Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures
The excessive use of Internet technology is leading to a massive increase in multimedia content. Fast and effective image retrieval over a wide range of databases is a difficult task in this modern research era. Various content-based image retrieval (CBIR) systems have been developed to store and re...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10792907/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841563270759055360 |
|---|---|
| author | Muhammad Arslan Muhammad Asad Ali Haider Khan Sajid Iqbal Muhammad Nabeel Asghar Abdullah Abdulrhman Alaulamie |
| author_facet | Muhammad Arslan Muhammad Asad Ali Haider Khan Sajid Iqbal Muhammad Nabeel Asghar Abdullah Abdulrhman Alaulamie |
| author_sort | Muhammad Arslan |
| collection | DOAJ |
| description | The excessive use of Internet technology is leading to a massive increase in multimedia content. Fast and effective image retrieval over a wide range of databases is a difficult task in this modern research era. Various content-based image retrieval (CBIR) systems have been developed to store and retrieve related images to meet the needs of these systems. However, the existing systems lack high accuracy due to problems in foreground and background objects distinction and high semantic gap. The proposed model presents a three-phase approach including image analysis, synthesis, and indexing to improve image retrieval efficiency and accuracy by integrating deep features of CNN models. Initially, color images are converted to grayscale images and the analysis phase accelerates the feature extraction process by applying intensity functions, outer boundary detection, thresholding, connected component labeling, and intensity inversion techniques to efficiently process grayscale images. These features are further refined through synthesis phase containing comprehensive steps, such as the use of multi-scale detection, enumeration, local binarization, invariance and covariance computations to improve the precision of the extracted data. The deep features of CNN models such as VGG19, InceptionV3 and AlexNet are combined with hand-crafted feature vectors to overcome semantic gap and improve image content analysis. This fusion provides a significant increase in image retrieval precision. Finally, integrating bag-of-words (BOW) model in indexing phase significantly improves the accuracy of image retrieval. The model is evaluated on Cifar-10, Cifar-100, and Caltech-101 datasets. The results are evaluated in terms of precision, recall, average retrieval precision (ARP), average retrieval recall (ARR), mean average precision (MAP), and mean average recall (MAR). The proposed model achieves MAP of 95% using VGG19, and 92% for both AlexNet and InceptionV3 for Cifar-10 dataset. The results show that the proposed model achieves high precision compared to state-of-the-art methods presented in the literature. |
| format | Article |
| id | doaj-art-1ba592af32f64cf58b6eab9584aca337 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1ba592af32f64cf58b6eab9584aca3372025-01-03T00:01:43ZengIEEEIEEE Access2169-35362025-01-011383485110.1109/ACCESS.2024.351545510792907Deep Image Synthesis, Analysis and Indexing Using Integrated CNN ArchitecturesMuhammad Arslan0https://orcid.org/0009-0007-4422-2421Muhammad Asad1https://orcid.org/0009-0001-5741-4197Ali Haider Khan2https://orcid.org/0000-0002-2393-7600Sajid Iqbal3https://orcid.org/0000-0002-8464-2275Muhammad Nabeel Asghar4https://orcid.org/0000-0002-9487-4344Abdullah Abdulrhman Alaulamie5Faculty of Computer Science, Lahore Garrison University, Lahore, PakistanFaculty of Computer Science, Lahore Garrison University, Lahore, PakistanFaculty of Computer Science, Lahore Garrison University, Lahore, PakistanDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Al-Hofuf, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Al-Hofuf, Saudi ArabiaDepartment of Information Systems, College of Computer Science and Information Technology, King Faisal University, Al-Hofuf, Saudi ArabiaThe excessive use of Internet technology is leading to a massive increase in multimedia content. Fast and effective image retrieval over a wide range of databases is a difficult task in this modern research era. Various content-based image retrieval (CBIR) systems have been developed to store and retrieve related images to meet the needs of these systems. However, the existing systems lack high accuracy due to problems in foreground and background objects distinction and high semantic gap. The proposed model presents a three-phase approach including image analysis, synthesis, and indexing to improve image retrieval efficiency and accuracy by integrating deep features of CNN models. Initially, color images are converted to grayscale images and the analysis phase accelerates the feature extraction process by applying intensity functions, outer boundary detection, thresholding, connected component labeling, and intensity inversion techniques to efficiently process grayscale images. These features are further refined through synthesis phase containing comprehensive steps, such as the use of multi-scale detection, enumeration, local binarization, invariance and covariance computations to improve the precision of the extracted data. The deep features of CNN models such as VGG19, InceptionV3 and AlexNet are combined with hand-crafted feature vectors to overcome semantic gap and improve image content analysis. This fusion provides a significant increase in image retrieval precision. Finally, integrating bag-of-words (BOW) model in indexing phase significantly improves the accuracy of image retrieval. The model is evaluated on Cifar-10, Cifar-100, and Caltech-101 datasets. The results are evaluated in terms of precision, recall, average retrieval precision (ARP), average retrieval recall (ARR), mean average precision (MAP), and mean average recall (MAR). The proposed model achieves MAP of 95% using VGG19, and 92% for both AlexNet and InceptionV3 for Cifar-10 dataset. The results show that the proposed model achieves high precision compared to state-of-the-art methods presented in the literature.https://ieeexplore.ieee.org/document/10792907/Deep image retrievalimage retrievalCNN-based image retrievalcolor image retrieval |
| spellingShingle | Muhammad Arslan Muhammad Asad Ali Haider Khan Sajid Iqbal Muhammad Nabeel Asghar Abdullah Abdulrhman Alaulamie Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures IEEE Access Deep image retrieval image retrieval CNN-based image retrieval color image retrieval |
| title | Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures |
| title_full | Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures |
| title_fullStr | Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures |
| title_full_unstemmed | Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures |
| title_short | Deep Image Synthesis, Analysis and Indexing Using Integrated CNN Architectures |
| title_sort | deep image synthesis analysis and indexing using integrated cnn architectures |
| topic | Deep image retrieval image retrieval CNN-based image retrieval color image retrieval |
| url | https://ieeexplore.ieee.org/document/10792907/ |
| work_keys_str_mv | AT muhammadarslan deepimagesynthesisanalysisandindexingusingintegratedcnnarchitectures AT muhammadasad deepimagesynthesisanalysisandindexingusingintegratedcnnarchitectures AT alihaiderkhan deepimagesynthesisanalysisandindexingusingintegratedcnnarchitectures AT sajidiqbal deepimagesynthesisanalysisandindexingusingintegratedcnnarchitectures AT muhammadnabeelasghar deepimagesynthesisanalysisandindexingusingintegratedcnnarchitectures AT abdullahabdulrhmanalaulamie deepimagesynthesisanalysisandindexingusingintegratedcnnarchitectures |