Grant: Engage Grants Program
University of Guelph
$19,869.00
Efficient layout and automatic creation of self inking stamps
EF 2011-12
Résumé
This proposal seeks to apply techniques in computational intelligence and machine learning to the problem of
enhancing the efficiency, esthetics, and ease-of-use of a system for ordering and shipping customer designed
self-inking stamps and similar office products, using an advanced integrated manufacturing platform. Specific
goals include layout of stamps for production in a laser stamp burning system, automatic assessment if the
image from a customer design will burn properly, and real time production of fonts that will burn correctly as
part of the online design tool. These problems all represent novel applications of well understood
computational technology. The result of the research will be an integrated system that increases quality and
customer satisfaction with stamps burned from designs created in an online tool by the customer. The stamp
layout problem for the laser burner is a well known NP-hard problem and the proposed system will exploit the
fact there are a small number of stamp sizes to become more intelligent. This goal is accomplished by
databasing best results found so far for the layout problem and using these as starting points for additional
layouts. This represents a novel type of adaptive tool within the problem domain. Classical machine learning
will be used to classify images that do and do not burn well and provide customers real time feedback about the
practicality of their designs. The results of these machine learning studies will also be mined for domain
knowledge about what image features will and will not burn correctly. The use of evolutionary computation in
the proposal is key for the stamp layout problem because of the ability of EC-based systems to use previous
results as starting points. It is also key to the burnability learning system because the classification of images
can be performed with data structures designed to be easy to mine for features that robustly classify images as
burnable and unburnable.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
417979-2011
Name nom
Ashlock, Daniel
Department département
Mathematics and Statistics
Organization id
24
Institution établissement
University of Guelph
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2011
Award amount
19869
Program id
EGP
Program nane en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2800
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Artificial intelligence (computer vision, use2603)
Research subject fr
Intelligence artificielle (vision artificielle, utiliser 2603)
Partie
1
Nb partie
1
Application title
Efficient layout and automatic creation of self inking stamps
Keyword
NSERC
Application summary
This proposal seeks to apply techniques in computational intelligence and machine learning to the problem of
enhancing the efficiency, esthetics, and ease-of-use of a system for ordering and shipping customer designed
self-inking stamps and similar office products, using an advanced integrated manufacturing platform. Specific
goals include layout of stamps for production in a laser stamp burning system, automatic assessment if the
image from a customer design will burn properly, and real time production of fonts that will burn correctly as
part of the online design tool. These problems all represent novel applications of well understood
computational technology. The result of the research will be an integrated system that increases quality and
customer satisfaction with stamps burned from designs created in an online tool by the customer. The stamp
layout problem for the laser burner is a well known NP-hard problem and the proposed system will exploit the
fact there are a small number of stamp sizes to become more intelligent. This goal is accomplished by
databasing best results found so far for the layout problem and using these as starting points for additional
layouts. This represents a novel type of adaptive tool within the problem domain. Classical machine learning
will be used to classify images that do and do not burn well and provide customers real time feedback about the
practicality of their designs. The results of these machine learning studies will also be mined for domain
knowledge about what image features will and will not burn correctly. The use of evolutionary computation in
the proposal is key for the stamp layout problem because of the ability of EC-based systems to use previous
results as starting points. It is also key to the burnability learning system because the classification of images
can be performed with data structures designed to be easy to mine for features that robustly classify images as
burnable and unburnable.