->Monkbot at 02:29, 14 December 2020

2020-12-14T02:29:23Z

New page

{{Short description|Research laboratory in Bangalore, India}}
{{Use dmy dates|date=August 2018}}
{{Use Indian English|date=August 2018}}

The '''Medical Intelligence and Language Engineering Laboratory''', also known as '''MILE lab''', is a [[research laboratory]] at the [[Indian Institute of Science]], [[Bangalore]] under the Department of Electrical Engineering. The lab is known for its work on [[Image processing]], online [[handwriting recognition]], [[Text-To-Speech]] and [[Optical character recognition]]<ref>{{cite web |url = http://iisc.researchmedia.center/article/mile-lab-iisc-developing-technologies-enable-specially-abled |title = MILE Lab at IISc: Developing technologies to enable the specially abled}}</ref> systems, all of which are focused mainly on [[document]]s and [[speech]] in [[Languages of India|Indian languages]].<ref>{{cite web |url = http://mile.ee.iisc.ernet.in/mile/newsroom.html |title = MILE Lab in news |author = MILE Lab |access-date= 2013-04-28 }}</ref> The lab is headed by [[A. G. Ramakrishnan]].<ref>{{cite web |url = http://mile.ee.iisc.ernet.in/mile/People.html |title = People |author = MILE Lab |access-date = 2013-04-28 |archive-url = https://web.archive.org/web/20140903114029/http://mile.ee.iisc.ernet.in/mile/People.html |archive-date = 3 September 2014 |url-status = dead }}</ref>

== Research focus ==
One of the commitments of MILE lab is the development of [[technology]] for people with [[visual impairment]] to harness knowledge from any available printed material in Indian languages.<ref>{{cite web|url=http://www.bangaloremirror.com/bangalore/others/Walking-an-extra-MILE-for-the-specially-abled/articleshow/46719906.cms|title=Walking an extra MILE for the specially abled - Bangalore Mirror}}</ref> The lab is working towards reaching this goal. Its work till now included: [[document mosaicing]] of coloured, camera captured images ; text extraction from complex colour images, including camera captured images; [[document layout analysis]]; detection of broken and merged characters; OCR technology for Tamil and Kannada;<ref>{{cite journal|title=Word level multiscript identification. | doi=10.1016/j.patrec.2008.01.027 | volume=29|issue=9 |journal=Pattern Recognition Letters|pages=1218–1229|year=2008 |last1=Pati |first1=Peeta Basa |last2=Ramakrishnan |first2=A.G. }}</ref> text to speech conversion in [[Tamil language|Tamil]] and [[Kannada]];<ref> {{cite web|url=http://www.festvox.org/blizzard/bc2013/MILE_Blizzard2013.pdf| title=Shiva Kumar H R, Ashwini J K, Rajaram B S R and A G Ramakrishnan, "MILE TTS for Tamil and Kannada for blizzard challenge 2013," Proc. Blizzard Challenge Workshop, Barcelona, Spain, Sept 3, 2013.}}</ref> pitch modification using [[discrete cosine transform]] in the source domain;<ref>{{cite journal|title= Pitch synchronous pitch modification. | doi=10.1016/j.specom.2003.05.001 | volume=42|journal=Speech Communication|pages=143–154}}</ref> automated [[part of speech]] tagging; phrase prediction and prosody modeling.

