Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition
Aiming at the problems in the best basis selection, this paper presents a novel criterion based on the statistical measurement of the curvature wavelet coefficient to dynamically select the single best basis of the quad-tree wavelet packet transformation. The selected single best basis works as an e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9930759/ |
| _version_ | 1797990195549700096 |
|---|---|
| author | Regina Lionnie Catur Apriono Rifai Chai Dadang Gunawan |
| author_facet | Regina Lionnie Catur Apriono Rifai Chai Dadang Gunawan |
| author_sort | Regina Lionnie |
| collection | DOAJ |
| description | Aiming at the problems in the best basis selection, this paper presents a novel criterion based on the statistical measurement of the curvature wavelet coefficient to dynamically select the single best basis of the quad-tree wavelet packet transformation. The selected single best basis works as an extracted feature for biometric periocular recognition system. The proposed method first extracts the mean curvature of wavelet coefficients inside the quad-tree wavelet packet transform. Second, the method finds the most distinctive features based on the largest standard deviation and dynamically selects the extracted curvature wavelet coefficients as the single best basis. Third, the selected single curvature best basis works as an extracted feature, and then it is combined with the histogram of oriented gradients method. Finally, the support vector machine is employed to perform classification. Two datasets of two-dimensional periocular digital images are tested against the proposed method. To show the extended ability, we analyze the curvature best basis method against wavelet functions and characteristics and test the proposed method against the plain face and masked face recognition. The proposed method achieves the highest performance results inside periocular recognition (97.53% accuracy for UBIPr-1 and 97.77% accuracy for EYB-P1), masked face recognition (98.11% accuracy), and plain face recognition (98.26% accuracy). The proposed method is robust against glasses occlusion, artificial geometry transformations, Gaussian and salt pepper noise. Comparison with other works in a similar recognition system shows that our proposed curvature best basis method yields the highest performance results. |
| first_indexed | 2024-04-11T08:32:41Z |
| format | Article |
| id | doaj.art-c071f853e96f48859343ffd31404d3fd |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T08:32:41Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c071f853e96f48859343ffd31404d3fd2022-12-22T04:34:27ZengIEEEIEEE Access2169-35362022-01-011011352311354210.1109/ACCESS.2022.32172439930759Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular RecognitionRegina Lionnie0https://orcid.org/0000-0002-5699-4994Catur Apriono1https://orcid.org/0000-0002-7843-6352Rifai Chai2https://orcid.org/0000-0002-1922-7024Dadang Gunawan3https://orcid.org/0000-0002-6320-003XDepartment of Electrical Engineering, Universitas Indonesia, Kampus Baru UI Depok, Jawa Barat, IndonesiaDepartment of Electrical Engineering, Universitas Indonesia, Kampus Baru UI Depok, Jawa Barat, IndonesiaSchool of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC, AustraliaDepartment of Electrical Engineering, Universitas Indonesia, Kampus Baru UI Depok, Jawa Barat, IndonesiaAiming at the problems in the best basis selection, this paper presents a novel criterion based on the statistical measurement of the curvature wavelet coefficient to dynamically select the single best basis of the quad-tree wavelet packet transformation. The selected single best basis works as an extracted feature for biometric periocular recognition system. The proposed method first extracts the mean curvature of wavelet coefficients inside the quad-tree wavelet packet transform. Second, the method finds the most distinctive features based on the largest standard deviation and dynamically selects the extracted curvature wavelet coefficients as the single best basis. Third, the selected single curvature best basis works as an extracted feature, and then it is combined with the histogram of oriented gradients method. Finally, the support vector machine is employed to perform classification. Two datasets of two-dimensional periocular digital images are tested against the proposed method. To show the extended ability, we analyze the curvature best basis method against wavelet functions and characteristics and test the proposed method against the plain face and masked face recognition. The proposed method achieves the highest performance results inside periocular recognition (97.53% accuracy for UBIPr-1 and 97.77% accuracy for EYB-P1), masked face recognition (98.11% accuracy), and plain face recognition (98.26% accuracy). The proposed method is robust against glasses occlusion, artificial geometry transformations, Gaussian and salt pepper noise. Comparison with other works in a similar recognition system shows that our proposed curvature best basis method yields the highest performance results.https://ieeexplore.ieee.org/document/9930759/Best basiscurvatureperiocular recognitionwavelet packet transform |
| spellingShingle | Regina Lionnie Catur Apriono Rifai Chai Dadang Gunawan Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition IEEE Access Best basis curvature periocular recognition wavelet packet transform |
| title | Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition |
| title_full | Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition |
| title_fullStr | Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition |
| title_full_unstemmed | Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition |
| title_short | Curvature Best Basis: A Novel Criterion to Dynamically Select a Single Best Basis as the Extracted Feature for Periocular Recognition |
| title_sort | curvature best basis a novel criterion to dynamically select a single best basis as the extracted feature for periocular recognition |
| topic | Best basis curvature periocular recognition wavelet packet transform |
| url | https://ieeexplore.ieee.org/document/9930759/ |
| work_keys_str_mv | AT reginalionnie curvaturebestbasisanovelcriteriontodynamicallyselectasinglebestbasisastheextractedfeatureforperiocularrecognition AT caturapriono curvaturebestbasisanovelcriteriontodynamicallyselectasinglebestbasisastheextractedfeatureforperiocularrecognition AT rifaichai curvaturebestbasisanovelcriteriontodynamicallyselectasinglebestbasisastheextractedfeatureforperiocularrecognition AT dadanggunawan curvaturebestbasisanovelcriteriontodynamicallyselectasinglebestbasisastheextractedfeatureforperiocularrecognition |