Automated Detection of Fish Bones in Salmon Fillets using X-ray Testing. Mery, D., Lillo, I., Loebel, H., Riffo, V., Soto, A., Cipriano, A., & Aguilera, J. In Proc. of 4th Pacific-Rim Symposium on Image and Video Technology (PSIVT-2010), 2010. Paper abstract bibtex 1 download X-ray testing is playing an increasingly important role in food quality assurance. In the production of fish fillets, however, fish bone detection is performed by human operators using their sense of touch and vision which can lead to misclassification. In countries where fish is often consumed, fish bones are some of the most frequently ingested foreign bodies encountered in foods. Effective detection of fish bones in the quality control process would help avoid this problem. For this reason, we developed an X-ray machine vision approach to au- tomatically detect fish bones in fish fillets. This paper describes our approach and the corresponding validation experiments with salmon fillets. The approach consists of six steps: 1) A digital X-ray image is taken of the fish fillet being tested. 2) The X-ray image is filtered and enhanced to facilitate the detection of fish bones. 3) Potential fish bones in the image are segmented using band pass filtering, thresholding and morphological techniques. 4) Intensity features of the enhanced X-ray image are extracted from small detection windows that are defined in those regions where potential fish bones were segmented. 5) A classifier is used to discriminate between ‘bones’ and ‘no-bones’ classes in the detection windows. 6) Finally, fish bones in the X-ray image are isolated using morphological operations applied on the corresponding segments classified as ‘bones’. In the experiments we used a high resolution flat panel detector with the capacity to capture up to a 6 million pixel digital X-ray image. In the training phase, we analyzed 20 representative salmon fillets, 7700 detection windows (10×10 pixels) and 279 intensity features. Cross validation yielded a detection performance of 95% using a support vector machine classifier with only 24 selected features. We believe that the proposed approach opens new possibilities in the field of automated visual inspection of salmon and other similar fish.
@InProceedings{ mery-psivt:etal:2010,
author = {D. Mery and I. Lillo and H. Loebel and V. Riffo and A.
Soto and A. Cipriano and JM. Aguilera},
title = {Automated Detection of Fish Bones in Salmon Fillets using
X-ray Testing},
booktitle = {Proc. of 4th Pacific-Rim Symposium on Image and Video
Technology (PSIVT-2010)},
year = {2010},
abstract = {X-ray testing is playing an increasingly important role in
food quality assurance. In the production of fish fillets,
however, fish bone detection is performed by human
operators using their sense of touch and vision which can
lead to misclassification. In countries where fish is often
consumed, fish bones are some of the most frequently
ingested foreign bodies encountered in foods. Effective
detection of fish bones in the quality control process
would help avoid this problem. For this reason, we
developed an X-ray machine vision approach to au-
tomatically detect fish bones in fish fillets. This paper
describes our approach and the corresponding validation
experiments with salmon fillets. The approach consists of
six steps: 1) A digital X-ray image is taken of the fish
fillet being tested. 2) The X-ray image is filtered and
enhanced to facilitate the detection of fish bones. 3)
Potential fish bones in the image are segmented using band
pass filtering, thresholding and morphological techniques.
4) Intensity features of the enhanced X-ray image are
extracted from small detection windows that are defined in
those regions where potential fish bones were segmented. 5)
A classifier is used to discriminate between ‘bones’
and ‘no-bones’ classes in the detection windows. 6)
Finally, fish bones in the X-ray image are isolated using
morphological operations applied on the corresponding
segments classified as ‘bones’. In the experiments we
used a high resolution flat panel detector with the
capacity to capture up to a 6 million pixel digital X-ray
image. In the training phase, we analyzed 20 representative
