اخبار و اعلانات

 آمار

تعداد نشریات286
تعداد نشریات سازمان84
تعداد شماره‌ها2,998
تعداد مقالات33,576
تعداد مشاهده مقاله44,216,264
تعداد دریافت فایل اصل مقاله20,565,930
Yousef Kalafi, Elham, Tan Wooi, Boon, Town, Christopher, Kaur Dhillon, Sarinder. (1397). Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor. سامانه مدیریت نشریات علمی, 17(4), 805-820. doi: 10.22092/ijfs.2018.117017
Elham Yousef Kalafi; Boon Tan Wooi; Christopher Town; Sarinder Kaur Dhillon. "Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor". سامانه مدیریت نشریات علمی, 17, 4, 1397, 805-820. doi: 10.22092/ijfs.2018.117017
Yousef Kalafi, Elham, Tan Wooi, Boon, Town, Christopher, Kaur Dhillon, Sarinder. (1397). 'Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor', سامانه مدیریت نشریات علمی, 17(4), pp. 805-820. doi: 10.22092/ijfs.2018.117017
Yousef Kalafi, Elham, Tan Wooi, Boon, Town, Christopher, Kaur Dhillon, Sarinder. Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor. سامانه مدیریت نشریات علمی, 1397; 17(4): 805-820. doi: 10.22092/ijfs.2018.117017

Identification of selected monogeneans using image processing, artificial neural network and K-nearest neighbor

Iranian Journal of Fisheries Sciences
مقاله 48، دوره 17، شماره 4، دی 2018، صفحه 805-820    اصل مقاله (695.26 K)
نوع مقاله: Research Paper
شناسه دیجیتال (DOI): 10.22092/ijfs.2018.117017
نویسندگان
Elham Yousef Kalafi1؛ Boon Tan Wooi1؛ Christopher Town2؛ Sarinder Kaur Dhillon* 1
1Institute of Biological Sciences, Faculty of Science,
2Computer Laboratory, University of Cambridge, Cambridge CB3 0FD, UK
چکیده
Abstract

Over the last two decades, improvements in developing computational tools made significant contributions to the classification of biological specimens` images to their correspondence species. These days, identification of biological species is much easier for taxonomist 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 classification with the K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN) classifiers for 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 overall form of anchors and bars for extraction of features were lead to achieve acceptable results in automated classification of monogenean. 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.
کلیدواژه‌ها
monogenean؛ Morphology؛ fish parasite؛ automated image recognition؛ Artificial Neural Networks؛ k-nearest neighbor؛ digital image processing
آمار
تعداد مشاهده مقاله: 503
تعداد دریافت فایل اصل مقاله: 323


counter
سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب