3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination
Recently, extensive research efforts have been dedicated to view-based 3D object retrieval, owing to its advantage of using a set of 2D images to represent 3D objects. Some existing image processing technologies can be employed. In this paper, we adopt Bag-of-Words for view-based 3D object retrieval...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/22/11523 |
| _version_ | 1797465996358844416 |
|---|---|
| author | Yuefan Hu Haoxuan Zhang Jing Gao Nan Li |
| author_facet | Yuefan Hu Haoxuan Zhang Jing Gao Nan Li |
| author_sort | Yuefan Hu |
| collection | DOAJ |
| description | Recently, extensive research efforts have been dedicated to view-based 3D object retrieval, owing to its advantage of using a set of 2D images to represent 3D objects. Some existing image processing technologies can be employed. In this paper, we adopt Bag-of-Words for view-based 3D object retrieval. Instead of SIFT, DSP-SIFT is extracted from all images as object features. Moreover, two codebooks of the same size are generated by approximate k-means. Then, we combine two codebooks to correct the quantization artifacts and improve recall. Bayes merging is applied to address the codebook correlation (overlapping among different vocabularies) and to provide the benefit of high recall. Moreover, Approximate Nearest Neighbor (ANN) is used to quantization. Experimental results on ETH-80 datasets show that our method improves the performance significantly compared with the state-of-the-art approaches. |
| first_indexed | 2024-03-09T18:30:32Z |
| format | Article |
| id | doaj.art-a3988cfacf1b4eac8a378eb1a2298bc4 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T18:30:32Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a3988cfacf1b4eac8a378eb1a2298bc42023-11-24T07:36:40ZengMDPI AGApplied Sciences2076-34172022-11-0112221152310.3390/app1222115233D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook CombinationYuefan Hu0Haoxuan Zhang1Jing Gao2Nan Li3Computational Aerodynamics Institute, China Aerodynamics Research and Development Center, Mianyang 621000, ChinaSchool of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, ChinaInformation Network Center, Beijing Technology and Business University, Beijing 100048, ChinaSchool of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, ChinaRecently, extensive research efforts have been dedicated to view-based 3D object retrieval, owing to its advantage of using a set of 2D images to represent 3D objects. Some existing image processing technologies can be employed. In this paper, we adopt Bag-of-Words for view-based 3D object retrieval. Instead of SIFT, DSP-SIFT is extracted from all images as object features. Moreover, two codebooks of the same size are generated by approximate k-means. Then, we combine two codebooks to correct the quantization artifacts and improve recall. Bayes merging is applied to address the codebook correlation (overlapping among different vocabularies) and to provide the benefit of high recall. Moreover, Approximate Nearest Neighbor (ANN) is used to quantization. Experimental results on ETH-80 datasets show that our method improves the performance significantly compared with the state-of-the-art approaches.https://www.mdpi.com/2076-3417/12/22/11523view-based 3D model retrievalBag-of-Wordscodebook combinationBayes merging |
| spellingShingle | Yuefan Hu Haoxuan Zhang Jing Gao Nan Li 3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination Applied Sciences view-based 3D model retrieval Bag-of-Words codebook combination Bayes merging |
| title | 3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination |
| title_full | 3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination |
| title_fullStr | 3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination |
| title_full_unstemmed | 3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination |
| title_short | 3D Model Retrieval Algorithm Based on DSP-SIFT Descriptor and Codebook Combination |
| title_sort | 3d model retrieval algorithm based on dsp sift descriptor and codebook combination |
| topic | view-based 3D model retrieval Bag-of-Words codebook combination Bayes merging |
| url | https://www.mdpi.com/2076-3417/12/22/11523 |
| work_keys_str_mv | AT yuefanhu 3dmodelretrievalalgorithmbasedondspsiftdescriptorandcodebookcombination AT haoxuanzhang 3dmodelretrievalalgorithmbasedondspsiftdescriptorandcodebookcombination AT jinggao 3dmodelretrievalalgorithmbasedondspsiftdescriptorandcodebookcombination AT nanli 3dmodelretrievalalgorithmbasedondspsiftdescriptorandcodebookcombination |