Multilayer vectorization to develop a deeper image feature learning model
Computer-Aided Diagnosis (CAD) approaches categorise medical images substantially. Shape, colour, and texture can be problem-specific in medical imagery. Conventional approaches rely largely on them and their relationship, resulting in systems that can't illustrate high-issue domain ideas and h...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-04-01
|
| Series: | Automatika |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/00051144.2022.2157946 |
| _version_ | 1811176997849661440 |
|---|---|
| author | D. Hemanand N. P. G. Bhavani Shahanaz Ayub Mohd Wazih Ahmad S. Narayanan Anandakumar Haldorai |
| author_facet | D. Hemanand N. P. G. Bhavani Shahanaz Ayub Mohd Wazih Ahmad S. Narayanan Anandakumar Haldorai |
| author_sort | D. Hemanand |
| collection | DOAJ |
| description | Computer-Aided Diagnosis (CAD) approaches categorise medical images substantially. Shape, colour, and texture can be problem-specific in medical imagery. Conventional approaches rely largely on them and their relationship, resulting in systems that can't illustrate high-issue domain ideas and have weak prototype generalization. Deep learning techniques deliver an end-to-end model that classifies medical photos thoroughly. Due to the improved medical picture quality and short dataset size, this approach may have high processing costs and model layer restrictions. Multilayer vectorization and the Coding Network-Multilayer Perceptron (CNMP) are merged with deep learning to handle these challenges. This study extracts a high-level characteristic using vectorization, CNN, and conventional characteristics. The model's steps are below. The input picture is vectorized into a few pixels during preprocessing. These pixel images are delivered to a coding network being trained to create high-level classification feature vectors. Medical imaging fundamentals determine picture properties. Finally, neural networks combine the collected features. The recommended technique is tested on ISIC2017 and HIS2828. The model's accuracy is 91% and 92%. |
| first_indexed | 2024-04-10T20:01:07Z |
| format | Article |
| id | doaj.art-1eb337f317ea49a786714319b432841d |
| institution | Directory Open Access Journal |
| issn | 0005-1144 1848-3380 |
| language | English |
| last_indexed | 2024-04-10T20:01:07Z |
| publishDate | 2023-04-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Automatika |
| spelling | doaj.art-1eb337f317ea49a786714319b432841d2023-01-27T04:35:05ZengTaylor & Francis GroupAutomatika0005-11441848-33802023-04-0164235536410.1080/00051144.2022.2157946Multilayer vectorization to develop a deeper image feature learning modelD. Hemanand0N. P. G. Bhavani1Shahanaz Ayub2Mohd Wazih Ahmad3S. Narayanan4Anandakumar Haldorai5Department of Computer Science and Engineering, S.A. Engineering College (Autonomous), Chennai, Tamil Nadu, IndiaDepartment of Electronic Instrumentation Systems Institute of ECE Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Chennai, Tamilnadu, IndiaElectronics and Communication Engineering Department, Bundelkhand Institute of Engineering and Technology, Jhansi, Uttar Pradesh, IndiaComputer Science and Engineering, Adama Science and Technology University Adama, Adama, EthiopiaDepartment of Information Technology, SRM Valliammai Engineering College, Kattankulathur, Chengalpattu, IndiaDepartment of Computer science and engineering, Sri Eshwar College of Engineering, Coimbatore, Tamil Nadu, IndiaComputer-Aided Diagnosis (CAD) approaches categorise medical images substantially. Shape, colour, and texture can be problem-specific in medical imagery. Conventional approaches rely largely on them and their relationship, resulting in systems that can't illustrate high-issue domain ideas and have weak prototype generalization. Deep learning techniques deliver an end-to-end model that classifies medical photos thoroughly. Due to the improved medical picture quality and short dataset size, this approach may have high processing costs and model layer restrictions. Multilayer vectorization and the Coding Network-Multilayer Perceptron (CNMP) are merged with deep learning to handle these challenges. This study extracts a high-level characteristic using vectorization, CNN, and conventional characteristics. The model's steps are below. The input picture is vectorized into a few pixels during preprocessing. These pixel images are delivered to a coding network being trained to create high-level classification feature vectors. Medical imaging fundamentals determine picture properties. Finally, neural networks combine the collected features. The recommended technique is tested on ISIC2017 and HIS2828. The model's accuracy is 91% and 92%.https://www.tandfonline.com/doi/10.1080/00051144.2022.2157946Multi-layer vectorizationCNNimage feature extractionCoding Network Multi-layer Perceptron (CNMP) |
| spellingShingle | D. Hemanand N. P. G. Bhavani Shahanaz Ayub Mohd Wazih Ahmad S. Narayanan Anandakumar Haldorai Multilayer vectorization to develop a deeper image feature learning model Automatika Multi-layer vectorization CNN image feature extraction Coding Network Multi-layer Perceptron (CNMP) |
| title | Multilayer vectorization to develop a deeper image feature learning model |
| title_full | Multilayer vectorization to develop a deeper image feature learning model |
| title_fullStr | Multilayer vectorization to develop a deeper image feature learning model |
| title_full_unstemmed | Multilayer vectorization to develop a deeper image feature learning model |
| title_short | Multilayer vectorization to develop a deeper image feature learning model |
| title_sort | multilayer vectorization to develop a deeper image feature learning model |
| topic | Multi-layer vectorization CNN image feature extraction Coding Network Multi-layer Perceptron (CNMP) |
| url | https://www.tandfonline.com/doi/10.1080/00051144.2022.2157946 |
| work_keys_str_mv | AT dhemanand multilayervectorizationtodevelopadeeperimagefeaturelearningmodel AT npgbhavani multilayervectorizationtodevelopadeeperimagefeaturelearningmodel AT shahanazayub multilayervectorizationtodevelopadeeperimagefeaturelearningmodel AT mohdwazihahmad multilayervectorizationtodevelopadeeperimagefeaturelearningmodel AT snarayanan multilayervectorizationtodevelopadeeperimagefeaturelearningmodel AT anandakumarhaldorai multilayervectorizationtodevelopadeeperimagefeaturelearningmodel |