Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Engage Grants Program

University of Waterloo

$25,000.00

Automatic and interactive image segmentation for visual search

FY 2014-15

Summary
Slyce Inc. specializes in the design and development of visual search solutions that address the challenges oftraditional product search for online and mobile shoppers. Slyce's IP visual search platform enables consumersto search for their desired product by snapping a photo with their smartphone or clicking on an image in theirbrowsers. Retrieving exact or visually-similar products from client retailers' catalog, Slyce's platform enablesthe retailers to clinch an on-the-spot sale at the moment of inspiration.The performance & the quality of experience of Slyce's current visual search technology has drawn greatinterest from the end-users and the engaged retailers and publishers who have tried the beta releases of ourmobile and web applications, resulting in the Slyce technology to be named as the best Retail Innovation of2013 by Startup Calgary. However, in order for Slyce to preserve its competitive advantage, we need tocontinue to improve and expand our current technology, particularly with the rapid growth of our business.Slyce seeks to leverage the knowledge and expertise of Dr. Zelek and his group to improve the performance ofits visual search technology by means of image segmentation. In particular, the goal of this project is two-fold:first, to investigate how automatic image segmentation can enable our visual search technology to focus on themost salient regions of the image (most potentially containing the object of user's interest); and second, toinvestigate how user's input (e.g., an annotation window placed around the target object, or the marks drawn onthe object) can be combined with the automatic segmentation of the first fold to produce a higher segmentationaccuracy.The project will support the continued development and service of a $50B market in retailers through onlineand mobile experiences. The net benefit is additional accuracy to the overall visual search process, bringinggreater service levels to apparel retailers, a more competitive offering in the market, and thus greatercertainty/profitability for the company.
Program
Engage Grants Program
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
469655-2014
Name nom
Zelek, John
Department département
Systems Design Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
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
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
900
Area of application group en
Commercial services
Area of application group fr
Services commerciaux
Area of application en
Commercial services
Area of application fr
Services commerciaux
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
Automatic and interactive image segmentation for visual search
Keyword
NSERC
Application summary
Slyce Inc. specializes in the design and development of visual search solutions that address the challenges oftraditional product search for online and mobile shoppers. Slyce's IP visual search platform enables consumersto search for their desired product by snapping a photo with their smartphone or clicking on an image in theirbrowsers. Retrieving exact or visually-similar products from client retailers' catalog, Slyce's platform enablesthe retailers to clinch an on-the-spot sale at the moment of inspiration.The performance & the quality of experience of Slyce's current visual search technology has drawn greatinterest from the end-users and the engaged retailers and publishers who have tried the beta releases of ourmobile and web applications, resulting in the Slyce technology to be named as the best Retail Innovation of2013 by Startup Calgary. However, in order for Slyce to preserve its competitive advantage, we need tocontinue to improve and expand our current technology, particularly with the rapid growth of our business.Slyce seeks to leverage the knowledge and expertise of Dr. Zelek and his group to improve the performance ofits visual search technology by means of image segmentation. In particular, the goal of this project is two-fold:first, to investigate how automatic image segmentation can enable our visual search technology to focus on themost salient regions of the image (most potentially containing the object of user's interest); and second, toinvestigate how user's input (e.g., an annotation window placed around the target object, or the marks drawn onthe object) can be combined with the automatic segmentation of the first fold to produce a higher segmentationaccuracy.The project will support the continued development and service of a $50B market in retailers through onlineand mobile experiences. The net benefit is additional accuracy to the overall visual search process, bringinggreater service levels to apparel retailers, a more competitive offering in the market, and thus greatercertainty/profitability for the company.