Relationship between color and tannin content in sorghum grain: application of image analysis and artificial neural network

摘要: The relationship between sorghum grain color and tannin content was reported in several references. In this study, 33 phenotypes of differing seed characteristics were collected analyzed by Folin-Ciocalteu method. A computer image analysis method used to determine the all phenotypes. Two methods multiple linear regression artificial neural network (ANN) models developed describe from three input parameters characteristics. goodness fit tested using R2, MS error, bias. technique a suitable estimate through strength. Therefore, quality samples described according parameters: L* (lightness), a* (redness - green red) b* (blueness blue yellow. ANN showed strong samples. (in terms R2), which corresponds training model, higher accuracy prediction compared with equation established (0.96 vs. 0.88). term error lower residuals distribution than that model (0.002 0.006). platform ANN-based may be sorghum.