Fingerlings mass estimation: A comparison between deep and shallow learning algorithms
The paper presents some results regarding the automatic mass estimation of Pintado Real fingerlings, using machine learning techniques to support the fish production process. For this purpose, an image dataset called FISHCV1206FSEG, was created which is composed of 1206 images of fingerlings with th...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Elsevier
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/6ba35f5a32c547899ff4f496b328e284 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:6ba35f5a32c547899ff4f496b328e284 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:6ba35f5a32c547899ff4f496b328e2842021-11-20T05:16:19ZFingerlings mass estimation: A comparison between deep and shallow learning algorithms2772-375510.1016/j.atech.2021.100020https://doaj.org/article/6ba35f5a32c547899ff4f496b328e2842021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2772375521000204https://doaj.org/toc/2772-3755The paper presents some results regarding the automatic mass estimation of Pintado Real fingerlings, using machine learning techniques to support the fish production process. For this purpose, an image dataset called FISHCV1206FSEG, was created which is composed of 1206 images of fingerlings with their respective annotated masses. Through the fish contours, the area and perimeter were extracted, and submitted to the J48, SVM, and KNN classification algorithms and a linear regression algorithm. The images were also submitted to ResNet50, InceptionV3, Exception, VGG16, and VGG19 convolutional neural networks. As a result, the classification algorithm J48 reached an accuracy of 58.2% and a linear regression model capable of predicting the mass of a Pintado Real fingerling with a mean squared error of 1.5 g. The convolutional neural network ResNet50 obtained an accuracy of 67.08%. We can highlight the contributions of this work through the presentation of a methodology to classify the mass of fingerlings in a non-invasive way and by the analyses and comparing results of different machine learning algorithms for classification and regression.Adair da Silva Oliveira JuniorDiego André Sant’AnaMarcio Carneiro Brito PacheVanir GarciaVanessa Aparecida de Moares WeberGilberto AstolfiFabricio de Lima WeberGeazy Vilharva MenezesGabriel Kirsten MenezesPedro Lucas França AlbuquerqueCelso Soares CostaEduardo Quirino Arguelho de QueirozJoão Victor Araújo RozalesMilena Wolff FerreiraMarco Hiroshi NakaHemerson PistoriElsevierarticleFishClassificationMass estimatePintado realComputer visionAgriculture (General)S1-972Agricultural industriesHD9000-9495ENSmart Agricultural Technology, Vol 1, Iss , Pp 100020- (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Fish Classification Mass estimate Pintado real Computer vision Agriculture (General) S1-972 Agricultural industries HD9000-9495 |
| spellingShingle |
Fish Classification Mass estimate Pintado real Computer vision Agriculture (General) S1-972 Agricultural industries HD9000-9495 Adair da Silva Oliveira Junior Diego André Sant’Ana Marcio Carneiro Brito Pache Vanir Garcia Vanessa Aparecida de Moares Weber Gilberto Astolfi Fabricio de Lima Weber Geazy Vilharva Menezes Gabriel Kirsten Menezes Pedro Lucas França Albuquerque Celso Soares Costa Eduardo Quirino Arguelho de Queiroz João Victor Araújo Rozales Milena Wolff Ferreira Marco Hiroshi Naka Hemerson Pistori Fingerlings mass estimation: A comparison between deep and shallow learning algorithms |
| description |
The paper presents some results regarding the automatic mass estimation of Pintado Real fingerlings, using machine learning techniques to support the fish production process. For this purpose, an image dataset called FISHCV1206FSEG, was created which is composed of 1206 images of fingerlings with their respective annotated masses. Through the fish contours, the area and perimeter were extracted, and submitted to the J48, SVM, and KNN classification algorithms and a linear regression algorithm. The images were also submitted to ResNet50, InceptionV3, Exception, VGG16, and VGG19 convolutional neural networks. As a result, the classification algorithm J48 reached an accuracy of 58.2% and a linear regression model capable of predicting the mass of a Pintado Real fingerling with a mean squared error of 1.5 g. The convolutional neural network ResNet50 obtained an accuracy of 67.08%. We can highlight the contributions of this work through the presentation of a methodology to classify the mass of fingerlings in a non-invasive way and by the analyses and comparing results of different machine learning algorithms for classification and regression. |
| format |
article |
| author |
Adair da Silva Oliveira Junior Diego André Sant’Ana Marcio Carneiro Brito Pache Vanir Garcia Vanessa Aparecida de Moares Weber Gilberto Astolfi Fabricio de Lima Weber Geazy Vilharva Menezes Gabriel Kirsten Menezes Pedro Lucas França Albuquerque Celso Soares Costa Eduardo Quirino Arguelho de Queiroz João Victor Araújo Rozales Milena Wolff Ferreira Marco Hiroshi Naka Hemerson Pistori |
| author_facet |
Adair da Silva Oliveira Junior Diego André Sant’Ana Marcio Carneiro Brito Pache Vanir Garcia Vanessa Aparecida de Moares Weber Gilberto Astolfi Fabricio de Lima Weber Geazy Vilharva Menezes Gabriel Kirsten Menezes Pedro Lucas França Albuquerque Celso Soares Costa Eduardo Quirino Arguelho de Queiroz João Victor Araújo Rozales Milena Wolff Ferreira Marco Hiroshi Naka Hemerson Pistori |
| author_sort |
Adair da Silva Oliveira Junior |
| title |
Fingerlings mass estimation: A comparison between deep and shallow learning algorithms |
| title_short |
Fingerlings mass estimation: A comparison between deep and shallow learning algorithms |
| title_full |
Fingerlings mass estimation: A comparison between deep and shallow learning algorithms |
| title_fullStr |
Fingerlings mass estimation: A comparison between deep and shallow learning algorithms |
| title_full_unstemmed |
Fingerlings mass estimation: A comparison between deep and shallow learning algorithms |
| title_sort |
fingerlings mass estimation: a comparison between deep and shallow learning algorithms |
| publisher |
Elsevier |
| publishDate |
2021 |
| url |
https://doaj.org/article/6ba35f5a32c547899ff4f496b328e284 |
| work_keys_str_mv |
AT adairdasilvaoliveirajunior fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT diegoandresantana fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT marciocarneirobritopache fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT vanirgarcia fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT vanessaaparecidademoaresweber fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT gilbertoastolfi fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT fabriciodelimaweber fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT geazyvilharvamenezes fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT gabrielkirstenmenezes fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT pedrolucasfrancaalbuquerque fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT celsosoarescosta fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT eduardoquirinoarguelhodequeiroz fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT joaovictoraraujorozales fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT milenawolffferreira fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT marcohiroshinaka fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms AT hemersonpistori fingerlingsmassestimationacomparisonbetweendeepandshallowlearningalgorithms |
| _version_ |
1718419487501320192 |