Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye
In this study, we propose a method for training convolutional neural networks to make them identify and classify images with higher classification accuracy. By combining the Cartesian and polar coordinate systems when describing the images, the method of recognition and classification for plankton i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/9/2592 |
| _version_ | 1827717551753265152 |
|---|---|
| author | Xuemin Cheng Yong Ren Kaichang Cheng Jie Cao Qun Hao |
| author_facet | Xuemin Cheng Yong Ren Kaichang Cheng Jie Cao Qun Hao |
| author_sort | Xuemin Cheng |
| collection | DOAJ |
| description | In this study, we propose a method for training convolutional neural networks to make them identify and classify images with higher classification accuracy. By combining the Cartesian and polar coordinate systems when describing the images, the method of recognition and classification for plankton images is discussed. The optimized classification and recognition networks are constructed. They are available for in situ plankton images, exploiting the advantages of both coordinate systems in the network training process. Fusing the two types of vectors and using them as the input for conventional machine learning models for classification, support vector machines (SVMs) are selected as the classifiers to combine these two features of vectors, coming from different image coordinate descriptions. The accuracy of the proposed model was markedly higher than those of the initial classical convolutional neural networks when using the in situ plankton image data, with the increases in classification accuracy and recall rate being 5.3% and 5.1% respectively. In addition, the proposed training method can improve the classification performance considerably when used on the public CIFAR-10 dataset. |
| first_indexed | 2024-03-10T20:05:03Z |
| format | Article |
| id | doaj.art-02d7c4375e564025b1d3453edf086941 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:05:03Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-02d7c4375e564025b1d3453edf0869412023-11-19T23:20:07ZengMDPI AGSensors1424-82202020-05-01209259210.3390/s20092592Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human EyeXuemin Cheng0Yong Ren1Kaichang Cheng2Jie Cao3Qun Hao4Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaShenzhen International Graduate School, Tsinghua University, Shenzhen 518055, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, ChinaIn this study, we propose a method for training convolutional neural networks to make them identify and classify images with higher classification accuracy. By combining the Cartesian and polar coordinate systems when describing the images, the method of recognition and classification for plankton images is discussed. The optimized classification and recognition networks are constructed. They are available for in situ plankton images, exploiting the advantages of both coordinate systems in the network training process. Fusing the two types of vectors and using them as the input for conventional machine learning models for classification, support vector machines (SVMs) are selected as the classifiers to combine these two features of vectors, coming from different image coordinate descriptions. The accuracy of the proposed model was markedly higher than those of the initial classical convolutional neural networks when using the in situ plankton image data, with the increases in classification accuracy and recall rate being 5.3% and 5.1% respectively. In addition, the proposed training method can improve the classification performance considerably when used on the public CIFAR-10 dataset.https://www.mdpi.com/1424-8220/20/9/2592cartesian and polar coordinateclassification and recognitiontwo features combinationmechanisms of human eyeconvolutional neural network |
| spellingShingle | Xuemin Cheng Yong Ren Kaichang Cheng Jie Cao Qun Hao Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye Sensors cartesian and polar coordinate classification and recognition two features combination mechanisms of human eye convolutional neural network |
| title | Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye |
| title_full | Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye |
| title_fullStr | Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye |
| title_full_unstemmed | Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye |
| title_short | Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye |
| title_sort | method for training convolutional neural networks for in situ plankton image recognition and classification based on the mechanisms of the human eye |
| topic | cartesian and polar coordinate classification and recognition two features combination mechanisms of human eye convolutional neural network |
| url | https://www.mdpi.com/1424-8220/20/9/2592 |
| work_keys_str_mv | AT xuemincheng methodfortrainingconvolutionalneuralnetworksforinsituplanktonimagerecognitionandclassificationbasedonthemechanismsofthehumaneye AT yongren methodfortrainingconvolutionalneuralnetworksforinsituplanktonimagerecognitionandclassificationbasedonthemechanismsofthehumaneye AT kaichangcheng methodfortrainingconvolutionalneuralnetworksforinsituplanktonimagerecognitionandclassificationbasedonthemechanismsofthehumaneye AT jiecao methodfortrainingconvolutionalneuralnetworksforinsituplanktonimagerecognitionandclassificationbasedonthemechanismsofthehumaneye AT qunhao methodfortrainingconvolutionalneuralnetworksforinsituplanktonimagerecognitionandclassificationbasedonthemechanismsofthehumaneye |