Localization of handwritten text in documents using moment invariants and Delaunay triangulation

This paper describes an approach based on Zernike moments and Delaunay triangulation for localization of hand-written text in machine printed text documents. The Zernike moments of the image are first evaluated and we classify the text as hand-written using the nearest neighbor classifier. These features are independent of size, slant, orientation, translation and other variations in handwritten text. We then use Delaunay triangulation to reclassify the misclassified text regions. When imposing Delaunay triangulation on the centroid points of the connected components, we extract features based on the triangles and reclassify the text. We remove the noise components in the document as part of the preprocessing step so this method works well on noisy documents. The success rate of the method is found to be 86%. Also for specific hand-written elements such as signatures or similar text the accuracy is found to be even higher at 93%.

Frechet distance based approach for searching online handwritten documents

We propose a novel, language-neutral approach for searching online handwritten text using Frechet distance. Online handwritten data, which is available as a time series (x,y,t), is treated as representing a parameterized curve in two-dimensions and the problem of searching online handwritten text is posed as a problem of matching two curves in a two-dimensional Euclidean space. Frechet distance is a natural measure for matching curves. The main contribution of this paper is the formulation of a variant of Frechet distance that can be used for retrieving words even when only a prefix of the word is given as query. Extensive experiments on UNIPEN dataset(1) consisting of over 16,000 words written by 7 users show that our method outperforms the state-of-the-art DTW method. Experiments were also conducted on a Multilingual dataset, generated on a PDA, with encouraging results. Our approach can be used to implement useful, exciting features like auto-completion of handwriting in PDAs.

Text localization and extraction from complex gray images

We propose two texture-based approaches, one involving Gabor filters and the other employing log-polar wavelets, for separating text from non-text elements in a document image. Both the proposed algorithms compute local energy at some information-rich points, which are marked by Harris' corner detector. The advantage of this approach is that the algorithm calculates the local energy at selected points and not throughout the image, thus saving a lot of computational time. The algorithm has been tested on a large set of scanned text pages and the results have been seen to be better than the results from the existing algorithms. Among the proposed schemes, the Gabor filter based scheme marginally outperforms the wavelet based scheme.

Automatic text block separation in document images

Separation of printed text blocks from the non-text areas, containing signatures, handwritten text, logos and other such symbols, is a necessary first step for an OCR involving printed text recognition. In the present work, we compare the efficacy of some feature-classifier combinations to carry out this separation task. We have selected length-nomalized horizontal projection profile (HPP) as the starting point of such a separation task. This is with the assumption that the printed text blocks contain lines of text which generate HPP's with some regularity. Such an assumption is demonstrated to be valid. Our features are the HPP and its two transformed versions, namely, eigen and Fisher profiles. Four well known classifiers, namely, Nearest neighbor, Linear discriminant function, SVM's and artificial neural networks have been considered and efficiency of the combination of these classifiers with the above features is compared. A sequential floating feature selection technique has been adopted to enhance the efficiency of this separation task. The results give an average accuracy of about 96.

Binarization and localization of text images captured on a mobile phone camera

This paper proposes and compares four methods of binarzing text images captured using a camera mounted on a cell phone. The advantages and disadvantages(image clarity and computational complexity) of each method over the others are demonstrated through binarized results. The images are of VGA or lower resolution.

Chemical potential of oxygen for iron-rutile-ilmenite and iron-ilmenite-ulvospinel equilibria

