Image retrieval based on effective feature extraction and diffusion process
Feature extraction and its matching are two critical tasks in image retrieval. This paper presents a new methodology for content-based image retrieval by integrating three features, and then optimizing feature metric by diffusion process. To boost the discriminative power, the color histogram, local...
| Main Authors: | , , , |
|---|---|
| Format: | Journal Article |
| Published: |
Springer
2018
|
| Online Access: | http://hdl.handle.net/20.500.11937/70077 |
| _version_ | 1848762208704528384 |
|---|---|
| author | Zhou, J. Liu, X. Liu, Wan-Quan Gan, J. |
| author_facet | Zhou, J. Liu, X. Liu, Wan-Quan Gan, J. |
| author_sort | Zhou, J. |
| building | Curtin Institutional Repository |
| collection | Online Access |
| description | Feature extraction and its matching are two critical tasks in image retrieval. This paper presents a new methodology for content-based image retrieval by integrating three features, and then optimizing feature metric by diffusion process. To boost the discriminative power, the color histogram, local directional pattern, and dense SIFT features based on bag of features (BoF) are selected. Then diffusion process is applied to seek a global optimization for image matching based on fused multi-features. The diffusion process can capture the intrinsic manifold structure on a dataset, and thus enhance the overall retrieval performance significantly. Finally, a new search strategy is explored to make the diffusion process work even better when the number of retrieval images is small. In order to validate our proposed approach, four benchmark databases are used, and the results of experiments show that the proposed approach outperforms all other existing approaches. |
| first_indexed | 2025-11-14T10:43:55Z |
| format | Journal Article |
| id | curtin-20.500.11937-70077 |
| institution | Curtin University Malaysia |
| institution_category | Local University |
| last_indexed | 2025-11-14T10:43:55Z |
| publishDate | 2018 |
| publisher | Springer |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | curtin-20.500.11937-700772019-04-30T03:43:12Z Image retrieval based on effective feature extraction and diffusion process Zhou, J. Liu, X. Liu, Wan-Quan Gan, J. Feature extraction and its matching are two critical tasks in image retrieval. This paper presents a new methodology for content-based image retrieval by integrating three features, and then optimizing feature metric by diffusion process. To boost the discriminative power, the color histogram, local directional pattern, and dense SIFT features based on bag of features (BoF) are selected. Then diffusion process is applied to seek a global optimization for image matching based on fused multi-features. The diffusion process can capture the intrinsic manifold structure on a dataset, and thus enhance the overall retrieval performance significantly. Finally, a new search strategy is explored to make the diffusion process work even better when the number of retrieval images is small. In order to validate our proposed approach, four benchmark databases are used, and the results of experiments show that the proposed approach outperforms all other existing approaches. 2018 Journal Article http://hdl.handle.net/20.500.11937/70077 10.1007/s11042-018-6192-1 Springer restricted |
| spellingShingle | Zhou, J. Liu, X. Liu, Wan-Quan Gan, J. Image retrieval based on effective feature extraction and diffusion process |
| title | Image retrieval based on effective feature extraction and diffusion process |
| title_full | Image retrieval based on effective feature extraction and diffusion process |
| title_fullStr | Image retrieval based on effective feature extraction and diffusion process |
| title_full_unstemmed | Image retrieval based on effective feature extraction and diffusion process |
| title_short | Image retrieval based on effective feature extraction and diffusion process |
| title_sort | image retrieval based on effective feature extraction and diffusion process |
| url | http://hdl.handle.net/20.500.11937/70077 |