SciELO - Scientific Electronic Library Online

 
vol.37 suppl.1Efecto de la madurez en la crioconservación de semillas de Nicotiana tabacum L.Citotoxicidad de una aspartil peptidasa de Salpichroa origanifolia frente a la infección causada por Phytophthora capsici en zapallitos verdes (Cucurbita maxima, var. Zapallito) índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

  • No hay articulos citadosCitado por SciELO

Links relacionados

  • No hay articulos similaresSimilares en SciELO

Compartir


Cultivos Tropicales

versión impresa ISSN 0258-5936versión On-line ISSN 1819-4087

Resumen

MARTINEZ-ESPINOSA, Yunieski; PEREZ-RODRIGUEZ, Juan L; SANTIESTEBAN-TOCA, Cosme E  y  BAEZ-PEREZ, Evelio L. Computer system to count seeds of Nicotiana tabacum. cultrop [online]. 2016, vol.37, suppl.1, pp.106-110. ISSN 0258-5936.

In Cuba, conservation of Nicotiana tabacum is vital because it is one of the main items on the export and sustainability of the economy. The experimental station of Cabaiguán in Sancti Spiritus, whose functions include the conservation of genetic material from Nicotiana tabacum. Due to the small size of these seeds (0,1-0,5 mm), quantification has become one of the main problems, showing inconsistency in results of the count (high error rate) of a specialist to another, labor intensive and time lost. Therefore, it is propose to develop a computer system for quantification of Nicotiana tabacum seeds, based on techniques of digital image processing. Seedsimagesare captured ingray levelsina conventionalscanner. Image segmentation is performed by thresholding the histogram from the frequency of gray levels. Impurities and image noise are eliminated from size. The average seed size and number of seeds present in each cluster is calculated. Finally, the number of seeds in the image is determined. To assess the quality and effectiveness of the proposed system an experimental validation was performed on 15 images containing 1492 seeds for different resolutions (150 dpi, 300 dpi, 600 dpi and 1200 dpi). Statistical results prove the ability of the system to count seeds with an accuracy above 99 % for the same or higher than 300 dpi resolutions

Palabras clave : quality; genetic material; digital image processing.

        · resumen en Español     · texto en Español     · Español ( pdf )

 

Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons