Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing
In recent years, deep-network-based hashing has gained prominence in image retrieval for its ability to generate compact and efficient binary representations. However, most existing methods predominantly focus on high-level semantic features extracted from the final layers of networks, often neglect...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/11/1/20 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588258364620800 |
|---|---|
| author | Amina Belalia Kamel Belloulata Adil Redaoui |
| author_facet | Amina Belalia Kamel Belloulata Adil Redaoui |
| author_sort | Amina Belalia |
| collection | DOAJ |
| description | In recent years, deep-network-based hashing has gained prominence in image retrieval for its ability to generate compact and efficient binary representations. However, most existing methods predominantly focus on high-level semantic features extracted from the final layers of networks, often neglecting structural details that are crucial for capturing spatial relationships within images. Achieving a balance between preserving structural information and maximizing retrieval accuracy is the key to effective image hashing and retrieval. To address this challenge, we introduce Multiscale Deep Feature Fusion for Supervised Hashing (MDFF-SH), a novel approach that integrates multiscale feature fusion into the hashing process. The hallmark of MDFF-SH lies in its ability to combine low-level structural features with high-level semantic context, synthesizing robust and compact hash codes. By leveraging multiscale features from multiple convolutional layers, MDFF-SH ensures the preservation of fine-grained image details while maintaining global semantic integrity, achieving a harmonious balance that enhances retrieval precision and recall. Our approach demonstrated a superior performance on benchmark datasets, achieving significant gains in the Mean Average Precision (MAP) compared with the state-of-the-art methods: 9.5% on CIFAR-10, 5% on NUS-WIDE, and 11.5% on MS-COCO. These results highlight the effectiveness of MDFF-SH in bridging structural and semantic information, setting a new standard for high-precision image retrieval through multiscale feature fusion. |
| format | Article |
| id | doaj-art-1e00404f8a03453386d469152538e42e |
| institution | Kabale University |
| issn | 2313-433X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj-art-1e00404f8a03453386d469152538e42e2025-01-24T13:36:18ZengMDPI AGJournal of Imaging2313-433X2025-01-011112010.3390/jimaging11010020Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised HashingAmina Belalia0Kamel Belloulata1Adil Redaoui2High School of Computer Sciences, Sidi Bel Abbes 22000, AlgeriaRCAM Laboratory, Telecommunications Department, Sidi Bel Abbes University, Sidi Bel Abbes 22000, AlgeriaRCAM Laboratory, Telecommunications Department, Sidi Bel Abbes University, Sidi Bel Abbes 22000, AlgeriaIn recent years, deep-network-based hashing has gained prominence in image retrieval for its ability to generate compact and efficient binary representations. However, most existing methods predominantly focus on high-level semantic features extracted from the final layers of networks, often neglecting structural details that are crucial for capturing spatial relationships within images. Achieving a balance between preserving structural information and maximizing retrieval accuracy is the key to effective image hashing and retrieval. To address this challenge, we introduce Multiscale Deep Feature Fusion for Supervised Hashing (MDFF-SH), a novel approach that integrates multiscale feature fusion into the hashing process. The hallmark of MDFF-SH lies in its ability to combine low-level structural features with high-level semantic context, synthesizing robust and compact hash codes. By leveraging multiscale features from multiple convolutional layers, MDFF-SH ensures the preservation of fine-grained image details while maintaining global semantic integrity, achieving a harmonious balance that enhances retrieval precision and recall. Our approach demonstrated a superior performance on benchmark datasets, achieving significant gains in the Mean Average Precision (MAP) compared with the state-of-the-art methods: 9.5% on CIFAR-10, 5% on NUS-WIDE, and 11.5% on MS-COCO. These results highlight the effectiveness of MDFF-SH in bridging structural and semantic information, setting a new standard for high-precision image retrieval through multiscale feature fusion.https://www.mdpi.com/2313-433X/11/1/20content-based image retrievalhashing codedeep learningmultiscale feature extractdeep supervised hashing |
| spellingShingle | Amina Belalia Kamel Belloulata Adil Redaoui Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing Journal of Imaging content-based image retrieval hashing code deep learning multiscale feature extract deep supervised hashing |
| title | Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing |
| title_full | Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing |
| title_fullStr | Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing |
| title_full_unstemmed | Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing |
| title_short | Enhanced Image Retrieval Using Multiscale Deep Feature Fusion in Supervised Hashing |
| title_sort | enhanced image retrieval using multiscale deep feature fusion in supervised hashing |
| topic | content-based image retrieval hashing code deep learning multiscale feature extract deep supervised hashing |
| url | https://www.mdpi.com/2313-433X/11/1/20 |
| work_keys_str_mv | AT aminabelalia enhancedimageretrievalusingmultiscaledeepfeaturefusioninsupervisedhashing AT kamelbelloulata enhancedimageretrievalusingmultiscaledeepfeaturefusioninsupervisedhashing AT adilredaoui enhancedimageretrievalusingmultiscaledeepfeaturefusioninsupervisedhashing |