the image rotated upside-down. The cut positions are then derived as closely matching valleys of the original and the rotated images. Our proposed segmentation algorithm works well for different font styles, shapes and sizes better than the existing vertical projection profile based segmentation. The proposed algorithm has been tested on 1125 different word images, each containing multiple merged characters, from an old Kannada book and 89.6% correct segmentation is achieved and the character recognition accuracy of merged words is 91.2%. A few points of merge are still missed due to the absence of a matched valley due to the specific shapes of the particular characters meeting at the merges.

Miscellaneous translations on oyster biology (contents page only - individual articles held as separate documents)

This is a translation of selected articles from the Japanese language publication Hiroshimaken Suisan Shikenjo Hokoku (Report of Hirshima Prefectural Fisheries Experimental Station), Hiroshima City, Japan, vol.22, no. 1, 1960, pages 1-76. Articles translated are: Haematological study of bacteria affected oysters, The distribution of oyster larvae and spatfalls in the Hiroshima City perimeter, On the investigation of the timing of spatfalls, On the prediction of oyster seeding at inner Hiroshima Bay, Oyster growth and its environment at the oyster farm in Hiroshima Bay

Ancillary ligand effects : from zirconium(IV)-catalyzed homogeneous propylene polymerization to platinum(II)-mediated C-H bond activation

A series of C_s- and C₁-symmetric doubly-linked ansa-metallocenes of the general formula {1,1'-SiMe₂-2,2'-E-('ƞ⁵-C₅H₂-4-R¹)-(ƞ⁵-C₅H-3',5'-(CHMe₂)₂)}ZrC₂ (E = SiMe₂ (1), SiPh₂ (2), SiMe₂ -SiMe₂ (3); R¹ = H, CHMe₂, C₅H₉, C₆H₁₁, C₆H₅) has been prepared. When activated by methylaluminoxane, these are active propylene polymerization catalysts. 1 and 2 produce syndiotactic polypropylenes, and 3 produces isotactic polypropylenes. Site epimerization is the major pathway for stereoerror formation for 1 and 2. In addition, the polymer chain has slightly stronger steric interaction with the diphenylsilylene linker than with the dimethylsilylene linker. This results in more frequent site epimerization and reduced syndiospecificity for 2 compared to 1.

C₁-Symmetric ansa-zirconocenes [1,1 '-SiMe₂-(C₅H₄)-(3-R-C₅H₃)]ZrCl₂ (4), [1,1 '-SiMe₂-(C₅H₄)-(2,4-R₂-C₅H₂)]ZrCl₂ (5) and [1,1 '-SiMe₂-2,2 '-(SiMe₂-SiMe₂)-(C₅H₃)-( 4-R-C₅H₂)]ZrCl₂ (6) have been prepared to probe the origin of isospecificity in 3. While 4 and 3 produce polymers with similar isospecificity, 5 and 6 give mostly hemi-isotactic-like polymers. It is proposed that the facile site epimerization via an associative pathway allows rapid equilibration of the polymer chain between the isospecific and aspecific insertion sites. This results in more frequent insertion from the isospecific site, which has a lower kinetic barrier for chain propagation. On the other hand, site epimerization for 5 and 6 is slow. This leads to mostly alternating insertion from the isospecific and aspecific sites, and consequently, a hemi-isotactic-like polymers. In comparison, site epimerization is even slower for 3, but enchainment from the aspecific site has an extremely high kinetic barrier for monomer coordination. Therefore, enchainment occurs preferentially from the isospecific site to produce isotactic polymers.

A series of cationic complexes [(ArN=CR-CR=NAr)PtMe(L)]⁺[BF₄]⁺ (Ar = aryl; R = H, CH₃; L = water, trifluoroethanol) has been prepared. They react smoothly with benzene at approximately room temperature in trifluoroethanol solvent to yield methane and the corresponding phenyl Pt(II) cations, via Pt(IV)-methyl-phenyl-hydride intermediates. The reaction products of methyl-substituted benzenes suggest an inherent reactivity preference for aromatic over benzylic C-H bond activation, which can however be overridden by steric effects. For the reaction of benzene with cationic Pt(II) complexes, in which the diimine ligands bear 3,5-disubstituted aryl groups at the nitrogen atoms, the rate-determining step is C-H bond activation. For the more sterically crowded analogs with 2,6-dimethyl-substituted aryl groups, benzene coordination becomes rate-determining. The more electron-rich the ligand, as reflected by the CO stretching frequency in the IR spectrum of the corresponding cationic carbonyl complex, the faster the rate of C-H bond activation. This finding, however, does not reflect the actual C-H bond activation process, but rather reflects only the relative ease of solvent molecules displacing water molecules to initiate the reaction. That is, the change in rates is mostly due to a ground state effect. Several lines of evidence suggest that associative substitution pathways operate to get the hydrocarbon substrate into, and out of, the coordination sphere; i.e., that benzene substitution proceeds by a solvent- (TFE-) assisted associative pathway.