Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks
The control of biofouling on marine vessels is challenging and costly. Early detection before hull performance is significantly affected is desirable, especially if “grooming” is an option. Here, a system is described to detect marine fouling at an early stage of development. In this study, an image...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/88686 http://hdl.handle.net/10220/45854 |
| _version_ | 1811680674744107008 |
|---|---|
| author | Chin, C. S. Si, JianTing Clare, A. S. Ma, Maode |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Chin, C. S. Si, JianTing Clare, A. S. Ma, Maode |
| author_sort | Chin, C. S. |
| collection | NTU |
| description | The control of biofouling on marine vessels is challenging and costly. Early detection before hull performance is significantly affected is desirable, especially if “grooming” is an option. Here, a system is described to detect marine fouling at an early stage of development. In this study, an image of fouling can be transferred wirelessly via a mobile network for analysis. The proposed system utilizes transfer learning and deep convolutional neural network (CNN) to perform image recognition on the fouling image by classifying the detected fouling species and the density of fouling on the surface. Transfer learning using Google’s Inception V3 model with Softmax at last layer was carried out on a fouling database of 10 categories and 1825 images. Experimental results gave acceptable accuracies for fouling detection and recognition. |
| first_indexed | 2024-10-01T03:28:49Z |
| format | Journal Article |
| id | ntu-10356/88686 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:28:49Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/886862020-03-07T14:02:36Z Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks Chin, C. S. Si, JianTing Clare, A. S. Ma, Maode School of Electrical and Electronic Engineering Convolutional Neural Network (CNN) DRNTU::Engineering::Electrical and electronic engineering Image Recognition The control of biofouling on marine vessels is challenging and costly. Early detection before hull performance is significantly affected is desirable, especially if “grooming” is an option. Here, a system is described to detect marine fouling at an early stage of development. In this study, an image of fouling can be transferred wirelessly via a mobile network for analysis. The proposed system utilizes transfer learning and deep convolutional neural network (CNN) to perform image recognition on the fouling image by classifying the detected fouling species and the density of fouling on the surface. Transfer learning using Google’s Inception V3 model with Softmax at last layer was carried out on a fouling database of 10 categories and 1825 images. Experimental results gave acceptable accuracies for fouling detection and recognition. Published version 2018-09-06T03:50:37Z 2019-12-06T17:08:50Z 2018-09-06T03:50:37Z 2019-12-06T17:08:50Z 2017 Journal Article Chin, C. S., Si, J., Clare, A. S., & Ma, M. (2017). Intelligent Image Recognition System for Marine Fouling Using Softmax Transfer Learning and Deep Convolutional Neural Networks. Complexity, 2017, 5730419-. doi:10.1155/2017/5730419 1076-2787 https://hdl.handle.net/10356/88686 http://hdl.handle.net/10220/45854 10.1155/2017/5730419 en Complexity © 2017 C. S. Chin et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 9 p. application/pdf |
| spellingShingle | Convolutional Neural Network (CNN) DRNTU::Engineering::Electrical and electronic engineering Image Recognition Chin, C. S. Si, JianTing Clare, A. S. Ma, Maode Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| title | Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| title_full | Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| title_fullStr | Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| title_full_unstemmed | Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| title_short | Intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| title_sort | intelligent image recognition system for marine fouling using softmax transfer learning and deep convolutional neural networks |
| topic | Convolutional Neural Network (CNN) DRNTU::Engineering::Electrical and electronic engineering Image Recognition |
| url | https://hdl.handle.net/10356/88686 http://hdl.handle.net/10220/45854 |
| work_keys_str_mv | AT chincs intelligentimagerecognitionsystemformarinefoulingusingsoftmaxtransferlearninganddeepconvolutionalneuralnetworks AT sijianting intelligentimagerecognitionsystemformarinefoulingusingsoftmaxtransferlearninganddeepconvolutionalneuralnetworks AT clareas intelligentimagerecognitionsystemformarinefoulingusingsoftmaxtransferlearninganddeepconvolutionalneuralnetworks AT mamaode intelligentimagerecognitionsystemformarinefoulingusingsoftmaxtransferlearninganddeepconvolutionalneuralnetworks |