Grant: Engage Grants Program
École Polytechnique de Montréal
$25,000.00
Deep networks for product recognition
EF 2013-14
Résumé
Planora Inc. is developing a software product to automatically validate the correct shelving of products instores. A system developed so far has an acceptable accuracy on some products (ex. cereal boxes); however,this rate is not maintained for differently shaped products such as cans and bottles and the approach has onlybeen tested in a controlled lab environment. The overall goal of this research project is to improve a system thatis capable of automatically comparing the organization of store shelves to desired templates. To achieve thisgoal, we propose to evaluate and extend the companies current technique for extracting objects and theirlocations from images. In particular, we shall compare an incrementally extended version of the companiescurrent system with a novel direction based on the use of deep neural network techniques for objectrecognition. We will extend their current system using various insights from both the fine-grained objectrecognition computer vision research literature, as well as novel techniques based on deep neural networks.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
461061-2013
Name nom
Pal, Christopher
Department département
Génie informatique et génie logiciel
Organization id
64
Institution établissement
École Polytechnique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2013
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
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
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
2604
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Intelligent systems applications
Research subject fr
Applications de systèmes intelligents
Partie
1
Nb partie
1
Application title
Deep networks for product recognition
Keyword
NSERC
Application summary
Planora Inc. is developing a software product to automatically validate the correct shelving of products instores. A system developed so far has an acceptable accuracy on some products (ex. cereal boxes); however,this rate is not maintained for differently shaped products such as cans and bottles and the approach has onlybeen tested in a controlled lab environment. The overall goal of this research project is to improve a system thatis capable of automatically comparing the organization of store shelves to desired templates. To achieve thisgoal, we propose to evaluate and extend the companies current technique for extracting objects and theirlocations from images. In particular, we shall compare an incrementally extended version of the companiescurrent system with a novel direction based on the use of deep neural network techniques for objectrecognition. We will extend their current system using various insights from both the fine-grained objectrecognition computer vision research literature, as well as novel techniques based on deep neural networks.