Articles producció científica> Enginyeria Informàtica i Matemàtiques

Enhancing spatio-chromatic representation with more-Than-Three color coding for image description

  • Datos identificativos

    Identificador: imarina:9285536
    Autores:
    Rafegas IVazquez-Corral JBenavente RVanrell MAlvarez S
    Resumen:
    The extraction of spatio-chromatic features from color images is usually performed independently on each color channel. Usual 3D color spaces, such as RGB, present a high inter-channel correlation for natural images. This correlation can be reduced using color-opponent representations, but the spatial structure of regions with small color differences is not fully captured in two generic Red-Green and Blue-Yellow channels. To overcome these problems, we propose new color coding that is adapted to the specific content of each image. Our proposal is based on two steps: (a) setting the number of channels to the number of distinctive colors we find in each image (avoiding the problem of channel correlation), and (b) building a channel representation that maximizes contrast differences within each color channel (avoiding the problem of low local contrast). We call this approach morethan-three color coding (MTT) to emphasize the fact that the number of channels is adapted to the image content. The higher the color complexity of an image, the more channels can be used to represent it. Here we select distinctive colors as the most predominant in the image, which we call color pivots, and we build the new color coding strategy using these color pivots as a basis. To evaluate the proposed approach, we measure the efficiency in an image categorization task. We show how a generic descriptor improves performance at the description level when applied to the MTT coding. © 2017 Optical Society of America.
  • Otros:

    Autor según el artículo: Rafegas I; Vazquez-Corral J; Benavente R; Vanrell M; Alvarez S
    Departamento: Enginyeria Informàtica i Matemàtiques
    Autor/es de la URV: Alvarez Fernandez, Susana Maria
    Palabras clave: Spatial structure Pattern recognition Image descriptions Image coding Image categorization Image analysis Human experiment Human Color difference Color complexity Color Codes (symbols) Chromatic features Channel representation Channel correlation Article
    Resumen: The extraction of spatio-chromatic features from color images is usually performed independently on each color channel. Usual 3D color spaces, such as RGB, present a high inter-channel correlation for natural images. This correlation can be reduced using color-opponent representations, but the spatial structure of regions with small color differences is not fully captured in two generic Red-Green and Blue-Yellow channels. To overcome these problems, we propose new color coding that is adapted to the specific content of each image. Our proposal is based on two steps: (a) setting the number of channels to the number of distinctive colors we find in each image (avoiding the problem of channel correlation), and (b) building a channel representation that maximizes contrast differences within each color channel (avoiding the problem of low local contrast). We call this approach morethan-three color coding (MTT) to emphasize the fact that the number of channels is adapted to the image content. The higher the color complexity of an image, the more channels can be used to represent it. Here we select distinctive colors as the most predominant in the image, which we call color pivots, and we build the new color coding strategy using these color pivots as a basis. To evaluate the proposed approach, we measure the efficiency in an image categorization task. We show how a generic descriptor improves performance at the description level when applied to the MTT coding. © 2017 Optical Society of America.
    Áreas temáticas: Sociología Psicología Optics Medicine (miscellaneous) Medicina ii Materiais Matemática / probabilidade e estatística Interdisciplinar Ensino Engenharias iv Electronic, optical and magnetic materials Computer vision and pattern recognition Ciências biológicas i Ciências agrárias i Ciência da computação Atomic and molecular physics, and optics Astronomia / física
    Acceso a la licencia de uso: https://creativecommons.org/licenses/by/3.0/es/
    Direcció de correo del autor: susana.alvarez@urv.cat
    Identificador del autor: 0000-0002-1376-2034
    Fecha de alta del registro: 2024-07-27
    Versión del articulo depositado: info:eu-repo/semantics/acceptedVersion
    Enlace a la fuente original: https://opg.optica.org/josaa/abstract.cfm?uri=josaa-34-5-827
    URL Documento de licencia: https://repositori.urv.cat/ca/proteccio-de-dades/
    Referencia al articulo segun fuente origial: Journal Of The Optical Society Of America A-Optics Image Science And Vision. 34 (5): 827-837
    Referencia de l'ítem segons les normes APA: Rafegas I; Vazquez-Corral J; Benavente R; Vanrell M; Alvarez S (2017). Enhancing spatio-chromatic representation with more-Than-Three color coding for image description. Journal Of The Optical Society Of America A-Optics Image Science And Vision, 34(5), 827-837. DOI: 10.1364/JOSAA.34.000827
    DOI del artículo: 10.1364/JOSAA.34.000827
    Entidad: Universitat Rovira i Virgili
    Año de publicación de la revista: 2017
    Tipo de publicación: Journal Publications
  • Palabras clave:

    Atomic and Molecular Physics, and Optics,Computer Vision and Pattern Recognition,Electronic, Optical and Magnetic Materials,Medicine (Miscellaneous),Optics
    Spatial structure
    Pattern recognition
    Image descriptions
    Image coding
    Image categorization
    Image analysis
    Human experiment
    Human
    Color difference
    Color complexity
    Color
    Codes (symbols)
    Chromatic features
    Channel representation
    Channel correlation
    Article
    Sociología
    Psicología
    Optics
    Medicine (miscellaneous)
    Medicina ii
    Materiais
    Matemática / probabilidade e estatística
    Interdisciplinar
    Ensino
    Engenharias iv
    Electronic, optical and magnetic materials
    Computer vision and pattern recognition
    Ciências biológicas i
    Ciências agrárias i
    Ciência da computação
    Atomic and molecular physics, and optics
    Astronomia / física
  • Documentos:

  • Cerca a google

    Search to google scholar