Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network
In this paper, we propose a novel method for plant leaves recognition by incorporating an unsupervised convolutional auto-encoder (CAE) and Siamese neural network in a unified framework by considering Siamese as an alternative to the conventional loss of CAE. Rather than the conventional exploitatio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/13/9/1705 |
| _version_ | 1797517147552874496 |
|---|---|
| author | Lamis Hamrouni Mohammed Lamine Kherfi Oussama Aiadi Abdellah Benbelghit |
| author_facet | Lamis Hamrouni Mohammed Lamine Kherfi Oussama Aiadi Abdellah Benbelghit |
| author_sort | Lamis Hamrouni |
| collection | DOAJ |
| description | In this paper, we propose a novel method for plant leaves recognition by incorporating an unsupervised convolutional auto-encoder (CAE) and Siamese neural network in a unified framework by considering Siamese as an alternative to the conventional loss of CAE. Rather than the conventional exploitation of CAE and Siamese, in our case we have proposed to extend CAE for a novel supervised scenario by considering it as one-class learning classifier. For each class, CAE is trained to reconstruct its positive and negative examples and Siamese is trained to distinguish the similarity and the dissimilarity of the obtained examples. On the contrary and asymmetric to the related hierarchical classification schemes which require pre-knowledge on the dataset being recognized, we propose a hierarchical classification scheme that doesn’t require such a pre-knowledge and can be employed by non-experts automatically. We cluster the dataset to assemble similar classes together. A test image is first assigned to the nearest cluster, then matched to one class from the classes that fall under the determined cluster using our novel one-class learning classifier. The proposed method has been evaluated on the ImageCLEF2012 dataset. Experimental results have proved the superiority of our method compared to several state-of-the art methods. |
| first_indexed | 2024-03-10T07:10:44Z |
| format | Article |
| id | doaj.art-9340218e2aa94cfab96942b10d6c3c18 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-10T07:10:44Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-9340218e2aa94cfab96942b10d6c3c182023-11-22T15:28:46ZengMDPI AGSymmetry2073-89942021-09-01139170510.3390/sym13091705Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural NetworkLamis Hamrouni0Mohammed Lamine Kherfi1Oussama Aiadi2Abdellah Benbelghit3Laboratoire de Génie Electrique (LAGE), University of Kasdi Merbah Ouargla, PB 511, Ouargla 30000, AlgeriaLAMIA Laboratory, University of Québec à Trois-Riviéres, Trois-Riviéres, QC G8Z 4M3, CanadaLINATI Laboratory, University of Kasdi Merbah Ouargla, PB 511, Ouargla 30000, AlgeriaLINATI Laboratory, University of Kasdi Merbah Ouargla, PB 511, Ouargla 30000, AlgeriaIn this paper, we propose a novel method for plant leaves recognition by incorporating an unsupervised convolutional auto-encoder (CAE) and Siamese neural network in a unified framework by considering Siamese as an alternative to the conventional loss of CAE. Rather than the conventional exploitation of CAE and Siamese, in our case we have proposed to extend CAE for a novel supervised scenario by considering it as one-class learning classifier. For each class, CAE is trained to reconstruct its positive and negative examples and Siamese is trained to distinguish the similarity and the dissimilarity of the obtained examples. On the contrary and asymmetric to the related hierarchical classification schemes which require pre-knowledge on the dataset being recognized, we propose a hierarchical classification scheme that doesn’t require such a pre-knowledge and can be employed by non-experts automatically. We cluster the dataset to assemble similar classes together. A test image is first assigned to the nearest cluster, then matched to one class from the classes that fall under the determined cluster using our novel one-class learning classifier. The proposed method has been evaluated on the ImageCLEF2012 dataset. Experimental results have proved the superiority of our method compared to several state-of-the art methods.https://www.mdpi.com/2073-8994/13/9/1705plant leaves classificationhierarchical classificationSiamese neural networkconvolutional auto-encoderone class learning |
| spellingShingle | Lamis Hamrouni Mohammed Lamine Kherfi Oussama Aiadi Abdellah Benbelghit Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network Symmetry plant leaves classification hierarchical classification Siamese neural network convolutional auto-encoder one class learning |
| title | Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network |
| title_full | Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network |
| title_fullStr | Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network |
| title_full_unstemmed | Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network |
| title_short | Plant Leaves Recognition Based on a Hierarchical One-Class Learning Scheme with Convolutional Auto-Encoder and Siamese Neural Network |
| title_sort | plant leaves recognition based on a hierarchical one class learning scheme with convolutional auto encoder and siamese neural network |
| topic | plant leaves classification hierarchical classification Siamese neural network convolutional auto-encoder one class learning |
| url | https://www.mdpi.com/2073-8994/13/9/1705 |
| work_keys_str_mv | AT lamishamrouni plantleavesrecognitionbasedonahierarchicaloneclasslearningschemewithconvolutionalautoencoderandsiameseneuralnetwork AT mohammedlaminekherfi plantleavesrecognitionbasedonahierarchicaloneclasslearningschemewithconvolutionalautoencoderandsiameseneuralnetwork AT oussamaaiadi plantleavesrecognitionbasedonahierarchicaloneclasslearningschemewithconvolutionalautoencoderandsiameseneuralnetwork AT abdellahbenbelghit plantleavesrecognitionbasedonahierarchicaloneclasslearningschemewithconvolutionalautoencoderandsiameseneuralnetwork |