Mozhi Vallan, the Tamil [[Optical character recognition|OCR]]<ref>{{cite news|url=http://www.thehindu.com/todays-paper/tp-national/tp-tamilnadu/digitising-tamil-books-is-still-a-big-challenge/article5584769.ece|title=Article in The Hindu on MILE Lab Tamil OCR.|newspaper=The Hindu|date=17 January 2014|last1=Subramanian|first1=Karthik}}</ref> product developed by MILE Lab, is being used by Worth Trust and Karna Vidya Technology Centre, Chennai<ref>{{cite web|url=http://kvtcaccess.blogspot.in/|title=Karna Vidya Technology Centre, Guindy, Chennai.}}</ref> for the conversion of printed school and college books to [[Braille]] format. [[Sri Ramakrishna Math, Chennai]]<ref>{{cite web|url=http://www.chennaimath.org/|title=Sri Ramakrishna Math, Chennai}}</ref> is using it to convert their printed philosophical books in Tamil to computer readable text. Lipi Gnani, the Kannada OCR developed by MILE Lab is being used by Braille Transcription Centers of Mitrajyothi<ref>{{cite web|url=http://www.mitrajyothi.org/braille-transcription-centre-2|archive-url=https://web.archive.org/web/20110203032443/http://www.mitrajyothi.org/braille-transcription-centre-2|url-status=dead|archive-date=2011-02-03|title=Mitrajyothi Braille Transcription Centre, Bangalore.}}</ref> and Canara Bank Relief & Welfare Society,<ref>{{cite web|url=http://mathruchhaya.net/braille_trans_centre.php|title= Braille Transcription Centre, Canara Bank Relief & Welfare Society, Bangalore}}</ref> Bangalore for similar purposes. Also, Thirukkural,<ref>{{cite book|doi=10.1109/WSS.2002.1224406|chapter-url=http://eprints.iisc.ac.in/5147/1/a_complete.pdf|chapter=A complete text-to-speech synthesis system in Tamil|title=Proceedings of 2002 IEEE Workshop on Speech Synthesis, 2002|year=2002|last1=Jayavardhana Rama|first1=G.L.|last2=Ramakrishnan|first2=A.G.|last3=Muralishankar|first3=R.|last4=Prathibha|first4=R.|pages=191–194|isbn=0-7803-7395-2|s2cid=13870581}}</ref> the Tamil [[Text-To-Speech|TTS]] system<ref>{{cite web|url=http://velang.blogspot.com/2012/06/blog-post_24.html|title=Blog in Tamil Manam on Thirukkural Tamil TTS}}</ref> developed by MILE Lab is being used by some school teachers in Singapore for assignments. Madhura, the Kannada TTS<ref>{{cite web|url=http://www.deccanherald.com/content/77617/iis-develops-text-speech-software.html|title=Deccan Herald: IISc develops text-to-speech software for Kannada, Tamil|date=26 June 2010}}</ref> developed by the lab, is being used by two blind students, integrated with a [[screen reader]], to read aloud text OCR'ed with Lipi Gnani from Kannada books. Currently, the lab is researching on [[machine listening]]<ref>{{cite web|url=http://mile.ee.iisc.ernet.in/mile/AboutMile.html|title= MILE Lab research focus}}</ref> and a novel temporal feature named as plosion index has been proposed, which has been shown to be extremely effective in detecting closure-burst transitions of [[stop consonants]] and [[affricates]] from continuous speech, even in [[noise]].<ref>{{cite journal|title=Plosion index, a temporal feature to detect bursts in stops and affricates|doi=10.1121/1.4836055|pmid=24437786|year=2014|last1=Ananthapadmanabha|first1=T. V.|last2=Prathosh|first2=A. P.|last3=Ramakrishnan|first3=A. G.|journal=The Journal of the Acoustical Society of America|volume=135|issue=1|pages=460–71}}</ref> Another feature proposed is DCTILPR,<ref>{{cite journal|title=A G Ramakrishnan, B Abhiram and S R Mahadeva Prasanna, "Voice source characterization using pitch synchronous discrete cosine transform for speaker identification," Journal of the Acoustical Society of America Express Letters, Vol. 137(), pp., 2015.|journal=The Journal of the Acoustical Society of America|volume=137|issue=6|pages=EL469-75|doi=10.1121/1.4921679|pmid=26093457|year=2015|last1=Ramakrishnan|first1=A. G.|last2=Abhiram|first2=B.|last3=Prasanna|first3=S. R.}}</ref> which is a voice source based feature vector that improves the recognition performance of a [[speaker identification]] system.

In the early days, significant work was carried out in medical signal and image processing. A unique algorithm was proposed for [[ECG]] [[Data compression|compression]] by treating each [[cardiac cycle]] as a vector, and applying [[linear prediction]] on the [[discrete wavelet transform]] of this vector, after normalizing its [[Periodic function|period]] using multirate processing based [[interpolation]].<ref>{{cite journal|title=Cardiac cycle synchronized compression of ECG|doi=10.1109/10.649997|pmid=9401225|year=1997|last1=Ramakrishnan|first1=A. G.|last2=Saha|first2=S.|journal=IEEE Transactions on Bio-Medical Engineering|volume=44|issue=12|pages=1253–61|s2cid=8834327|url=http://eprints.iisc.ac.in/484/1/ECG_Coding_by_Wavelet-Based_Linear_Prediction.pdf}}</ref> The maturity of the fetal [[lung]] was predicted using [[image texture]] features obtained from the [[liver]] and lung regions of the [[ultrasound]] images obtained from [[pregnant women]]<ref>{{cite journal|title=Predicting maturity of fetal lung from ultrasound image features|doi=10.1109/4233.992160|pmid=11936595|year=2002|last1=Prakash|first1=K. N.|last2=Ramakrishnan|first2=A. G.|last3=Suresh|first3=S.|last4=Chow|first4=T. W.|journal= IEEE Transactions on Information Technology in Biomedicine|volume=6|issue=1|pages=38–45|s2cid=14662967|url=http://eprints.iisc.ac.in/481/1/Featal_Lung_Maturity_Analysis_Using_Ultrasound_Image_Feature.pdf}}</ref> An effective technique was proposed for [[lossless compression]] of 3D [[magnetic resonance imaging|magnetic resonance image]]s of the [[brain]]. Each [[MRI]] slice was represented by uniform or adaptive mesh; [[affine transformation]] was applied between the corresponding mesh elements of adjacent slices and context-based [[entropy coding]], on the residues.<ref>{{cite journal|title=3D brain MRI compression using adaptive mesh and contextual encoding.|doi=10.1109/TMI.2005.853638|pmid=16156357|year=2005|last1=Srikanth|first1=R.|last2=Ramakrishnan|first2=A. G.|journal=IEEE Transactions on Medical Imaging|volume=24|issue=9|pages=1199–206|s2cid=7523030|url=http://eprints.iisc.ac.in/4010/1/contextual.pdf}}</ref>

==References==
{{Reflist}}

==External links==
*[http://www.ee.iisc.ac.in/index.php Department of Electrical Engineering, IISc]
*[http://mile.ee.iisc.ac.in/ Medical Intelligence and Language Engineering laboratory]
*[http://mile.ee.iisc.ac.in/AGR/index.htm A. G. Ramakrishnan]
*[http://www.worthtrust.in/worth-bookshare-project.html Worth Digitization]

{{DEFAULTSORT:Medical Intelligence and Language Engineering Lab}}

[[Category:Electrical engineering organizations]]
[[Category:Indian Institute of Science]]
[[Category:Research in India]]

Medical intelligence and language engineering lab - Revision history

->Monkbot at 02:29, 14 December 2020