Detail publikace

An Imaging Method for Automated Detection of Acrylamide in Potato Chips

Originální název

An Imaging Method for Automated Detection of Acrylamide in Potato Chips

Anglický název

An Imaging Method for Automated Detection of Acrylamide in Potato Chips

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

BibTex


@inproceedings{BUT163642,
  author="Radim {Burget}",
  title="An Imaging Method for Automated Detection of Acrylamide in Potato Chips",
  annote="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.",
  address="IEEE",
  booktitle="IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics Engineering",
  chapter="163642",
  doi="10.1109/UPCON.2017.8251097",
  howpublished="online",
  institution="IEEE",
  year="2017",
  month="october",
  pages="1--4",
  publisher="IEEE",
  type="conference paper"
}