salmon fillets, 7700 detection windows (10×10 pixels) and
279 intensity features. Cross validation yielded a
detection performance of 95% using a support vector machine
classifier with only 24 selected features. We believe that
the proposed approach opens new possibilities in the field
of automated visual inspection of salmon and other similar
fish. },
url = {http://saturno.ing.puc.cl/media/papers_alvaro/PSIVT-2010.pdf}
}
Downloads: 1
{"_id":{"_str":"534276560e946d920a0011aa"},"__v":397,"authorIDs":["32ZR23o2BFySHbtQK","3ear6KFZSRqbj6YeT","4Pq6KLaQ8jKGXHZWH","5456ff2b8b01c819300000f6","54578d9a2abc8e9f370004f0","547561eacb4bf04e39000ace","5e126ca5a4cabfdf01000053","5e158f76f1f31adf01000118","5e16174bf67f7dde010003ad","5e1f631ae8f5ddde010000eb","5e1f7182e8f5ddde010001ff","5e26da3642065ede01000066","5e3acefaf2a00cdf010001c8","5e62c3aecb259cde010000f9","5e65830c6e5f4cf3010000e7","5e666dfc46e828de010002c9","6cMBYieMJhf6Nd58M","6w6sGsxYSK2Quk6yZ","7xDcntrrtC62vkWM5","ARw5ReidxxZii9TTZ","BjzM7QpRCG7uCF7Zf","DQ4JRTTWkvKXtCNCp","GbYBJvxugXMriQwbi","HhRoRmBvwWfD4oLyK","JFk6x26H6LZMoht2n","JvArGGu5qM6EvSCvB","LpqQBhFH3PxepH9KY","MT4TkSGzAp69M3dGt","QFECgvB5v2i4j2Qzs","RKv56Kes3h6FwEa55","Rb9TkQ3KkhGAaNyXq","RdND8NxcJDsyZdkcK","SpKJ5YujbHKZnHc4v","TSRdcx4bbYKqcGbDg","W8ogS2GJa6sQKy26c","WTi3X2fT8dzBN5d8b","WfZbctNQYDBaiYW6n","XZny8xuqwfoxzhBCB","Xk2Q5qedS5MFHvjEW","bbARiTJLYS79ZMFbk","cBxsyeZ37EucQeBYK","cFyFQps7W3Sa2Wope","dGRBfr8zhMmbwK6eP","eRLgwkrEk7T7Lmzmf","fMYSCX8RMZap548vv","g6iKCQCFnJgKYYHaP","h2hTcQYuf2PB3oF8t","h83jBvZYJPJGutQrs","jAtuJBcGhng4Lq2Nd","pMoo2gotJcdDPwfrw","q5Zunk5Y2ruhw5vyq","rzNGhqxkbt2MvGY29","uC8ATA8AfngWpYLBq","uoJ7BKv28Q6TtPmPp","vMiJzqEKCsBxBEa3v","vQE6iTPpjxpuLip2Z","wQDRsDjhgpMJDGxWX","wbNg79jvDpzX9zHLK","wk86BgRiooBjy323E","zCbPxKnQGgDHiHMWn","zf9HENjsAzdWLMDAu"],"author_short":["Mery, D.","Lillo, I.","Loebel, H.","Riffo, V.","Soto, A.","Cipriano, A.","Aguilera, J."],"bibbaseid":"mery-lillo-loebel-riffo-soto-cipriano-aguilera-automateddetectionoffishbonesinsalmonfilletsusingxraytesting-2010","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["D."],"propositions":[],"lastnames":["Mery"],"suffixes":[]},{"firstnames":["I."],"propositions":[],"lastnames":["Lillo"],"suffixes":[]},{"firstnames":["H."],"propositions":[],"lastnames":["Loebel"],"suffixes":[]},{"firstnames":["V."],"propositions":[],"lastnames":["Riffo"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Soto"],"suffixes":[]},{"firstnames":["A."],"propositions":[],"lastnames":["Cipriano"],"suffixes":[]},{"firstnames":["JM."],"propositions":[],"lastnames":["Aguilera"],"suffixes":[]}],"title":"Automated Detection of Fish Bones in Salmon Fillets using X-ray Testing","booktitle":"Proc. of 4th Pacific-Rim Symposium on Image and Video Technology (PSIVT-2010)","year":"2010","abstract":"X-ray testing is playing an increasingly important role in food quality assurance. In the production of fish fillets, however, fish bone detection is performed by human operators using their sense of touch and vision which can lead to misclassification. In countries where fish is often consumed, fish bones are some of the most frequently ingested foreign bodies encountered in foods. Effective detection of fish bones in the quality control process would help avoid this problem. For this reason, we developed an X-ray machine vision approach to au- tomatically detect fish bones in fish fillets. This paper describes our approach and the corresponding validation experiments with salmon fillets. The approach consists of six steps: 1) A digital X-ray image is taken of the fish fillet being tested. 2) The X-ray image is filtered and enhanced to facilitate the detection of fish bones. 3) Potential fish bones in the image are segmented using band pass filtering, thresholding and morphological techniques. 4) Intensity features of the enhanced X-ray image are extracted from small detection windows that are defined in those regions where potential fish bones were segmented. 5) A classifier is used to discriminate between ‘bones’ and ‘no-bones’ classes in the detection windows. 