Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor
Over the last two decades, improvements in developing computational tools have made significant contributions to the classification of images of biological specimens to their corresponding species. These days, identification of biological species is much easier for taxonomists and even non-taxonomis...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Published: |
Iranian Fisheries Science Research Institute
2018
|
| Subjects: |
| _version_ | 1825721461878292480 |
|---|---|
| author | Kalafi, Elham Yousef Tan, Wooi Boon Town, Christopher Dhillon, Sarinder Kaur |
| author_facet | Kalafi, Elham Yousef Tan, Wooi Boon Town, Christopher Dhillon, Sarinder Kaur |
| author_sort | Kalafi, Elham Yousef |
| collection | UM |
| description | Over the last two decades, improvements in developing computational tools have made significant contributions to the classification of images of biological specimens to their corresponding species. These days, identification of biological species is much easier for taxonomists and even non-taxonomists due to the development of automated computer techniques and systems. In this study, we developed a fully automated identification model for monogenean images based on the shape characters of the haptoral organs of eight species: Sinodiplectanotrema malayanum, Diplectanum jaculator, Trianchoratus pahangensis, Trianchoratus lonianchoratus, Trianchoratus malayensis, Metahaliotrema ypsilocleithru, Metahaliotrema mizellei and Metahaliotrema similis. Linear Discriminant Analysis (LDA) method was used to reduce the dimension of extracted feature vectors which were then used in the classification with K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN) classifiers for the identification of monogenean specimens of eight species. The need for the discovery of new characters for identification of species has been acknowledged for log by systematic parasitology. Using the overall form of anchors and bars for extraction of features led to acceptable results in automated classification of monogeneans. To date, this is the first fully automated identification model for monogeneans with an accuracy of 86.25% using KNN and 93.1% using ANN. |
| first_indexed | 2024-03-06T05:50:41Z |
| format | Article |
| id | um.eprints-20259 |
| institution | Universiti Malaya |
| last_indexed | 2024-03-06T05:50:41Z |
| publishDate | 2018 |
| publisher | Iranian Fisheries Science Research Institute |
| record_format | dspace |
| spelling | um.eprints-202592019-02-12T01:34:59Z http://eprints.um.edu.my/20259/ Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor Kalafi, Elham Yousef Tan, Wooi Boon Town, Christopher Dhillon, Sarinder Kaur Q Science (General) QH Natural history Over the last two decades, improvements in developing computational tools have made significant contributions to the classification of images of biological specimens to their corresponding species. These days, identification of biological species is much easier for taxonomists and even non-taxonomists due to the development of automated computer techniques and systems. In this study, we developed a fully automated identification model for monogenean images based on the shape characters of the haptoral organs of eight species: Sinodiplectanotrema malayanum, Diplectanum jaculator, Trianchoratus pahangensis, Trianchoratus lonianchoratus, Trianchoratus malayensis, Metahaliotrema ypsilocleithru, Metahaliotrema mizellei and Metahaliotrema similis. Linear Discriminant Analysis (LDA) method was used to reduce the dimension of extracted feature vectors which were then used in the classification with K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN) classifiers for the identification of monogenean specimens of eight species. The need for the discovery of new characters for identification of species has been acknowledged for log by systematic parasitology. Using the overall form of anchors and bars for extraction of features led to acceptable results in automated classification of monogeneans. To date, this is the first fully automated identification model for monogeneans with an accuracy of 86.25% using KNN and 93.1% using ANN. Iranian Fisheries Science Research Institute 2018 Article PeerReviewed Kalafi, Elham Yousef and Tan, Wooi Boon and Town, Christopher and Dhillon, Sarinder Kaur (2018) Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor. Iranian Journal of Fisheries Sciences, 17 (4). pp. 805-820. ISSN 1562-2916, http://jifro.areo.ir/article_117017.html |
| spellingShingle | Q Science (General) QH Natural history Kalafi, Elham Yousef Tan, Wooi Boon Town, Christopher Dhillon, Sarinder Kaur Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor |
| title | Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor |
| title_full | Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor |
| title_fullStr | Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor |
| title_full_unstemmed | Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor |
| title_short | Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor |
| title_sort | identification of selected monogeneans using image processing artificial neural network and k nearest neighbor |
| topic | Q Science (General) QH Natural history |
| work_keys_str_mv | AT kalafielhamyousef identificationofselectedmonogeneansusingimageprocessingartificialneuralnetworkandknearestneighbor AT tanwooiboon identificationofselectedmonogeneansusingimageprocessingartificialneuralnetworkandknearestneighbor AT townchristopher identificationofselectedmonogeneansusingimageprocessingartificialneuralnetworkandknearestneighbor AT dhillonsarinderkaur identificationofselectedmonogeneansusingimageprocessingartificialneuralnetworkandknearestneighbor |