On the Efficacy of Handcrafted and Deep Features for Seed Image Classification
Computer vision techniques have become important in agriculture and plant sciences due to their wide variety of applications. In particular, the analysis of seeds can provide meaningful information on their evolution, the history of agriculture, the domestication of plants, and knowledge of diets in...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-08-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/7/9/171 |
| _version_ | 1797518643617071104 |
|---|---|
| author | Andrea Loddo Cecilia Di Ruberto |
| author_facet | Andrea Loddo Cecilia Di Ruberto |
| author_sort | Andrea Loddo |
| collection | DOAJ |
| description | Computer vision techniques have become important in agriculture and plant sciences due to their wide variety of applications. In particular, the analysis of seeds can provide meaningful information on their evolution, the history of agriculture, the domestication of plants, and knowledge of diets in ancient times. This work aims to propose an exhaustive comparison of several different types of features in the context of multiclass seed classification, leveraging two public plant seeds data sets to classify their families or species. In detail, we studied possible optimisations of five traditional machine learning classifiers trained with seven different categories of handcrafted features. We also fine-tuned several well-known convolutional neural networks (CNNs) and the recently proposed SeedNet to determine whether and to what extent using their deep features may be advantageous over handcrafted features. The experimental results demonstrated that CNN features are appropriate to the task and representative of the multiclass scenario. In particular, SeedNet achieved a mean F-measure of 96%, at least. Nevertheless, several cases showed satisfactory performance from the handcrafted features to be considered a valid alternative. In detail, we found that the Ensemble strategy combined with all the handcrafted features can achieve 90.93% of mean F-measure, at least, with a considerably lower amount of times. We consider the obtained results an excellent preliminary step towards realising an automatic seeds recognition and classification framework. |
| first_indexed | 2024-03-10T07:32:37Z |
| format | Article |
| id | doaj.art-226ae458552849dbb0845ac776e177a9 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T07:32:37Z |
| publishDate | 2021-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-226ae458552849dbb0845ac776e177a92023-11-22T13:44:02ZengMDPI AGJournal of Imaging2313-433X2021-08-017917110.3390/jimaging7090171On the Efficacy of Handcrafted and Deep Features for Seed Image ClassificationAndrea Loddo0Cecilia Di Ruberto1Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, ItalyDepartment of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, ItalyComputer vision techniques have become important in agriculture and plant sciences due to their wide variety of applications. In particular, the analysis of seeds can provide meaningful information on their evolution, the history of agriculture, the domestication of plants, and knowledge of diets in ancient times. This work aims to propose an exhaustive comparison of several different types of features in the context of multiclass seed classification, leveraging two public plant seeds data sets to classify their families or species. In detail, we studied possible optimisations of five traditional machine learning classifiers trained with seven different categories of handcrafted features. We also fine-tuned several well-known convolutional neural networks (CNNs) and the recently proposed SeedNet to determine whether and to what extent using their deep features may be advantageous over handcrafted features. The experimental results demonstrated that CNN features are appropriate to the task and representative of the multiclass scenario. In particular, SeedNet achieved a mean F-measure of 96%, at least. Nevertheless, several cases showed satisfactory performance from the handcrafted features to be considered a valid alternative. In detail, we found that the Ensemble strategy combined with all the handcrafted features can achieve 90.93% of mean F-measure, at least, with a considerably lower amount of times. We consider the obtained results an excellent preliminary step towards realising an automatic seeds recognition and classification framework.https://www.mdpi.com/2313-433X/7/9/171image analysisclassificationdeep learningfeatures extractionseeds analysis |
| spellingShingle | Andrea Loddo Cecilia Di Ruberto On the Efficacy of Handcrafted and Deep Features for Seed Image Classification Journal of Imaging image analysis classification deep learning features extraction seeds analysis |
| title | On the Efficacy of Handcrafted and Deep Features for Seed Image Classification |
| title_full | On the Efficacy of Handcrafted and Deep Features for Seed Image Classification |
| title_fullStr | On the Efficacy of Handcrafted and Deep Features for Seed Image Classification |
| title_full_unstemmed | On the Efficacy of Handcrafted and Deep Features for Seed Image Classification |
| title_short | On the Efficacy of Handcrafted and Deep Features for Seed Image Classification |
| title_sort | on the efficacy of handcrafted and deep features for seed image classification |
| topic | image analysis classification deep learning features extraction seeds analysis |
| url | https://www.mdpi.com/2313-433X/7/9/171 |
| work_keys_str_mv | AT andrealoddo ontheefficacyofhandcraftedanddeepfeaturesforseedimageclassification AT ceciliadiruberto ontheefficacyofhandcraftedanddeepfeaturesforseedimageclassification |