An Imaging Method for Automated Detection of Acrylamide in Potato Chips

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F17%3APU136258" target="_blank" >RIV/00216305:26220/17:PU136258 - isvavai.cz</a>

Výsledek na webu

<a href="http://ieeexplore.ieee.org/document/8251097/?tp=&arnumber=8251097&refinements%3D4225165638%26filter%3DAND(p_IS_Number:8251011)" target="_blank" >http://ieeexplore.ieee.org/document/8251097/?tp=&arnumber=8251097&refinements%3D4225165638%26filter%3DAND(p_IS_Number:8251011)</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/UPCON.2017.8251097" target="_blank" >10.1109/UPCON.2017.8251097</a>

Jazyk výsledku

angličtina

Název v původním jazyce

An Imaging Method for Automated Detection of Acrylamide in Potato Chips

Popis výsledku v původním jazyce

Neurotoxin substance acrylamide is commonly formed in starchy food stuffs like potato during deep frying. This is a problem especially for small manufacturers. Conventionally identification of acrylamide is done by chemical based LC-MS analysis which is destructive, expensive procedure and may need expert manpower. Automated and non-destructive detection of such toxic substances like acrylamide in food stuffs is of great significance. The proposed work presents non-destructive imaging system for objective estimation of acrylamide in potato chips, which can be processed by most current smartphones. To find out discrimination between healthy and acrylamide affected potato chips, the area of chip (ROI) is automatically segmented from input image followed by feature analysis for machine learning. Statistical features were extracted from different components of ROI segmented color chip images. Extracted prominent features were subjected to artificial intelligence classifier for classification of healthy and acrylamide affected potato chip samples. The proposed imaging system is tested on a comprehensive dataset consisting of 84 samples and achieved 99% area under curve which is encouraging.

Název v anglickém jazyce

An Imaging Method for Automated Detection of Acrylamide in Potato Chips

Popis výsledku anglicky

Neurotoxin substance acrylamide is commonly formed in starchy food stuffs like potato during deep frying. This is a problem especially for small manufacturers. Conventionally identification of acrylamide is done by chemical based LC-MS analysis which is destructive, expensive procedure and may need expert manpower. Automated and non-destructive detection of such toxic substances like acrylamide in food stuffs is of great significance. The proposed work presents non-destructive imaging system for objective estimation of acrylamide in potato chips, which can be processed by most current smartphones. To find out discrimination between healthy and acrylamide affected potato chips, the area of chip (ROI) is automatically segmented from input image followed by feature analysis for machine learning. Statistical features were extracted from different components of ROI segmented color chip images. Extracted prominent features were subjected to artificial intelligence classifier for classification of healthy and acrylamide affected potato chip samples. The proposed imaging system is tested on a comprehensive dataset consisting of 84 samples and achieved 99% area under curve which is encouraging.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering

ISBN

978-1-5386-3004-4

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

487-490

Název nakladatele

IEEE

Místo vydání

Mathura, India, India

Místo konání akce

Delhi, Uttar Pradesh

Datum konání akce

26. 8. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000426124200086