Indian Language Benchmark Portal

8 results

Please Login/Register to submit the new Resources

Handwritten Bangla Alphabet Recognition using an MLP Based Classifier
Subhadip BasuNibaran DasRam SarkarMahantapas KunduMita NasipuriDipak Kumar Basu

The work presented here involves the design of a Multi Layer Perceptron (MLP) based classifier for recognition of handwritten Bangla alphabet using a 76 element feature set Bangla is the second most popular script and language in the Indian subcontinent and the fifth most popular language in the world. The feature set developed for representing handwritten characters of Bangla alphabet includes 24 shadow features, 16 centroid features and 36 longest-run features. Recognition performances of the MLP designed to work with this feature set are experimentally observed as 86.46% and 75.05% on the samples of the training and the test sets respectively. The work has useful application in the development of a complete OCR system for handwritten Bangla text.

UNL Based Bangla Natural Text Conversion - Predicate Preserving Parser Approach
Md. Nawab Yousuf AliShamim RiponShaikh Muhammad Allayear

Universal Networking Language (UNL) is a declarative formal language that is used to represent semantic data extracted from natural language texts. This paper presents a novel approach to converting Bangla natural language text into UNL using a method known as Predicate Preserving Parser (PPP) technique. PPP performs morphological, syntactic and semantic, and lexical analysis of text synchronously. This analysis produces a semantic-net like structure represented using UNL. We demonstrate how Bangla texts are analyzed following the PPP technique to produce UNL documents which can then be translated into any other suitable natural language facilitating the opportunity to develop a universal language translation method via UNL.

Nonequilibrium Thermodynamics. Symmetric and Unique Formulation of the First Law, Statistical Definition of Heat and Work, Adiabatic Theorem and the Fate of the Clausius Inequality: A Microscopic View
P. D. Gujrati

The status of heat and work in nonequilibrium thermodynamics is quite confusing and non-unique at present with conflicting interpretations even after a long history of the first law in terms of exchange heat and work, and is far from settled. Moreover, the exchange quantities lack certain symmetry. By generalizing the traditional concept to also include their time-dependent irreversible components allows us to express the first law in a symmetric form dE(t)= dQ(t)-dW(t) in which dQ(t) and work dW(t) appear on an equal footing and possess the symmetry. We prove that irreversible work turns into irreversible heat. Statistical analysis in terms of microstate probabilities p_{i}(t) uniquely identifies dW(t) as isentropic and dQ(t) as isometric (see text) change in dE(t); such a clear separation does not occur for exchange quantities. Hence, our new formulation of the first law provides tremendous advantages and results in an extremely useful formulation of non-equilibrium thermodynamics, as we have shown recently. We prove that an adiabatic process does not alter p_{i}. All these results remain valid no matter how far the system is out of equilibrium. When the system is in internal equilibrium, dQ(t)\equivT(t)dS(t) in terms of the instantaneous temperature T(t) of the system, which is reminiscent of equilibrium. We demonstrate that p_{i}(t) has a form very different from that in equilibrium. The first and second laws are no longer independent so that we need only one law, which is again reminiscent of equilibrium. The traditional formulas like the Clausius inequality {\oint}d_{e}Q(t)/T_{0}<0, etc. become equalities {\oint}dQ(t)/T(t)\equiv0, etc, a quite remarkable but unexpected result in view of irreversibility. We determine the irreversible components in two simple cases to show the usefulness of our approach; here, the traditional formulation is of no use.

Input Scheme for Hindi Using Phonetic Mapping
Nisheeth JoshiIti Mathur

Written Communication on Computers requires knowledge of writing text for the desired language using Computer. Mostly people do not use any other language besides English. This creates a barrier. To resolve this issue we have developed a scheme to input text in Hindi using phonetic mapping scheme. Using this scheme we generate intermediate code strings and match them with pronunciations of input text. Our system show significant success over other input systems available.

Discrimination of English to other Indian languages (Kannada and Hindi) for OCR system
Ankit KumarTushar PatnaikVivek Kr Verma

India is a multilingual multi-script country. In every state of India there are two languages one is state local language and the other is English. For example in Andhra Pradesh, a state in India, the document may contain text words in English and Telugu script. For Optical Character Recognition (OCR) of such a bilingual document, it is necessary to identify the script before feeding the text words to the OCRs of individual scripts. In this paper, we are introducing a simple and efficient technique of script identification for Kannada, English and Hindi text words of a printed document. The proposed approach is based on the horizontal and vertical projection profile for the discrimination of the three scripts. The feature extraction is done based on the horizontal projection profile of each text words. We analysed 700 different words of Kannada, English and Hindi in order to extract the discrimination features and for the development of knowledge base. We use the horizontal projection profile of each text word and based on the horizontal projection profile we extract the appropriate features. The proposed system is tested on 100 different document images containing more than 1000 text words of each script and a classification rate of 98.25%, 99.25% and 98.87% is achieved for Kannada, English and Hindi respectively.

A Hindi Speech Actuated Computer Interface for Web Search
Kamlesh SharmaS. V. A. V. PrasadT. V. Prasad

Aiming at increasing system simplicity and flexibility, an audio evoked based system was developed by integrating simplified headphone and user-friendly software design. This paper describes a Hindi Speech Actuated Computer Interface for Web search (HSACIWS), which accepts spoken queries in Hindi language and provides the search result on the screen. This system recognizes spoken queries by large vocabulary continuous speech recognition (LVCSR), retrieves relevant document by text retrieval, and provides the search result on the Web by the integration of the Web and the voice systems. The LVCSR in this system showed enough performance levels for speech with acoustic and language models derived from a query corpus with target contents.

Design of English-Hindi Translation Memory for Efficient Translation
Nisheeth JoshiIti Mathur

Developing parallel corpora is an important and a difficult activity for Machine Translation. This requires manual annotation by Human Translators. Translating same text again is a useless activity. There are tools available to implement this for European Languages, but no such tool is available for Indian Languages. In this paper we present a tool for Indian Languages which not only provides automatic translations of the previously available translation but also provides multiple translations, in cases where a sentence has multiple translations, in ranked list of suggestive translations for a sentence. Moreover this tool also lets translators have global and local saving options of their work, so that they may share it with others, which further lightens the task.

Real-time scene text localization and recognition
Lukáš Neumann Jiří Matas

An end-to-end real-time scene text localization and recognition method is presented. The real-time performance is achieved by posing the character detection problem as an efficient sequential selection from the set of Extremal Regions (ERs). The ER detector is robust to blur, illumination, color and texture variation and handles low-contrast text. In the first classification stage, the probability of each ER being a character is estimated using novel features calculated with O(1) complexity per region tested. Only ERs with locally maximal probability are selected for the second stage, where the classification is improved using more computationally expensive features. A highly efficient exhaustive search with feedback loops is then applied to group ERs into words and to select the most probable character segmentation. Finally, text is recognized in an OCR stage trained using synthetic fonts. The method was evaluated on two public datasets. On the ICDAR 2011 dataset, the method achieves state-of-the-art text localization results amongst published methods and it is the first one to report results for end-to-end text recognition. On the more challenging Street View Text dataset, the method achieves state-of-the-art recall. The robustness of the proposed method against noise and low contrast of characters is demonstrated by “false positives” caused by detected watermark text in the dataset.

Filter by Author
P. D. Gujrati (8)
Manish Shrivastava (7)
Umapada Pal (5)
Partha Pratim Roy (5)
Iti Mathur (4)
C.V. Jawahar (4)