Virtual Lab for histogram-based binarization of gray level images: Heuristic threshold

• Autor: Montenegro Joo, Javier
• Formato: artículo
• Fecha de Publicación: 2014
• Institución: Universidad Nacional Mayor de San Marcos
• Repositorio: Revistas - Universidad Nacional Mayor de San Marcos
• Lenguaje: español
• OAI Identifier: oai:ojs.csi.unmsm:article/11541
• Enlace del recurso: https://revistasinvestigacion.unmsm.edu.pe/index.php/fisica/article/view/11541
• Nivel de acceso: acceso abierto
• Materia: Virtual Lab; digital image processing; automatic binarization; gray scale histogram; heuristic threshold; Laboratorio virtual; procesamiento digital de imágenes; binarización automática; histograma de niveles de gris; umbral heurístico

The creation of a Virtual Lab, integrated and interactive software, to perform histogram-based binarization of gray scaled images is reported. In an attempt to optimize the binarization the developed virtual lab introduces a Heuristic Binarization Threshold. At processing time, the module extracts the histogram of the input gray scaled image, and then a Heuristic Threshold is calculated by taking the weighted average of the foreground grey levels of the image. Next those pixels in input image whose grey levels are above this threshold are highlighted. Although still not experimentally optimum, this heuristic threshold provides a first approximation towards automatic optimum binarization of grey scaled images. For comparison purposes when an input image is operated on by the binarization module, it is possible to visualize up to three different binarizations on screen simultaneously, each for a different binarization threshold fixed by the user.