The chemical potential of oxygen corresponding to the iron-rutile-ilmenite (IRI) and iron-ilmenite-ulvospinel (IIU) equilibria has been measured employing solid-state galvanic cells,$$Pt, Fe + TiO_2 + FeTiO_3 //(Y_2 O_3 ) ZrO_2 //Fe + FeO, Pt$$ and $${\text{Pt, Fe + FeTiO}}_{\text{3}} {\text{ + Fe}}_{\text{2}} {\text{TiO}}_{\text{4}} {\text{//(Y}}_{\text{2}} {\text{0}}_{\text{3}} {\text{) ZrO}}_{\text{2}} {\text{//Fe + FeO, Pt}}$$ in the temperature range of 875 to 1275 K and 900 to 1373 K, respectively. The cells are written such that the right-hand electrodes are positive. The electromotive force (emf) of both the cells was found to be reversible and to vary linearly with temperature over the entire range of measurement. The chemical potential of oxygen for IRI equilibrium is represented by Δμo2(IRI) = -550,724 - 29.445T + 20.374T InT(±210) J mol−1 (875 <-T<- 1184 K) = -620,260 + 369.593T - 27.716T lnT(±210) J mol−1 (1184 <-T<- 1275 K) and that for IIU equilibrium by Δμo2(IIU) = -501,800 - 49.035T + 20.374T lnT(±210) J mol−1 (900 <-T<- 1184 K) = -571,336 + 350.003T− 27.716T lnT(=−210) J mol-1 (1184 <-T<- 1373 K) The standard Gibbs energy changes for IRI and IIU equilibria have been deduced from the measured oxygen potentials. Since ilmenite contains small amounts of Ti³+ ions, a correction for the activity of FeTiO3 has been incorporated by assuming ideal mixing on each cation sublattice in the FeTiO3-Ti2O3 system. Similarly, the ulvospinel contains some Fe³+ ions and a correction for the activity of Fe2TiO4 has been included by modeling the Fe2TiO4-Fe3O4 system. The third-law analysis of the results obtained for IRI equilibrium gives ΔH 298 0 = -575 (±1.0) kJ mol-1 and for IIU equilibrium yields ΔH 298 0 = -523.7 (±0.7) kJ mol−1}. The present results suggest that Fe2+ and Ti4+ cations mix almost ideally on the octahedral site of spinel lattice in Fe2TiO4, giving rise to a configurational contribution of 2R In 2 (11.5256 J mol-1 K-1) to the entropy of Fe2TiO4.

Continuity Metric for Unit Selection based Text-to-Speech Synthesis

A new method based on unit continuity metric (UCM) is proposed for optimal unit selection in text-to-speech (TTS) synthesis. UCM employs two features, namely, pitch continuity metric and spectral continuity metric. The methods have been implemented and tested on our test bed called MILE-TTS and it is available as web demo. After verification by a self selection test, the algorithms are evaluated on 8 paragraphs each for Kannada and Tamil by native users of the languages. Mean-opinion-score (MOS) shows that naturalness and comprehension are better with UCM based algorithm than the non-UCM based ones. The naturalness of the TTS output is further enhanced by a new rule based algorithm for pause prediction for Tamil language. The pauses between the words are predicted based on parts-of-speech information obtained from the input text.

Open-source tools for enhancing full-text searching of OPACs Use of Koha, Greenstone and Fedora

Purpose - There are many library automation packages available as open-source software, comprising two modules: staff-client module and online public access catalogue (OPAC). Although the OPAC of these library automation packages provides advanced features of searching and retrieval of bibliographic records, none of them facilitate full-text searching. Most of the available open-source digital library software facilitates indexing and searching of full-text documents in different formats. This paper makes an effort to enable full-text search features in the widely used open-source library automation package Koha, by integrating it with two open-source digital library software packages, Greenstone Digital Library Software (GSDL) and Fedora Generic Search Service (FGSS), independently. Design/methodology/approach - The implementation is done by making use of the Search and Retrieval by URL (SRU) feature available in Koha, GSDL and FGSS. The full-text documents are indexed both in Koha and GSDL and FGSS. Findings - Full-text searching capability in Koha is achieved by integrating either GSDL or FGSS into Koha and by passing an SRU request to GSDL or FGSS from Koha. The full-text documents are indexed both in the library automation package (Koha) and digital library software (GSDL, FGSS) Originality/value - This is the first implementation enabling the full-text search feature in a library automation software by integrating it into digital library software.

An Online Kannada Text Transliteration System for Mobile Phones

Transliteration system for mobile phone is an area that is always in demand given the difficulties and constraints we face in its implementation. In this paper we deal with automatic transliteration system for Kannada which has a non-uniform geometry and inter-character spacing unlike non-oriental language text like English. So it is even more a challenging problem. Working model consists of part of the process taking place on a mobile with remaining on a server. Good results are achieved.

