Grant: Engage Grants Program
Ryerson University
$25,000.00
Extracting cosmetics product ingredients from noisy OCR images submitted by user's smart devices
FY 2016-17
Summary
In this project we develop an algorithm to help consumers of Think Dirty Company obtaining cosmeticsproducts safety information. This information, in terms of toxicity, carcinogenicity and allergenicity of theiringredients, is provided by using the OCR technology. Research and development of a machine learningalgorithm, using the OCR technology, is the focus of this project. The objectives of this proposal arecomputational approaches to a number of key research-intensive problems associated with acquisition,recognition and management of cosmetics product safety-related data from smart device product images, onlinedatabases and scientific literature. The proposed project has three main steps: 1) Finding and creating aninnovative algorithm in recognition of cosmetics product ingredient names in noisy OCR results from smartdevices images 2) Development of API to mass process ingredients and image submissions by users 3)Development of API to effectively clean and map out data. This research has significant impacts forsocio-economic, environmental and health issues. It will also provide direct economic benefits to Think DirtyInc, through creation of novel intellectual property directly affecting the company bottom line by facilitatingbetter service to customers and reducing the costs. Since the company's main product is targeting the globalmarket, using the research proposed here to improve the product competitiveness, will also facilitate exportrevenue growth. The HQP involved in this project will be exposed to a practical industrial problem thatrequires knowledge and implementation of machine learning, OCR technology, and image processingtechniques.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
503260-2016
Name nom
Beheshti, Soosan
Department département
Electrical and Computer Engineering
Organization id
43
Institution établissement
Ryerson University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
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
1200
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Advancement of knowledge
Area of application fr
Avancement des connaissances
Research subject code
2510
Research subject group en
Electrical and electronic engineering
Research subject group fr
Génie électrique et électronique
Research subject en
Adaptive, learning and evolutionary systems
Research subject fr
Systèmes d'apprentissage adaptatifs et évolutifs
Partie
1
Nb partie
1
Application title
Extracting cosmetics product ingredients from noisy OCR images submitted by user's smart devices
Keyword
NSERC
Application summary
In this project we develop an algorithm to help consumers of Think Dirty Company obtaining cosmeticsproducts safety information. This information, in terms of toxicity, carcinogenicity and allergenicity of theiringredients, is provided by using the OCR technology. Research and development of a machine learningalgorithm, using the OCR technology, is the focus of this project. The objectives of this proposal arecomputational approaches to a number of key research-intensive problems associated with acquisition,recognition and management of cosmetics product safety-related data from smart device product images, onlinedatabases and scientific literature. The proposed project has three main steps: 1) Finding and creating aninnovative algorithm in recognition of cosmetics product ingredient names in noisy OCR results from smartdevices images 2) Development of API to mass process ingredients and image submissions by users 3)Development of API to effectively clean and map out data. This research has significant impacts forsocio-economic, environmental and health issues. It will also provide direct economic benefits to Think DirtyInc, through creation of novel intellectual property directly affecting the company bottom line by facilitatingbetter service to customers and reducing the costs. Since the company's main product is targeting the globalmarket, using the research proposed here to improve the product competitiveness, will also facilitate exportrevenue growth. The HQP involved in this project will be exposed to a practical industrial problem thatrequires knowledge and implementation of machine learning, OCR technology, and image processingtechniques.