EQUALIZING AND SEGMENTING IMAGES USING COLOR INFORMATION

Digital image processing techniques are generally applied to grayscale images, despite the large availability of color images. Although the literature always devotes some topic to the study of processing using colors and, they claim that all processing with grayscale images can be extended to color...

Descripción completa

Detalles Bibliográficos
Autores: Inocêncio, Marcos Vinicius, Artero, Almir Olivette, Eler, Danilo Medeiros, Silva, Francisco Assis da, Pereira, Danillo Roberto
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2020
País:Brasil
Institución:Universidade do Oeste Paulista (UNOESTE)
Repositorio:Colloquium Exactarum
Idioma:portugués
OAI Identifier:oai:ojs.pkp.sfu.ca:article/3501
Acceso en línea:https://journal.unoeste.br/index.php/ce/article/view/3501
Access Level:acceso abierto
Palabra clave:Color image processing; Equalization; Segmentation
Processamento de imagens coloridas; Equalização; Segmentação
Descripción
Sumario:Digital image processing techniques are generally applied to grayscale images, despite the large availability of color images. Although the literature always devotes some topic to the study of processing using colors and, they claim that all processing with grayscale images can be extended to color images, using the three color channels, in practice, the processing of color images still it is very little explored. Thus, this work presents some proposals for using color information in segmentation (using an edge detector) and in image equalization (presents a proposal that avoids the conversion between color models). The results obtained are evaluated through a qualitative and quantitative analysis of the images obtained with traditional processing, using only gray tones and images obtained using the proposed strategies. The results show that different ways of combining color information during the process lead to very different results.