E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization
This paper presents an extended bio-inspired texture (E-BiT) descriptor for image texture characterization. The E-BiT descriptor combines global ecological concepts of species diversity, evenness, richness, and taxonomic indexes to effectively capture texture patterns at local and global levels whil...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/9/2086 |
| _version_ | 1797602793373040640 |
|---|---|
| author | Steve Tsham Mpinda Ataky Alessandro Lameiras Koerich |
| author_facet | Steve Tsham Mpinda Ataky Alessandro Lameiras Koerich |
| author_sort | Steve Tsham Mpinda Ataky |
| collection | DOAJ |
| description | This paper presents an extended bio-inspired texture (E-BiT) descriptor for image texture characterization. The E-BiT descriptor combines global ecological concepts of species diversity, evenness, richness, and taxonomic indexes to effectively capture texture patterns at local and global levels while maintaining invariance to scale, translation, and permutation. First, we pre-processed the images by normalizing and applying geometric transformations to assess the invariance properties of the proposed descriptor. Next, we assessed the performance of the proposed E-BiT descriptor on four datasets, including histopathological images and natural texture images. Finally, we compared it with the original BiT descriptor and other texture descriptors, such as Haralick, GLCM, and LBP. The E-BiT descriptor achieved state-of-the-art texture classification performance, with accuracy improvements ranging from 0.12% to 20% over other descriptors. In addition, the E-BiT descriptor demonstrated its generic nature by performing well in both natural and histopathologic images. Future work could examine the E-BiT descriptor’s behavior at different spatial scales and resolutions to optimize texture property extraction and improve performance. |
| first_indexed | 2024-03-11T04:20:30Z |
| format | Article |
| id | doaj.art-c367fa1d71994473a5ddc90ac36278a8 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T04:20:30Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-c367fa1d71994473a5ddc90ac36278a82023-11-17T22:48:29ZengMDPI AGElectronics2079-92922023-05-01129208610.3390/electronics12092086E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and CharacterizationSteve Tsham Mpinda Ataky0Alessandro Lameiras Koerich1École de Technologie Supérieure, Université du Québec, 1100, rue Notre-Dame Ouest, Montreal, QC H3C 1K3, CanadaÉcole de Technologie Supérieure, Université du Québec, 1100, rue Notre-Dame Ouest, Montreal, QC H3C 1K3, CanadaThis paper presents an extended bio-inspired texture (E-BiT) descriptor for image texture characterization. The E-BiT descriptor combines global ecological concepts of species diversity, evenness, richness, and taxonomic indexes to effectively capture texture patterns at local and global levels while maintaining invariance to scale, translation, and permutation. First, we pre-processed the images by normalizing and applying geometric transformations to assess the invariance properties of the proposed descriptor. Next, we assessed the performance of the proposed E-BiT descriptor on four datasets, including histopathological images and natural texture images. Finally, we compared it with the original BiT descriptor and other texture descriptors, such as Haralick, GLCM, and LBP. The E-BiT descriptor achieved state-of-the-art texture classification performance, with accuracy improvements ranging from 0.12% to 20% over other descriptors. In addition, the E-BiT descriptor demonstrated its generic nature by performing well in both natural and histopathologic images. Future work could examine the E-BiT descriptor’s behavior at different spatial scales and resolutions to optimize texture property extraction and improve performance.https://www.mdpi.com/2079-9292/12/9/2086pattern recognitiontexture characterizationecological diversity measuresbio-inspired texture descriptor |
| spellingShingle | Steve Tsham Mpinda Ataky Alessandro Lameiras Koerich E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization Electronics pattern recognition texture characterization ecological diversity measures bio-inspired texture descriptor |
| title | E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization |
| title_full | E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization |
| title_fullStr | E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization |
| title_full_unstemmed | E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization |
| title_short | E-BiT: Extended Bio-Inspired Texture Descriptor for 2D Texture Analysis and Characterization |
| title_sort | e bit extended bio inspired texture descriptor for 2d texture analysis and characterization |
| topic | pattern recognition texture characterization ecological diversity measures bio-inspired texture descriptor |
| url | https://www.mdpi.com/2079-9292/12/9/2086 |
| work_keys_str_mv | AT stevetshammpindaataky ebitextendedbioinspiredtexturedescriptorfor2dtextureanalysisandcharacterization AT alessandrolameiraskoerich ebitextendedbioinspiredtexturedescriptorfor2dtextureanalysisandcharacterization |