Limits...
Species Identification of Food Contaminating Beetles by Recognizing Patterns in Microscopic Images of Elytra Fragments.

Park SI, Bisgin H, Ding H, Semey HG, Langley DA, Tong W, Xu J - PLoS ONE (2016)

Bottom Line: A crucial step of food contamination inspection is identifying the species of beetle fragments found in the sample, since the presence of some storage beetles is a good indicator of insanitation or potential food safety hazards.Both global and local characteristics were quantified and used as feature inputs to artificial neural networks for species classification.Through examining the overall and per species accuracies, we further demonstrated that the local features are better suited than the global features for species identification.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, Texas A&M University, College Station, Texas, United States of America.

ABSTRACT
A crucial step of food contamination inspection is identifying the species of beetle fragments found in the sample, since the presence of some storage beetles is a good indicator of insanitation or potential food safety hazards. The current pratice, visual examination by human analysts, is time consuming and requires several years of experience. Here we developed a species identification algorithm which utilizes images of microscopic elytra fragments. The elytra, or hardened forewings, occupy a large portion of the body, and contain distinctive patterns. In addition, elytra fragments are more commonly recovered from processed food products than other body parts due to their hardness. As a preliminary effort, we chose 15 storage product beetle species frequently detected in food inspection. The elytra were then separated from the specimens and imaged under a microscope. Both global and local characteristics were quantified and used as feature inputs to artificial neural networks for species classification. With leave-one-out cross validation, we achieved overall accuracy of 80% through the proposed global and local features, which indicates that our proposed features could differentiate these species. Through examining the overall and per species accuracies, we further demonstrated that the local features are better suited than the global features for species identification. Future work will include robust testing with more beetle species and algorithm refinement for a higher accuracy.

No MeSH data available.


Related in: MedlinePlus

Overall accuracies of species identification using four different feature sets.Each bar plots the mean and the standard deviation of the overall accuracy achieved during 100 rounds of cross validation.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4920424&req=5

pone.0157940.g011: Overall accuracies of species identification using four different feature sets.Each bar plots the mean and the standard deviation of the overall accuracy achieved during 100 rounds of cross validation.

Mentions: Fig 11 shows the overall identification accuracy for each of four feature sets, which are labeled “global features 1”, “global features 2”, “local features”, and “all features”, respectively. Networks built with all features achieved the highest overall identification accuracy (with a mean accuracy at 80%). When comparing the results between “global features 1/2” and “local features”, and those between “local features” and “all features”, the global features performed worse than the local features and seemed to contribute little to the overall performance achieved by “all features”. Furthermore, except two or three rounds of cross validation, local features consistenly outperformed the global features 1 and 2 (data not shown). This result implies that the local features are more likely than the global features to capture the elytra characteristics specific to each species. In addition, it supports the interpretation that the global features might be more sensitive to overall data quality than the local features computed around the refined and merged feature points. In turn, the necessity of collecting image data with consistent quality needs to be emphasized for further research.


Species Identification of Food Contaminating Beetles by Recognizing Patterns in Microscopic Images of Elytra Fragments.

Park SI, Bisgin H, Ding H, Semey HG, Langley DA, Tong W, Xu J - PLoS ONE (2016)

Overall accuracies of species identification using four different feature sets.Each bar plots the mean and the standard deviation of the overall accuracy achieved during 100 rounds of cross validation.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4920424&req=5

pone.0157940.g011: Overall accuracies of species identification using four different feature sets.Each bar plots the mean and the standard deviation of the overall accuracy achieved during 100 rounds of cross validation.
Mentions: Fig 11 shows the overall identification accuracy for each of four feature sets, which are labeled “global features 1”, “global features 2”, “local features”, and “all features”, respectively. Networks built with all features achieved the highest overall identification accuracy (with a mean accuracy at 80%). When comparing the results between “global features 1/2” and “local features”, and those between “local features” and “all features”, the global features performed worse than the local features and seemed to contribute little to the overall performance achieved by “all features”. Furthermore, except two or three rounds of cross validation, local features consistenly outperformed the global features 1 and 2 (data not shown). This result implies that the local features are more likely than the global features to capture the elytra characteristics specific to each species. In addition, it supports the interpretation that the global features might be more sensitive to overall data quality than the local features computed around the refined and merged feature points. In turn, the necessity of collecting image data with consistent quality needs to be emphasized for further research.

Bottom Line: A crucial step of food contamination inspection is identifying the species of beetle fragments found in the sample, since the presence of some storage beetles is a good indicator of insanitation or potential food safety hazards.Both global and local characteristics were quantified and used as feature inputs to artificial neural networks for species classification.Through examining the overall and per species accuracies, we further demonstrated that the local features are better suited than the global features for species identification.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science, Texas A&M University, College Station, Texas, United States of America.

ABSTRACT
A crucial step of food contamination inspection is identifying the species of beetle fragments found in the sample, since the presence of some storage beetles is a good indicator of insanitation or potential food safety hazards. The current pratice, visual examination by human analysts, is time consuming and requires several years of experience. Here we developed a species identification algorithm which utilizes images of microscopic elytra fragments. The elytra, or hardened forewings, occupy a large portion of the body, and contain distinctive patterns. In addition, elytra fragments are more commonly recovered from processed food products than other body parts due to their hardness. As a preliminary effort, we chose 15 storage product beetle species frequently detected in food inspection. The elytra were then separated from the specimens and imaged under a microscope. Both global and local characteristics were quantified and used as feature inputs to artificial neural networks for species classification. With leave-one-out cross validation, we achieved overall accuracy of 80% through the proposed global and local features, which indicates that our proposed features could differentiate these species. Through examining the overall and per species accuracies, we further demonstrated that the local features are better suited than the global features for species identification. Future work will include robust testing with more beetle species and algorithm refinement for a higher accuracy.

No MeSH data available.


Related in: MedlinePlus