Browsing by Author "Khan, Mumit"

Now showing 1 - 20 of 117

A Bangla phonetic encoding for better spelling suggesions
(BRAC University, 2004) Naushad UzZaman; Khan, Mumit
We present a phonetic encoding for Bangla that can be used by spelling checkers to provide better suggestions for misspelled words. The encoding is based on the Soundex algorithm, modified to match Bangla phonetics. We start by analyzing Soundex encoding scheme when applied to Bangla. Next we propose a new encoding that handles the case of Bangla words, including those containing conjuncts. We conclude with a demonstration of a prototype spelling checker that uses this phonetic encoding to offer suggestions for a set of misspelled Bangla words.
A comprehensive Bangla spelling checker
(BRAC University, 2006) Naushad UzZaman,; Khan, Mumit
We present a comprehensive Bangla spelling checker that improves the quality of suggestions for misspelled words. The complex rules for Bangla spelling presents a significant challenge in producing suggestions for a misspelled word when employing the traditional methods; one must take phonetic similarity into account for suggested alternatives to be reasonably accurate. In Bangla there are several algorithms available for spell checking, however, none of these considers the complex orthographic rules of Bangla. As a result, spelling checker application does not perform well. In this paper, we describe the process of checking the spelling of a Bangla document (i.e. detecting misspelled words, generating suggestions for misspelled word, and ranking the suggestions), compare the methodologies with existing solutions available in the literature, and then propose solutions for each step. Finally, we conclude by showing the performance and evaluation of our proposed solution.
A comprehensive Bangla spelling checker
(BRAC University, 2006) Naushad UzZaman; Khan, Mumit
We present a comprehensive Bangla spelling checker that improves the quality of suggestions for misspelled words. The complex rules for Bangla spelling presents a significant challenge in producing suggestions for a misspelled word when employing the traditional methods; one must take phonetic similarity into account for suggested alternatives to be reasonably accurate. In Bangla there are several algorithms available for spell checking, however, none of these considers the complex orthographic rules of Bangla. As a result, spelling checker application does not perform well. In this paper, we describe the process of checking the spelling of a Bangla document (i.e. detecting misspelled words, generating suggestions for misspelled word, and ranking the suggestions), compare the methodologies with existing solutions available in the literature, and then propose solutions for each step. Finally, we conclude by showing the performance and evaluation of our proposed solution.
A comprehensive roman (English)-to-Bangla transliteration scheme
(BRAC University, 2006) Naushad UzZaman,; Zaheen, Arnab; Khan, Mumit
A transliteration scheme from Roman (English) to Bangla can help increase the use of Bangla in essential and diverse computing areas such as word processing, Internet and mobile communication and information query and retrieval. The Bangla script’s irregular phonetic nature and its large repertoire of consonant clusters (juktakkhors) create a large gap between the pronunciation and the orthography for a given Bangla word. In this paper, we describe a comprehensive Roman (English)-to-Bangla transliteration scheme that is designed to handle the full complexity of the Bangla script. We apply a phonetic encoding scheme to produce intermediate code-strings that facilitate matching pronunciations of input strings and the desired outputs. We also provide graceful degradation to a more conventional direct phonetic mapping in special circumstances. A prototype of our scheme shows significant success in test cases.
A double metaphone encoding for approximate name searching and matching in Bangla
(BRAC University, 2005) Naushad UzZaman,; Khan, Mumit
Almost any word can be a Bangali name, and the name in turn is often spelled in many different ways, all of which are considered correct and interchangeable. The reason for the spelling complication is two-fold: (1) there is a large gap between the script and pronunciation in Bangla, largely attributed to the large scale Sanskritization process that started in the 12th century and continued throughout the middle ages, and (2) typical Bangla names have very different origins, from the indigenous names derived primarily from Sanskrit, to the imported Muslim names from Persian and Arabic, Christian names from Portuguese, and even the names from popular Western TV soap-operas. However, there is always a large degree of phonetic similarity in the spelling variants of a name, which is the key to searching and matching names in records. We present a Double Metaphone encoding for Bangla names, taking into account the various spelling and phonetic rules in use, which can be used by applications to search for and match names. We encode the spelling variants of a large number of names found in the literature to demonstrate that the encoding does indeed show that the variants of a name are equivalent. A name searching algorithm may employ various figures of merit to narrow the list of possibilities when searching for similar names; we demonstrate one such figure of merit using name encoding and edit distance that has shown good promise.
A double metaphone encoding for Bangla and its application in spelling checker
(BRAC University, 2005) Naushad UzZaman; Khan, Mumit
We present a Double Metaphone encoding for Bangla that can be used by spelling checkers to improve the quality of suggestions for misspelled words. The complex rules of Bangla spelling present a significant challenge in producing suggestions for a misspelled word when employing the traditional edit-distance methods; one must take phonetic similarity into account for the suggested alternatives to be reasonably accurate. We propose a Double Metaphone encoding for Bangla, taking into account the various context-sensitive rules, including those involving the large repertoire of consonant clusters in Bangla, and present a comparison with the traditional edit-distance based methods in producing suggestions for misspelled words.