6) Finally, fish bones in the X-ray image are isolated using morphological operations applied on the corresponding segments classified as ‘bones’. In the experiments we used a high resolution flat panel detector with the capacity to capture up to a 6 million pixel digital X-ray image. In the training phase, we analyzed 20 representative salmon fillets, 7700 detection windows (10×10 pixels) and 279 intensity features. Cross validation yielded a detection performance of 95% using a support vector machine classifier with only 24 selected features. We believe that the proposed approach opens new possibilities in the field of automated visual inspection of salmon and other similar fish. ","url":"http://saturno.ing.puc.cl/media/papers_alvaro/PSIVT-2010.pdf","bibtex":"@InProceedings{\t mery-psivt:etal:2010,\n author\t= {D. Mery and I. Lillo and H. Loebel and V. Riffo and A.\n\t\t Soto and A. Cipriano and JM. Aguilera},\n title\t\t= {Automated Detection of Fish Bones in Salmon Fillets using\n\t\t X-ray Testing},\n booktitle\t= {Proc. of 4th Pacific-Rim Symposium on Image and Video\n\t\t Technology (PSIVT-2010)},\n year\t\t= {2010},\n abstract\t= {X-ray testing is playing an increasingly important role in\n\t\t food quality assurance. In the production of fish fillets,\n\t\t however, fish bone detection is performed by human\n\t\t operators using their sense of touch and vision which can\n\t\t lead to misclassification. In countries where fish is often\n\t\t consumed, fish bones are some of the most frequently\n\t\t ingested foreign bodies encountered in foods. Effective\n\t\t detection of fish bones in the quality control process\n\t\t would help avoid this problem. For this reason, we\n\t\t developed an X-ray machine vision approach to au-\n\t\t tomatically detect fish bones in fish fillets. This paper\n\t\t describes our approach and the corresponding validation\n\t\t experiments with salmon fillets. The approach consists of\n\t\t six steps: 1) A digital X-ray image is taken of the fish\n\t\t fillet being tested. 2) The X-ray image is filtered and\n\t\t enhanced to facilitate the detection of fish bones. 3)\n\t\t Potential fish bones in the image are segmented using band\n\t\t pass filtering, thresholding and morphological techniques.\n\t\t 4) Intensity features of the enhanced X-ray image are\n\t\t extracted from small detection windows that are defined in\n\t\t those regions where potential fish bones were segmented. 5)\n\t\t A classifier is used to discriminate between ‘bones’\n\t\t and ‘no-bones’ classes in the detection windows. 6)\n\t\t Finally, fish bones in the X-ray image are isolated using\n\t\t morphological operations applied on the corresponding\n\t\t segments classified as ‘bones’. In the experiments we\n\t\t used a high resolution flat panel detector with the\n\t\t capacity to capture up to a 6 million pixel digital X-ray\n\t\t image. In the training phase, we analyzed 20 representative\n\t\t salmon fillets, 7700 detection windows (10×10 pixels) and\n\t\t 279 intensity features. Cross validation yielded a\n\t\t detection performance of 95% using a support vector machine\n\t\t classifier with only 24 selected features. We believe that\n\t\t the proposed approach opens new possibilities in the field\n\t\t of automated visual inspection of salmon and other similar\n\t\t fish. },\n url\t\t= {http://saturno.ing.puc.cl/media/papers_alvaro/PSIVT-2010.pdf}\n}\n\n","author_short":["Mery, D.","Lillo, I.","Loebel, H.","Riffo, V.","Soto, A.","Cipriano, A.","Aguilera, J."],"key":"mery-psivt:etal:2010","id":"mery-psivt:etal:2010","bibbaseid":"mery-lillo-loebel-riffo-soto-cipriano-aguilera-automateddetectionoffishbonesinsalmonfilletsusingxraytesting-2010","role":"author","urls":{"Paper":"http://saturno.ing.puc.cl/media/papers_alvaro/PSIVT-2010.pdf"},"metadata":{"authorlinks":{"soto, a":"https://asoto.ing.puc.cl/publications/"}},"downloads":1},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/ialab-puc/ialab.ing.puc.cl/master/pubs.bib","downloads":1,"keywords":[],"search_terms":["automated","detection","fish","bones","salmon","fillets","using","ray","testing","mery","lillo","loebel","riffo","soto","cipriano","aguilera"],"title":"Automated Detection of Fish Bones in Salmon Fillets using X-ray Testing","year":2010,"dataSources":["3YPRCmmijLqF4qHXd","sg6yZ29Z2xB5xP79R","sj4fjnZAPkEeYdZqL","m8qFBfFbjk9qWjcmJ","QjT2DEZoWmQYxjHXS"]}