A novel technique for texture description and image classification based in RGB compositions
Abstract At present, facial recognition entertains great importance in performing authentication processes, because it prevents unauthorized access to devices and places. Additionally, it allows for the identification of persons. Henceforth, this paper proposes a novel texture descriptor called Cycl...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-06-01
|
| Series: | IET Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cmu2.12601 |
| _version_ | 1797808456450703360 |
|---|---|
| author | Carlos Eduardo Padilla Leyferman José Trinidad Guillen Bonilla Juan Carlos Estrada Gutiérrez Maricela Jiménez Rodríguez |
| author_facet | Carlos Eduardo Padilla Leyferman José Trinidad Guillen Bonilla Juan Carlos Estrada Gutiérrez Maricela Jiménez Rodríguez |
| author_sort | Carlos Eduardo Padilla Leyferman |
| collection | DOAJ |
| description | Abstract At present, facial recognition entertains great importance in performing authentication processes, because it prevents unauthorized access to devices and places. Additionally, it allows for the identification of persons. Henceforth, this paper proposes a novel texture descriptor called Cyclical Chroma and a new classification technique, which takes in consideration the sub‐pixel values of 0–255 for each RGB (Red, Green, Blue) channel that conforms the image. To verify the effectiveness of the proposed techniques, tests were performed with a database of images in a controlled environment and in one under uncontrolled conditions; additionally, Cyclical Chroma was tested with a different classifier, denominated the Multiclass Classifier, and the results were compared against other descriptors, including GLCM, SHDH, LQP, and CCR, demonstrating the effectiveness of the proposed techniques with 100% efficiency with controlled images and 78% effectiveness under uncontrolled conditions prior to the application of an equalization technique, increasing the efficiency to 100%. |
| first_indexed | 2024-03-13T06:37:47Z |
| format | Article |
| id | doaj.art-1c7ac70e62804789b37c0cdc824c8f59 |
| institution | Directory Open Access Journal |
| issn | 1751-8628 1751-8636 |
| language | English |
| last_indexed | 2024-03-13T06:37:47Z |
| publishDate | 2023-06-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj.art-1c7ac70e62804789b37c0cdc824c8f592023-06-09T03:35:55ZengWileyIET Communications1751-86281751-86362023-06-0117101162117610.1049/cmu2.12601A novel technique for texture description and image classification based in RGB compositionsCarlos Eduardo Padilla Leyferman0José Trinidad Guillen Bonilla1Juan Carlos Estrada Gutiérrez2Maricela Jiménez Rodríguez3Department of Technological Sciences, University Center of La CiénegaUniversity of Guadalajara OcotlánJaliscoMéxicoDepartment of Electro‐photonics, University Center of Exact Sciences and EngineeringUniversity of Guadalajara GuadalajaraJaliscoMéxicoDepartment of Technological Sciences, University Center of La CiénegaUniversity of Guadalajara OcotlánJaliscoMéxicoDepartment of Basic SciencesUniversity Center of La CiénegaUniversity of Guadalajara OcotlánJaliscoMéxicoAbstract At present, facial recognition entertains great importance in performing authentication processes, because it prevents unauthorized access to devices and places. Additionally, it allows for the identification of persons. Henceforth, this paper proposes a novel texture descriptor called Cyclical Chroma and a new classification technique, which takes in consideration the sub‐pixel values of 0–255 for each RGB (Red, Green, Blue) channel that conforms the image. To verify the effectiveness of the proposed techniques, tests were performed with a database of images in a controlled environment and in one under uncontrolled conditions; additionally, Cyclical Chroma was tested with a different classifier, denominated the Multiclass Classifier, and the results were compared against other descriptors, including GLCM, SHDH, LQP, and CCR, demonstrating the effectiveness of the proposed techniques with 100% efficiency with controlled images and 78% effectiveness under uncontrolled conditions prior to the application of an equalization technique, increasing the efficiency to 100%.https://doi.org/10.1049/cmu2.12601facial recognitionhistogram matchingimage classificationimage classifiertexture descriptor |
| spellingShingle | Carlos Eduardo Padilla Leyferman José Trinidad Guillen Bonilla Juan Carlos Estrada Gutiérrez Maricela Jiménez Rodríguez A novel technique for texture description and image classification based in RGB compositions IET Communications facial recognition histogram matching image classification image classifier texture descriptor |
| title | A novel technique for texture description and image classification based in RGB compositions |
| title_full | A novel technique for texture description and image classification based in RGB compositions |
| title_fullStr | A novel technique for texture description and image classification based in RGB compositions |
| title_full_unstemmed | A novel technique for texture description and image classification based in RGB compositions |
| title_short | A novel technique for texture description and image classification based in RGB compositions |
| title_sort | novel technique for texture description and image classification based in rgb compositions |
| topic | facial recognition histogram matching image classification image classifier texture descriptor |
| url | https://doi.org/10.1049/cmu2.12601 |
| work_keys_str_mv | AT carloseduardopadillaleyferman anoveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT josetrinidadguillenbonilla anoveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT juancarlosestradagutierrez anoveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT maricelajimenezrodriguez anoveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT carloseduardopadillaleyferman noveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT josetrinidadguillenbonilla noveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT juancarlosestradagutierrez noveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions AT maricelajimenezrodriguez noveltechniquefortexturedescriptionandimageclassificationbasedinrgbcompositions |