Real-Time Detection of Colour and Surface Defects of Maize Kernels Using Machine Vision

Liao, Ken Ying-Kai; Paulsen, Marvin R; Reid, John F.

doi:10.1006/jaer.1994.1085

Cited by 41 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The quantitative estimate of important characters such as colour, dimension and shape of the seeds has found application both for the distinction of cultivars of the same species (Liao et al, 1994;Venora et al, 2006Venora et al, , 2007Wan, 1999), and for the identification of weedy seeds in seed purity analyses (Churchill et al, 1993;Granitto et al, 2003a, b;Petersen and Krutz, 1992). In this way, qualitative features of the seeds were also examined, such as the germination attitude in relation to colour, shapes and sizes (Dell'Aquila, 2006;Jansen, 1995;McDonald et al, 2001).…”

Section: Introductionmentioning

confidence: 97%

Morpho-colorimetric characterization by image analysis to identify diaspores of wild plant species

Bacchetta¹,

Grillo

Mattana³

et al. 2008

Flora - Morphology, Distribution, Functional Ecology of Plants

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 97%

Morpho-colorimetric characterization by image analysis to identify diaspores of wild plant species

Bacchetta¹,

Grillo

Mattana³

et al. 2008

Flora - Morphology, Distribution, Functional Ecology of Plants

View full text Add to dashboard Cite

“…Image analysis was used for the inspection of agricultural products like fruit (Shahin, Tollner, Evans, & Arabnia, 1999a;Schatzki et al, 1997), vegetables (Shahin, Tollner, Gitailis, Summer, & Maw, 1999b) and grain (Wan, 1999;Liao, Paulsen, & Reid, 1994). Morphological, optical and textural characterization measures for classification of many types of grains, e.g.…”

Section: Introductionmentioning

confidence: 99%

Identification of Sicilian landraces and Canadian cultivars of lentil using an image analysis system

Venora¹,

Grillo²,

Shahin³

et al. 2007

Food Research International

View full text Add to dashboard Cite

“…To our knowledge, there have been few reports comparing color models in discrimination among different materials based on their colors. Liao et al (1994) found that the RGB model was more suitable than the HSI model in discriminating between white and yellow maize kernels. The discriminatory power can be attributed to a clear difference in the intensity of blueness.…”

Section: Comparison Of the Color Modelsmentioning

confidence: 96%

Semiquantitative color profiling of soils over a land degradation gradient in Sakaerat, Thailand

Doi

Wachrinrat

Teejuntuk

et al. 2009

Environ Monit Assess

View full text Add to dashboard Cite

In this study, we attempted multivariate color profiling of soils over a land degradation gradient represented by dry evergreen forest (original vegetation), dry deciduous forest (moderately disturbed by fire), and bare ground (severely degraded) in Sakaerat, Thailand. The soils were sampled in a dry-to-wet seasonal transition. Values of the red-green-blue (RGB), cyan-magenta-yellow-key black (CMYK), L*a*b*, and hue-intensity-saturation (HIS) color models were determined using the digital software Adobe Photoshop. Land degradation produced significant variations (p<0.05) in R, C, Y, L*, a*, b*, S, and I values (p<0.05). The seasonal transition produced significant variations (p<0.05) in R, G, B, C, M, K, L*, b*, and I values. In discriminating the soils, the color models did not differ in discriminatory power, while discriminatory power was affected by seasonal changes. Most color variation patterns had nonlinear relationships with the intensity of the land degradation gradient, due to effects of fire that darkened the deciduous forest soil, masking the nature of the soil as the intermediate between the evergreen forest and the bare ground soils. Taking these findings into account, the utilization of color profiling of soils in land conservation and rehabilitation is discussed.

show abstract

Real-Time Detection of Colour and Surface Defects of Maize Kernels Using Machine Vision

Cited by 41 publications

References 0 publications

Morpho-colorimetric characterization by image analysis to identify diaspores of wild plant species

Morpho-colorimetric characterization by image analysis to identify diaspores of wild plant species

Identification of Sicilian landraces and Canadian cultivars of lentil using an image analysis system

Semiquantitative color profiling of soils over a land degradation gradient in Sakaerat, Thailand

Contact Info

Product

Resources

About