Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval
Spherical harmonic (SH) has shown excellent advantages in terms of accuracy and efficiency in the retrieval of complete three-dimensional shapes. However, since the spherical function directly takes the shape centroid as the global reference point, the SH features depend heavily on the central posit...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9216116/ |
| _version_ | 1819172996956291072 |
|---|---|
| author | Jia Li Zikuan Li Huan Lin Renxi Chen Qiuping Lan |
| author_facet | Jia Li Zikuan Li Huan Lin Renxi Chen Qiuping Lan |
| author_sort | Jia Li |
| collection | DOAJ |
| description | Spherical harmonic (SH) has shown excellent advantages in terms of accuracy and efficiency in the retrieval of complete three-dimensional shapes. However, since the spherical function directly takes the shape centroid as the global reference point, the SH features depend heavily on the central position. In this context, the features become no longer reliable in the query of incomplete shapes that may cause erratic centroid. In this work, we propose a novel shape descriptor, namely spherical harmonic energy over the Gaussian sphere (SHE-GS), especially for the incomplete shape retrieval. Firstly, all unit normal vectors on the shape surface are mapped to points on a Gaussian sphere, which has the constant center. Secondly, kernel density estimation is used to establish a Gaussian Sphere Model (GSM) to describe the density change of these mapping points. Finally, the shape descriptor is generated by applying an SH transformation on the model. According to the way of GSM being regarded as a surface model or a volume model, we have separately designed two specific algorithm implementations. Experimental results, on two engineering shape sets containing artificially defective shapes, indicate that the proposed method outperforms other traditional methods also defined in the sphere space for incomplete shape retrieval. The superiority is verified for both similar objects in the same category or the single specific object of query. |
| first_indexed | 2024-12-22T20:16:04Z |
| format | Article |
| id | doaj.art-2a40431fdd4546c0aaeeb0498f45f989 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T20:16:04Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2a40431fdd4546c0aaeeb0498f45f9892022-12-21T18:13:57ZengIEEEIEEE Access2169-35362020-01-01818311718312610.1109/ACCESS.2020.30291039216116Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape RetrievalJia Li0https://orcid.org/0000-0001-8015-6512Zikuan Li1https://orcid.org/0000-0001-7471-1188Huan Lin2https://orcid.org/0000-0002-3653-8932Renxi Chen3https://orcid.org/0000-0003-2929-2302Qiuping Lan4https://orcid.org/0000-0002-9701-0859School of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaAdvanced Institute of Information Technology (AIIT), Peking University, Hangzhou, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaSchool of Earth Sciences and Engineering, Hohai University, Nanjing, ChinaSpherical harmonic (SH) has shown excellent advantages in terms of accuracy and efficiency in the retrieval of complete three-dimensional shapes. However, since the spherical function directly takes the shape centroid as the global reference point, the SH features depend heavily on the central position. In this context, the features become no longer reliable in the query of incomplete shapes that may cause erratic centroid. In this work, we propose a novel shape descriptor, namely spherical harmonic energy over the Gaussian sphere (SHE-GS), especially for the incomplete shape retrieval. Firstly, all unit normal vectors on the shape surface are mapped to points on a Gaussian sphere, which has the constant center. Secondly, kernel density estimation is used to establish a Gaussian Sphere Model (GSM) to describe the density change of these mapping points. Finally, the shape descriptor is generated by applying an SH transformation on the model. According to the way of GSM being regarded as a surface model or a volume model, we have separately designed two specific algorithm implementations. Experimental results, on two engineering shape sets containing artificially defective shapes, indicate that the proposed method outperforms other traditional methods also defined in the sphere space for incomplete shape retrieval. The superiority is verified for both similar objects in the same category or the single specific object of query.https://ieeexplore.ieee.org/document/9216116/Engineering shapeGaussian sphere model (GSM)incomplete shape retrievalpoint cloudspherical harmonic (SH)surface normal |
| spellingShingle | Jia Li Zikuan Li Huan Lin Renxi Chen Qiuping Lan Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval IEEE Access Engineering shape Gaussian sphere model (GSM) incomplete shape retrieval point cloud spherical harmonic (SH) surface normal |
| title | Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval |
| title_full | Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval |
| title_fullStr | Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval |
| title_full_unstemmed | Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval |
| title_short | Spherical Harmonic Energy Over Gaussian Sphere for Incomplete 3D Shape Retrieval |
| title_sort | spherical harmonic energy over gaussian sphere for incomplete 3d shape retrieval |
| topic | Engineering shape Gaussian sphere model (GSM) incomplete shape retrieval point cloud spherical harmonic (SH) surface normal |
| url | https://ieeexplore.ieee.org/document/9216116/ |
| work_keys_str_mv | AT jiali sphericalharmonicenergyovergaussiansphereforincomplete3dshaperetrieval AT zikuanli sphericalharmonicenergyovergaussiansphereforincomplete3dshaperetrieval AT huanlin sphericalharmonicenergyovergaussiansphereforincomplete3dshaperetrieval AT renxichen sphericalharmonicenergyovergaussiansphereforincomplete3dshaperetrieval AT qiupinglan sphericalharmonicenergyovergaussiansphereforincomplete3dshaperetrieval |