A high performance domain specific OCR for Bangla script
(BRAC University, 2007) Hasnat, Md. Abul; Habib, S. M. Murtoza; Khan, Mumit
Research on recognizing Bengali script has been started since mid 1980’s. A variety of different techniques have been applied and the performance is examined. In this paper we present a high performance domain specific OCR for recognizing Bengali script. We select the training data set from the script of the specified domain. We choose Hidden Markov Model (HMM) for character classification due to its simple and straightforward way of representation. We examine the primary error types that mainly occurred at preprocessing level and carefully handled those errors by adding special error correcting module as a part of recognizer. Finally we added a dictionary and some error specific rules to correct the probable errors after the word formation is done. The entire technique significantly increases the performance of the OCR for a specific domain to a great extent.
A high performance domain specific OCR for Bangla script
(BRAC University, 2008) Hasnat, Md. Abul; Habib, S. M. Murtoza; Khan, Mumit
Abstract-Research on recognizing Bengali script has been started since mid 1980’s. A variety of different techniques have been applied and the performance is examined. In this paper we present a high performance domain specific OCR for recognizing Bengali script. We select the training data set from the script of the specified domain. We choose Hidden Markov Model (HMM) for character classification due to its simple and straightforward way of representation. We examine the primary error types that mainly occurred at preprocessing level and carefully handled those errors by adding special error correcting module as a part of recognizer. Finally we added a dictionary and some error specific rules to correct the probable errors after the word formation is done. The entire technique significantly increases the performance of the OCR for a specific domain to a great extent.
A light weight stemmer for Bengali and its use in spelling checker
(BRAC University, 2007) Islam, Md. Zahurul; Uddin, Md. Nizam; Khan, Mumit
Stemming is an operation that splits a word into the constituent root part and affix without doing complete morphological analysis. It is used to improve the performance of spelling checkers and information retrieval applications, where morphological analysis would be too computationally expensive. For spelling checkers specifically, using stemming may drastically reduce the dictionary size, often a bottleneck for mobile and embedded devices. This paper presents a computationally inexpensive stemming algorithm for Bengali, which handles suffix removal in a domain independent way. The evaluation of the proposed algorithm in a Bengali spelling checker indicates that it can be effectively used in information retrieval applications in general.
A proposed automated extraction procedure of Bangla text for corpus creation in unicode
(BRAC University, 2006) Pavel, Dewan Shahriar Hossain; Sarkar, Asif Iqbal; Khan, Mumit
This paper addresses the issue of automated Bangla corpus creation, which will significantly help the processes of lexicon development, morphological analysis, automatic parts of speech detection and automatic grammar extraction and machine translation. The plan is to collect all free Bangla documents on the world wide web and offline documents available and extract all the words in them to make a huge repository of text. This body of text or corpus will be used for several purposes of Bangla language processing after it is converted to Unicode text. The conversion process is also one of the associated and equally important research and development issue. Among several procedures our research focuses on a combination of font and language detection and Unicode conversion of retrieved Bangla text as a solution for automatic Bangla corpus creation and the methodology has been described in the paper.
A survey on script segmentation for Bangla OCR
(Center for research on Bangla language processing (CRBLP), BRAC University, 2007) Abduallah, Arif Billah Al-Mahmud; Khan, Mumit
Script segmentation is an important primary task for any Optical Character Recognition (OCR) software. Especially, in case of off-line OCR for printed character, it has more importance. Through script segmentation a big image of some written document is fragmented into a number of small pieces which are then used for pattern matching to determine the expected sequence of characters. In the implementation of Bangla OCR, the script segmentation may also play a vital role. But, for accurate and proper segmentation it is necessary to identify the properties of Bangla script as well as the exceptions. This paper depicts the most important and useful properties, advantages, disadvantages of various Bangla scripts, especially the printed scripts. It also gives some ideas regarding the prospective field of Bangla OCR and its applications.
Acoustic analysis of Bangla consonants
(BRAC University, 2008) Alam, Firoj; Habib, S. M. Murtoza; Khan, Mumit
This paper describes the acoustic characteristics of Bangla consonants, obtained by analyzing the recordings of male and female voices. First, the duration of each phoneme was identified by averaging both the male and female voice data; then, formant were measured and formant comparison was made for controversial phonemes, which also served to resolve the controversies in the existing phoneme inventories; and finally, a consonant phoneme inventory was designed.
Acoustic analysis of Bangla vowel inventory
(BRAC University, 2008) Alam, Firoj; Habib, S. M. Murtoza; Khan, Mumit
This paper describes the acoustic characteristics of Bangla vowels, obtained by analyzing the recordings of male and female voices. First, the duration of each phoneme was identified by averaging both the male and female voice data; then, formants were analyzed for all the phonemes and finally vowel phoneme inventory was designed and presented in this paper.
