Prof. Boutin’s research areas include applied mathematics, signal processing and portable device applications. She is pictured here discussing REDDO, an app for translating restaurant menus, with graduate student Albert Parra Pozo.

Current Research Themes

 

Browsing of large object Databases;

Light-weight methods for portable device applications;

Object representation and recognition using invariant statistics;

Context specific language translation and interpretation;

Automatic food nutrient analysis;

Applied and applicable mathematics

Some Past Research Projects

MERGE: a smart phone app to automatically identify HAZMAT signs

PI: E. Delp

Co-PI: M. Boutin

Graduate students: Andrew Haddad, Shanshan Huang.

The goal of this research was to enable first responders to quickly identify the meaning of HAZMAT signs in an emergency situation. 


This research was funded in parts by a grant from the department of Homeland Security (through Purdue’s VACCINE center).

For more information:

  1. Andrew W. Haddad, Shanshan Huang, Mireille Boutin, Edward J. Delp III, Detection of Symmetric shapes on a mobile device with application to automatic sign interpretation” IS&T/SPIE Joint Symposium, Multimedia on Mobile Devices conference, San Francisco, CA, January 2012.

GARI: a smart phone app to automatically identify and analyze gang graffiti.

PI: M. Boutin

Co-PI: E. Delp


The goal of this research was to enable law enforcement personal to interpret gang graffiti using a commercially available smart phone equipped with a camera. This project was widely covered by the press, including wlfi, Discover magazine, and many other news outlet. See one Purdue press release here.


This research was funded in parts by a grant from the department of Homeland Security (through Purdue’s VACCINE center).

For more information:

  1. Albert Parra Pozo, “An integrated mobile system for gang graffiti image acquisition and recognition,” MSEE Thesis, Purdue University, 2011

  2. Albert Parra Pozo, Mireille Boutin, Edward J. Delp III , “Location-aware gang graffiti acquisition and browsing on a mobile device,” IS&T/SPIE Joint Symposium, Multimedia on Mobile Devices conference, San Francisco, CA, January 2012.


Automatic Portrait Beautification

In collaboration with Changhyung Lee (now at Samsungs), Morgan Schramm (HP), and Prof. Jan Allebach (ECE, Purdue)


This research aimed to develop automatic methods to improve the appearance of subjects in digital pictures. Portrait beautification is routinely performed in the fashion industry using image editing software such as photoshop. Processing images this way is slow and costly. The methods we developed in this project allow one to process a large number of pictures quickly and without user input.

Three Different beautification steps were implemented.

1)      Skin Smoothing: Smoothing the skin has the effect of reducing the appearance of wrinkles and blemishes in the subject. To learn about our proposed method for automatic skin smoothing, look at this presentation or see the following publication:

2) Sclera Whitening:

3) Iris lense effect. 


This research was funded by a grant from the Hewlett-Packard Company.

For more information:

  1. C. Lee, “Hybrid Screen Design and Automatic Portrait Image Enhancement,” PhD Thesis, Purdue University, 2008.

  2. C. Lee, M. Schramm, M. Boutin, and J. Allebach, "An Algorithm for Automatic Skin Smoothing in Digital Portraits,” IEEE Int'l Conference on Image Processing (ICIP), 2009.

REDDO: automatic translation and disambiguation of restaurant menus

In collaboration with Prof. Ed Delp and graduate students Albert Parra Pozo and Andrew Haddad.


This goal of this research was to automatically translate a restaurant menu using a cellular phone or a PDA.


This research was funded in parts by a grant from the department of Homeland Security (through Purdue’s VACCINE center).


For more information:

  1. Click here for DEMO VIDEO.

  2. A. Parra, A. W. Haddad, M. Boutin, and E. J. Delp, "A Hand-Held Multimedia Translation and Interpretation System for Diet Management", Proceedings of the 1st IEEE International Workshop on Multimedia Services and Technologies for E-health in conjunction with the International Conference on Multimedia and Expo (ICME), Barcelona, Spain, July 2011.

VERTO: automatic translation of Spanish text documents using a PDA

In collaboration with Prof. Ed Delp and graduate students Albert Parra Pozo and Andrew Haddad.


This goal of this research was to automatically translate text documents in Spanish using a cellular phone or a PDA equiped with a camera.


This research was funded in parts by a grant from the department of Homeland Security (through Purdue’s VACCINE center).


For more information:

  1. A. Parra, A. W. Haddad, M. Boutin, and E. J. Delp, "A Method for Translating Printed Documents Using a Hand-Held Device", Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Barcelona, Spain, July 2011.

ROSETTA PHONE: automatic translation of  foreign character signs on a mobile device

PI: M. Boutin

Co-PI: Ed Delp

Industrial Partner: Next Wave Systems, LLC


This research was funded by DARPA and the Indiana 21st Century Fund.


For more information:

  1. K.L. Bouman, G. Abdollahian, M. Boutin, and E.J. Delp, “A Low Complexity Text Area Detection Method For Mobile Applications,” IEEE Transactions on Multimedia, 13(5): 922-934, 2011.

  2. Nitin Khanna, Golnaz Abdollahian, Ben Brame, Mireille Boutin, and Edward J. Delp, “Arabic word recognizer for mobile applications”, IS&T/SPIE Joint Symposium, Computational Imaging IX, San Francisco, CA, January 2011.

  3. K.L. Bouman, G. Abdollahian, M. Boutin, and E.J. Delp, “A low-complexity method for detection of text area in natural images,” IEEE Int’l conference on Accoustic, speech and signal  Processing (ICASSP), Texas, March 14-19, Dallas, Texas, 2010.

  4. S.A.R. Jafri, A.K. Mikkilineni, M. Boutin, and E.J. Delp, “The Rosetta Phone: a real-time system for automatic detection and translation of signs”, IS&T/SPIE Joint Symposium, Multimedia on Mobile Devices 2008, San Jose, CA, Jan-Feb 2008.