SciELO - Scientific Electronic Library Online

 
vol.29 número1Lesion Labeling Analysis in LR Assisted by SAM-DR and Segmentation with YOLO v8-obbA Model to Optimize the Allocation of Public Administrative Services índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

  • No hay artículos similaresSimilares en SciELO

Compartir


Computación y Sistemas

versión On-line ISSN 2007-9737versión impresa ISSN 1405-5546

Resumen

GUERRA IBARRA, Juan Pablo  y  CUEVAS DE LA ROSA, Francisco. A Greedy Algorithm for Highlighting of Color Dominance in Tomato Leaves and Fruit Segmentation. Comp. y Sist. [online]. 2025, vol.29, n.1, pp.217-227.  Epub 05-Dic-2025. ISSN 2007-9737.  https://doi.org/10.13053/cys-29-1-5500.

The improvement of agricultural processes in recent years through the application of various technologies, including computational algorithms, has given rise to a field of research called precision agriculture. This field aims to provide the plant with the resources it needs for its development at the right time. Deficiencies of a nutrient element necessary for the development of a plant are mainly manifested in the leaves. In this paper, a greedy algorithm is proposed in order to optimize the segmentation method by color dominance that seeks to emphasize the dominance of the green color present in the leaves and the red of the ripe fruits of tomato plants existing naturally using the RGB color model. The algorithm searches a numerical range for the value that maximizes color dominance, the range is reduced until a stop condition is reached. The objective function to maximize is the average performance when segmenting the pixels of the leaves and fruits. The classification images can be used in the detection of pests, diseases or nutritional deficiencies.

Palabras llave : Optimization; greedy algorithm; segmentation; precision agriculture; computer vision.

        · texto en Inglés     · Inglés ( pdf )