Acoutstic analysis of Bangla consonants
(BRAC University, 2008) Alam, Firoj; Habib, S. M. Murtoza; Khan, Mumit
This paper describes the acoustic characteristics of Bangla consonants, obtained by analyzing the recordings of male and female voices. First, the duration of each phoneme was identified by averaging both the male and female voice data; then, formant were measured and formant comparison was made for controversial phonemes, which also served to resolve the controversies in the existing phoneme inventories; and finally, a consonant phoneme inventory was designed.
Analysis of N-Gram based text categorization for Bangla in a newspaper
(BRAC University, 2006) Mansur, Munirul; UzZaman, Naushad; Khan, Mumit
In this paper, we study the outcome of using ngram based algorithm for Bangla text categorization. To analyze the efficiency of this methodology we used one year Prothom-Alo news corpus. Our results show that n-grams of length 2 or 3 are the most useful for categorization. Using gram lengths more than 3reduces the performance of categorization.
Analysis of N-Gram based text categorization for Bangla in a newspaper corpus
(BRAC University, 2006-08) Mansur, Munirul; Khan, Mumit
The goal of any classification is to build a set of models that can correctly predict the class of different objects. Text categorization is one such application and can be used in many classification task, e.g. news categorization, language identification, authorship attribution, text genre categorization, recommendation systems etc. In this paper we analyze the performance of n-gram based text categorization for Bangla in a Bangladeshi newspaper, Prothom-Alo corpus.
Application of augmented reality: Mobile camera based bangla text detection and translation
(BRAC University, 12/12/2012) S.Mahbub-Uz-Zaman; Islam, Tanjina; Khan, Mumit
In this paper, we demonstrate an Augmented Reality based Bangla text detection and translation application on Android-platform (2.2). This application recognizes the text that is captured by a mobile phone camera and translates the text and finally displays back the recognized text along with the translation onto the screen. To develop this application we have used the Optical Character Recognition, OCR engine (Tesseract), Google translate API and an open source Android application called android-ocr. The objective of this project is to assist the tourists navigate while they are roaming around in abroad. To achieve our goal we develop an application based on the mobile camera which can be able to detect Bangla text at word level and translate it into English.
Automatic Bangla corpus creation
(BRAC University, 2007) Sarkar, Asif Iqbal; Pavel, Dewan Shahriar Hossain; Khan, Mumit
This paper addresses the issue of automatic Bangla corpus creation, which will significantly help the processes of Lexicon development, Morphological Analysis, Automatic Parts of Speech Detection and Automatic grammar Extraction and machine translation. The plan is to collect all free Bangla documents on the World Wide Web and offline documents available and extract all the words in them to make a huge repository of text. This body of text or corpus will be used for several purposes of Bangla language processing after it is converted to Unicode text. The conversion process is also one of the associated and equally important research and development issue. Among several procedures our research focuses on a combination of font and language detection and Unicode conversion of retrieved Bangla text as a solution for automatic Bangla corpus creation and the methodology has been described in the paper.
Automatic recognition of Bangla sign language
(BRAC University, 2012-12) Choudhury, Najeefa Nikhat; Kayas, Golam; Khan, Mumit; Alom, Md. Zahangir
Sign Language is the mode of communication among the deaf and dumb. However, integrating them into the main stream is very difficult as the majority of the society is unaware of their language. So, to bridge the communication gap between the hearing and speech impaired and the rest in Bangladesh, we conducted a research to recognize Bangla sign language using a computer-vision based approach. To achieve our goals we used Neural Networks to train individual signs. In the future, this research, besides helping as an interpreter, can also open doors to numerous other applications like sign language tutorials or dictionaries and also help the deaf and dumb to search the web or send mails more conveniently.
Automatic will enabled system of multi-modal operation
(© 2013 IEEE, 2013) Karim, Md. Risul; Waliullah, Syed Shaiyan Kamran; Kamal, Badruddin; Rhaman, Md. Khalilur; Khan, Mumit; Jamil, Insan Arafat
AWESOMMO(Automatic Will Enabled System of Multi-Modal Operation)uses Sony PS3 Eye image sensor for high speed image processing and a microphone for voice recognition commands. Armed with 3 degrees of freedom of operation, provides the ability to move freely and interact with the physical objects around it. This robot uses a M.M.O (massively multiplayer online) server named 'Spider Monkey', which enables the robot to be operated remotely. For the first time, a game engine has been customized with serial communication protocol addition to control microcontroller unit of a robot as the game engine handles multithreaded operation in the best possible way. This paper discusses the physical, mechanical and computational methods used in design and construction of the robot along with its multi-modal control feature. This paper also demonstrates the abilities and benefits of using M.M.O and PS3 Eye in such a way that it becomes platform for developing software for robotics and embedded system development.