Machine recognition of printed Kannada text

This paper presents the design of a full fledged OCR system for printed Kannada text. The machine recognition of Kannada characters is difficult due to similarity in the shapes of different characters, script complexity and non-uniqueness in the representation of diacritics. The document image is subject to line segmentation, word segmentation and zone detection. From the zonal information, base characters, vowel modifiers and consonant conjucts are separated. Knowledge based approach is employed for recognizing the base characters. Various features are employed for recognising the characters. These include the coefficients of the Discrete Cosine Transform, Discrete Wavelet Transform and Karhunen-Louve Transform. These features are fed to different classifiers. Structural features are used in the subsequent levels to discriminate confused characters. Use of structural features, increases recognition rate from 93% to 98%. Apart from the classical pattern classification technique of nearest neighbour, Artificial Neural Network (ANN) based classifiers like Back Propogation and Radial Basis Function (RBF) Networks have also been studied. The ANN classifiers are trained in supervised mode using the transform features. Highest recognition rate of 99% is obtained with RBF using second level approximation coefficients of Haar wavelets as the features on presegmented base characters.

Research bed for unit selection based text to speech synthesis

The paper describes a modular, unit selection based TTS framework, which can be used as a research bed for developing TTS in any new language, as well as studying the effect of changing any parameter during synthesis. Using this framework, TTS has been developed for Tamil. Synthesis database consists of 1027 phonetically rich prerecorded sentences. This framework has already been tested for Kannada. Our TTS synthesizes intelligible and acceptably natural speech, as supported by high mean opinion scores. The framework is further optimized to suit embedded applications like mobiles and PDAs. We compressed the synthesis speech database with standard speech compression algorithms used in commercial GSM phones and evaluated the quality of the resultant synthesized sentences. Even with a highly compressed database, the synthesized output is perceptually close to that with uncompressed database. Through experiments, we explored the ambiguities in human perception when listening to Tamil phones and syllables uttered in isolation,thus proposing to exploit the misperception to substitute for missing phone contexts in the database. Listening experiments have been conducted on sentences synthesized by deliberately replacing phones with their confused ones.

A MATLAB Code for Three Dimensional Linear Elastostatics using Constant Boundary Elements

Present work presents a code written in the very simple programming language MATLAB, for three dimensional linear elastostatics, using constant boundary elements. The code, in full or in part, is not a translation or a copy of any of the existing codes. Present paper explains how the code is written, and lists all the formulae used. Code is verified by using the code to solve a simple problem which has the well known approximate analytical solution. Of course, present work does not make any contribution to research on boundary elements, in terms of theory. But the work is justified by the fact that, to the best of author’s knowledge, as of now, one cannot find an open access MATLAB code for three dimensional linear elastostatics using constant boundary elements. Author hopes this paper to be of help to beginners who wish to understand how a simple but complete boundary element code works, so that they can build upon and modify the present open access code to solve complex engineering problems quickly and easily. The code is available online for open access (as supplementary file for the present paper), and may be downloaded from the website for the present journal.

Direct ultrafast laser written C-band waveguide amplifier in Er-doped chalcogenide glass

This paper reports the fabrication and characterization of an ultrafast laser written Er-doped chalcogenide glass buried waveguide amplifier; Er-doped GeGaS glass has been synthesized by the vacuum sealed melt quenching technique. Waveguides have been fabricated inside the 4 mm long sample by direct ultrafast laser writing. The total passive fiber-to-fiber insertion loss is 2.58 +/- 0.02 dB at 1600 nm, including a propagation loss of 1.6 +/- 0.3 dB. Active characterization shows a relative gain of 2.524 +/- 0.002 dB/cm and 1.359 +/- 0.005 dB/cm at 1541 nm and 1550 nm respectively, for a pump power of 500 mW at a wavelength of 980 nm. (C) 2012 Optical Society of America