Grant: Engage Grants Program
Simon Fraser University
$25,000.00
Adaptation of image analysis and machine learning concepts to the fine arts industry
EF 2014-15
Résumé
Beheld Technologies Inc. has a large collection of original artwork being sold through its e-commerce webapplication. All artwork is digitally scanned and catalogued along with their related metadata (e.g. artist,material, and price). The problem Beheld is facing is how to assist potential buyers in browsing the largecatalog of artwork, how to show them the artwork to generate interest, and how to recommend artwork that isexpected to appeal to the potential buyer. As art is a very personal product, a generic approach for displaying orrecommending artwork is not suitable, but rather an approach that is customer specific is required. Imageanalysis and machine learning concepts have proven powerful in related problems in biomedical image analysisand other domains. In order to address the search queries and recommendation problem of Beheld, this researchteam will work on adapting, extending, and applying of image analysis and machine learning concepts to thefine arts industry. The technology that will be developed would address Beheld's problem and enable it to buildthe world's first technology that performs an analysis of the physical characteristics of an artwork andsubsequently use it to search, find and recommend suitable artwork. Two pieces of technology will bedeveloped: 1. Novel image analysis software that breaks down the physical characteristics of an artwork (e.g.understanding the colour composition of the artwork with secondary measured variables such as texture, brushstrokes and objects). 2. A machine-learning algorithm to suggest unique artworks to each user by leveraging thedata created from the image analysis software combined with user logs from the web application to show onlyrelevant artwork to the given user.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
469893-2014
Name nom
Hamarneh, Ghassan
Department département
Computing Science, School of
Organization id
5
Institution établissement
Simon Fraser University
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2014
Award amount
25000
Program id
EGP
Program name 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
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
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
2603
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Computer vision
Research subject fr
Vision artificielle
Partie
1
Nb partie
1
Application title
Adaptation of image analysis and machine learning concepts to the fine arts industry
Keyword
NSERC
Application summary
Beheld Technologies Inc. has a large collection of original artwork being sold through its e-commerce webapplication. All artwork is digitally scanned and catalogued along with their related metadata (e.g. artist,material, and price). The problem Beheld is facing is how to assist potential buyers in browsing the largecatalog of artwork, how to show them the artwork to generate interest, and how to recommend artwork that isexpected to appeal to the potential buyer. As art is a very personal product, a generic approach for displaying orrecommending artwork is not suitable, but rather an approach that is customer specific is required. Imageanalysis and machine learning concepts have proven powerful in related problems in biomedical image analysisand other domains. In order to address the search queries and recommendation problem of Beheld, this researchteam will work on adapting, extending, and applying of image analysis and machine learning concepts to thefine arts industry. The technology that will be developed would address Beheld's problem and enable it to buildthe world's first technology that performs an analysis of the physical characteristics of an artwork andsubsequently use it to search, find and recommend suitable artwork. Two pieces of technology will bedeveloped: 1. Novel image analysis software that breaks down the physical characteristics of an artwork (e.g.understanding the colour composition of the artwork with secondary measured variables such as texture, brushstrokes and objects). 2. A machine-learning algorithm to suggest unique artworks to each user by leveraging thedata created from the image analysis software combined with user logs from the web application to show onlyrelevant artwork to the given user.