How does Computer vision compare to standard colorimeter in assessing the seed coat color of common bean (Phaseolus vulgaris L.)?

Abstract

Common bean (Phaseolus vulgaris L.) exhibits a wide range of seed coat colors and this morphological trait is widely used in cultivar identification and assessment of diversity within this species. With an advancement in technology and informatics, new methods of assessing seed color are emerging in addition to traditionally used visual observation. Due to a great variety of color measuring techniques, the evaluation of the agreement between methods is needed prior to using the methods interchangeably. Seed coat color in terms of CIE L*a*b* color coordinates of 100 common bean accessions belonging to five mono-colored landraces was assessed using two methods, colorimeter and Computer vision. The percentage difference between the two methods across all samples for L* color coordinate was 5.81%, for a* color coordinate 23.32% and for b* color coordinate 44.44%. According to Bland-Altman difference plot there is a considerable lack of agreement between the two methods. However, using stepwise discriminant analysis revealed that colorimeter method correctly classified 97% of accessions into their respective landrace, while the classification success of the Computer vision was 99%.

Evaluación fenotípica de semillas de haba (Vicia faba L.) colectadas en Nariño-Colombia

“…se analizaron, se confirman los beneficios referidos respecto a la confiabilidad y rapidez de la metodología digital, indicados en otras investigaciones (Varga et al 2019;Di Cecco et al 2019).…”

“…La cuantificación de esta característica, resumida en la tabla 4, puede reducir la subjetividad vinculada con la inspección visual, dotando de valores numéricos para la comparación del germoplasma entre variedades y accesiones, respaldado, además, en el hecho, que no se encontraron diferencias estadísticas, mediante la prueba de T Student, entre el método digital y el espectrofotómetro, presentando una variación inferior a 17 %, que es asumido como aceptable, por Varga et al (2019), al comparar los mismos métodos en semillas de fríjol (Phaseolus vulgaris L.).…”

“…Por último, la correlación entre L*, a* y b* confirma que estos parámetros son dependientes entre sí y aportan cada uno una parte sustancial de información del color de la semilla (Varga et al 2019). L* x b* (r=0,90) presentó una correlación alta positiva a diferencia de las variables L* x a* y a* x b*, con un coeficiente de Pearson de r=-0,83 y -0,76, que muestra la influencia de la saturación de los colores sobre la luminosidad y la presencia de tonalidades marcadas dentro de la colección, con color blanco, rojo, rosado y verde.…”

Seed coat color genetics and genotype × environment effects in yellow beans via machine‐learning and genome‐wide association

“…Automated separation of seed coat and hilum ring and corona areas are substantial because they are all under different genetic controls (Bassett, 2007). Bean seed colors have been measured traditionally with colorimeters(Arns et al, 2018;Erfatpour et al, 2018;Possobom et al, 2015) and more recently with ImageJ (Bassett et al, 2021;Bornowski et al, 2020;Varga et al, 2019), but the seed coat, hilum ring, and corona colors were not separated. Thus, this study has provided a novel, automated method to obtain color values from seed coat pixels.The L* values range from 0 to 100 with 100 being the lightest; positive a* values indicate redness while negative a* indicates greenness; and positive b* indicates yellowness, while negative b* indicates blueness…”

A Low cost and high throughput spectroscopic method for quantification of seed coat colour differences in plain seeded bean (Phaseolus vulgaris L.) germplasm from Western Himalayan Kashmir

“…In terms of deviations from standard colours depicted by δ E, highest mean value was observed in red colour (6012.16) and lowest was recorded for green (18.36) with a mean of 2525.72 across all colours. Varga et al (2019) also characterized seed coat colour in terms of CIE L*a*b* colour coordinates of 100 common bean accessions belonging to ve monocoloured landraces using colourimeter and computer vision. The percentage difference between the two methods across all samples colour coordinates was 5.81%, for L*, 23.32% and for a* and 44.44% for b*.…”